Recent GenAI Papers I Read.

FMBasic

Recent Readings for Basic Topics of Foundation Models (since 2022) (Index of Posts):

No. Read Date Title and Information We Read @
1 2025, Apr, 25 LLM Post-training 2025-S4
2 2025, Apr, 18 Inference test time scaling law 2025-S4
3 2025, Apr, 13 Model Interpretibility for FM 2025-S4
4 2025, Apr, 9 multimodal FMs - video / audio 2025-S4
5 2025, Apr, 4 More Model Serving Readings - SGlang + Chunked Prefill 2025-S4
6 2025, Apr, 2 LLM Alignment - PPO 2025-S4
7 2025, Jan, 20 more LLM basics - a survey 2025-S2
8 2025, Jan, 15 LLM basics - emergent ability and GenAI platform 2025-S1
9 2025, Jan, 13 Introduction 2025-S0
10 2024, Feb, 8 Open Source LLM - Mistral Data preparation 2024-S6
11 2024, Feb, 6 Survey human alignment 2024-S5
12 2024, Jan, 30 LLM evaluating framework 2024-S3
13 2024, Jan, 23 LLM basics 2024-S1
14 2022, Dec, 3 RLHF + InstructGPT 2022-W6
15 2022, Dec, 1 Stable diffusion + DreamBooth + LoRA 2022-W5
16 2022, Oct, 1 Emergent Abilities of LLM 2022-W4
17 2022, May, 3 A Generalist Agent + offline RL + UniMask 2022-W1


Here is a detailed list of posts!


[1]: LLM Post-training

read on: - 25 Apr 2025
Customization

In this session, our readings cover:

Required PPO readings

Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study

  • Shusheng Xu, Wei Fu, Jiaxuan Gao, Wenjie Ye, Weilin Liu, Zhiyu Mei, Guangju Wang, Chao Yu, Yi Wu
  • [Submitted on 16 Apr 2024 (v1), last revised 10 Oct 2024 (this version, v3)]
  • Reinforcement Learning from Human Feedback (RLHF) is currently the most widely used method to align large language models (LLMs) with human preferences. Existing RLHF methods can be roughly categorized as either reward-based or reward-free. Novel applications such as ChatGPT and Claude leverage reward-based methods that first learn a reward model and apply actor-critic algorithms, such as Proximal Policy Optimization (PPO). However, in academic benchmarks, state-of-the-art results are often achieved via reward-free methods, such as Direct Preference Optimization (DPO). Is DPO truly superior to PPO? Why does PPO perform poorly on these benchmarks? In this paper, we first conduct both theoretical and empirical studies on the algorithmic properties of DPO and show that DPO may have fundamental limitations. Moreover, we also comprehensively examine PPO and reveal the key factors for the best performances of PPO in fine-tuning LLMs. Finally, we benchmark DPO and PPO across a collection of RLHF testbeds, ranging from dialogue to code generation. Experiment results demonstrate that PPO is able to surpass other alignment methods in all cases and achieve state-of-the-art results in challenging code competitions. Our code is publicly available at this https URL.

Tulu 3: Pushing Frontiers in Open Language Model Post-Training

  • URL
  • [Submitted on 22 Nov 2024 (v1), last revised 29 Jan 2025 (this version, v3)]
  • Nathan Lambert, Jacob Morrison, Valentina Pyatkin, Shengyi Huang, Hamish Ivison, Faeze Brahman, Lester James V. Miranda, Alisa Liu, Nouha Dziri, Shane Lyu, Yuling Gu, Saumya Malik, Victoria Graf, Jena D. Hwang, Jiangjiang Yang, Ronan Le Bras, Oyvind Tafjord, Chris Wilhelm, Luca Soldaini, Noah A. Smith, Yizhong Wang, Pradeep Dasigi, Hannaneh Hajishirzi
  • Language model post-training is applied to refine behaviors and unlock new skills across a wide range of recent language models, but open recipes for applying these techniques lag behind proprietary ones. The underlying training data and recipes for post-training are simultaneously the most important pieces of the puzzle and the portion with the least transparency. To bridge this gap, we introduce Tulu 3, a family of fully-open state-of-the-art post-trained models, alongside its data, code, and training recipes, serving as a comprehensive guide for modern post-training techniques. Tulu 3, which builds on Llama 3.1 base models, achieves results surpassing the instruct versions of Llama 3.1, Qwen 2.5, Mistral, and even closed models such as GPT-4o-mini and Claude 3.5-Haiku. The training algorithms for our models include supervised finetuning (SFT), Direct Preference Optimization (DPO), and a novel method we call Reinforcement Learning with Verifiable Rewards (RLVR). With Tulu 3, we introduce a multi-task evaluation scheme for post-training recipes with development and unseen evaluations, standard benchmark implementations, and substantial decontamination of existing open datasets on said benchmarks. We conclude with analysis and discussion of training methods that did not reliably improve performance. In addition to the Tulu 3 model weights and demo, we release the complete recipe – including datasets for diverse core skills, a robust toolkit for data curation and evaluation, the training code and infrastructure, and, most importantly, a detailed report for reproducing and further adapting the Tulu 3 approach to more domains.

More Readings:

[2]: Inference test time scaling law

read on: - 18 Apr 2025
Scaling

In this session, our readings cover:

Required Readings:

What, How, Where, and How Well? A Survey on Test-Time Scaling in Large Language Models

  • [Submitted on 31 Mar 2025]
  • Qiyuan Zhang, Fuyuan Lyu, Zexu Sun, Lei Wang, Weixu Zhang, Zhihan Guo, Yufei Wang, Irwin King, Xue Liu, Chen Ma
  • As enthusiasm for scaling computation (data and parameters) in the pretraining era gradually diminished, test-time scaling (TTS), also referred to as ``test-time computing’’ has emerged as a prominent research focus. Recent studies demonstrate that TTS can further elicit the problem-solving capabilities of large language models (LLMs), enabling significant breakthroughs not only in specialized reasoning tasks, such as mathematics and coding, but also in general tasks like open-ended Q&A. However, despite the explosion of recent efforts in this area, there remains an urgent need for a comprehensive survey offering a systemic understanding. To fill this gap, we propose a unified, multidimensional framework structured along four core dimensions of TTS research: what to scale, how to scale, where to scale, and how well to scale. Building upon this taxonomy, we conduct an extensive review of methods, application scenarios, and assessment aspects, and present an organized decomposition that highlights the unique functional roles of individual techniques within the broader TTS landscape. From this analysis, we distill the major developmental trajectories of TTS to date and offer hands-on guidelines for practical deployment. Furthermore, we identify several open challenges and offer insights into promising future directions, including further scaling, clarifying the functional essence of techniques, generalizing to more tasks, and more attributions.

Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

  • [Submitted on 6 Aug 2024]
  • URL
  • Charlie Snell, Jaehoon Lee, Kelvin Xu, Aviral Kumar
  • Enabling LLMs to improve their outputs by using more test-time computation is a critical step towards building generally self-improving agents that can operate on open-ended natural language. In this paper, we study the scaling of inference-time computation in LLMs, with a focus on answering the question: if an LLM is allowed to use a fixed but non-trivial amount of inference-time compute, how much can it improve its performance on a challenging prompt? Answering this question has implications not only on the achievable performance of LLMs, but also on the future of LLM pretraining and how one should tradeoff inference-time and pre-training compute. Despite its importance, little research attempted to understand the scaling behaviors of various test-time inference methods. Moreover, current work largely provides negative results for a number of these strategies. In this work, we analyze two primary mechanisms to scale test-time computation: (1) searching against dense, process-based verifier reward models; and (2) updating the model’s distribution over a response adaptively, given the prompt at test time. We find that in both cases, the effectiveness of different approaches to scaling test-time compute critically varies depending on the difficulty of the prompt. This observation motivates applying a “compute-optimal” scaling strategy, which acts to most effectively allocate test-time compute adaptively per prompt. Using this compute-optimal strategy, we can improve the efficiency of test-time compute scaling by more than 4x compared to a best-of-N baseline. Additionally, in a FLOPs-matched evaluation, we find that on problems where a smaller base model attains somewhat non-trivial success rates, test-time compute can be used to outperform a 14x larger model.

s1: Simple test-time scaling

  • https://arxiv.org/abs/2501.19393
  • Niklas Muennighoff, Zitong Yang, Weijia Shi, Xiang Lisa Li, Li Fei-Fei, Hannaneh Hajishirzi, Luke Zettlemoyer, Percy Liang, Emmanuel Candès, Tatsunori Hashimoto
  • Test-time scaling is a promising new approach to language modeling that uses extra test-time compute to improve performance. Recently, OpenAI’s o1 model showed this capability but did not publicly share its methodology, leading to many replication efforts. We seek the simplest approach to achieve test-time scaling and strong reasoning performance. First, we curate a small dataset s1K of 1,000 questions paired with reasoning traces relying on three criteria we validate through ablations: difficulty, diversity, and quality. Second, we develop budget forcing to control test-time compute by forcefully terminating the model’s thinking process or lengthening it by appending “Wait” multiple times to the model’s generation when it tries to end. This can lead the model to double-check its answer, often fixing incorrect reasoning steps. After supervised finetuning the Qwen2.5-32B-Instruct language model on s1K and equipping it with budget forcing, our model s1-32B exceeds o1-preview on competition math questions by up to 27% (MATH and AIME24). Further, scaling s1-32B with budget forcing allows extrapolating beyond its performance without test-time intervention: from 50% to 57% on AIME24. Our model, data, and code are open-source at this https URL

More Readings:

Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models

  • [Submitted on 1 Aug 2024 (v1), last revised 14 Oct 2024 (this version, v2)]
  • Yangzhen Wu, Zhiqing Sun, Shanda Li, Sean Welleck, Yiming Yang
  • While the scaling laws of large language models (LLMs) training have been extensively studied, optimal inference configurations of LLMs remain underexplored. We study inference scaling laws and compute-optimal inference, focusing on the trade-offs between model sizes and generating additional tokens with different inference strategies. As a first step towards understanding and designing compute-optimal inference methods, we studied cost-performance trade-offs for inference strategies such as greedy search, majority voting, best-of-n, weighted voting, and two different tree search algorithms, using different model sizes and compute budgets. Our findings indicate smaller models (e.g., Llemma-7B) can outperform larger models given the same computation budgets, and that smaller models paired with advanced inference algorithms yield Pareto-optimal cost-performance trade-offs. For instance, the Llemma-7B model, equipped with our novel tree search algorithm, consistently outperforms Llemma-34B with standard majority voting on the MATH benchmark across all FLOPs budgets. We hope these findings contribute to a broader understanding of inference scaling laws for LLMs.

[3]: Model Interpretibility for FM

read on: - 13 Apr 2025
Safety

In this session, our readings cover:

Required Readings:

Open Problems in Mechanistic Interpretability

  • [Submitted on 27 Jan 2025]
  • Lee Sharkey, Bilal Chughtai, Joshua Batson, Jack Lindsey, Jeff Wu, Lucius Bushnaq, Nicholas Goldowsky-Dill, Stefan Heimersheim, Alejandro Ortega, Joseph Bloom, Stella Biderman, Adria Garriga-Alonso, Arthur Conmy, Neel Nanda, Jessica Rumbelow, Martin Wattenberg, Nandi Schoots, Joseph Miller, Eric J. Michaud, Stephen Casper, Max Tegmark, William Saunders, David Bau, Eric Todd, Atticus Geiger, Mor Geva, Jesse Hoogland, Daniel Murfet, Tom McGrath
  • Mechanistic interpretability aims to understand the computational mechanisms underlying neural networks’ capabilities in order to accomplish concrete scientific and engineering goals. Progress in this field thus promises to provide greater assurance over AI system behavior and shed light on exciting scientific questions about the nature of intelligence. Despite recent progress toward these goals, there are many open problems in the field that require solutions before many scientific and practical benefits can be realized: Our methods require both conceptual and practical improvements to reveal deeper insights; we must figure out how best to apply our methods in pursuit of specific goals; and the field must grapple with socio-technical challenges that influence and are influenced by our work. This forward-facing review discusses the current frontier of mechanistic interpretability and the open problems that the field may benefit from prioritizing.

Position-aware Automatic Circuit Discovery

  • Tal Haklay, Hadas Orgad, David Bau, Aaron Mueller, Yonatan Belinkov
  • A widely used strategy to discover and understand language model mechanisms is circuit analysis. A circuit is a minimal subgraph of a model’s computation graph that executes a specific task. We identify a gap in existing circuit discovery methods: they assume circuits are position-invariant, treating model components as equally relevant across input positions. This limits their ability to capture cross-positional interactions or mechanisms that vary across positions. To address this gap, we propose two improvements to incorporate positionality into circuits, even on tasks containing variable-length examples. First, we extend edge attribution patching, a gradient-based method for circuit discovery, to differentiate between token positions. Second, we introduce the concept of a dataset schema, which defines token spans with similar semantics across examples, enabling position-aware circuit discovery in datasets with variable length examples. We additionally develop an automated pipeline for schema generation and application using large language models. Our approach enables fully automated discovery of position-sensitive circuits, yielding better trade-offs between circuit size and faithfulness compared to prior work.

More Readings:

Mechanistic Interpretability for AI Safety – A Review

  • [Submitted on 22 Apr 2024 (v1), last revised 23 Aug 2024 (this version, v3)]
  • Leonard Bereska, Efstratios Gavves
  • Understanding AI systems’ inner workings is critical for ensuring value alignment and safety. This review explores mechanistic interpretability: reverse engineering the computational mechanisms and representations learned by neural networks into human-understandable algorithms and concepts to provide a granular, causal understanding. We establish foundational concepts such as features encoding knowledge within neural activations and hypotheses about their representation and computation. We survey methodologies for causally dissecting model behaviors and assess the relevance of mechanistic interpretability to AI safety. We examine benefits in understanding, control, alignment, and risks such as capability gains and dual-use concerns. We investigate challenges surrounding scalability, automation, and comprehensive interpretation. We advocate for clarifying concepts, setting standards, and scaling techniques to handle complex models and behaviors and expand to domains such as vision and reinforcement learning. Mechanistic interpretability could help prevent catastrophic outcomes as AI systems become more powerful and inscrutable. Comments: Accepted to TMLR; for an HTML version, visit this https URL

Linearity of Relation Decoding in Transformer Language Models

  • Evan Hernandez, Arnab Sen Sharma, Tal Haklay, Kevin Meng, Martin Wattenberg, Jacob Andreas, Yonatan Belinkov, David Bau
  • Much of the knowledge encoded in transformer language models (LMs) may be expressed in terms of relations: relations between words and their synonyms, entities and their attributes, etc. We show that, for a subset of relations, this computation is well-approximated by a single linear transformation on the subject representation. Linear relation representations may be obtained by constructing a first-order approximation to the LM from a single prompt, and they exist for a variety of factual, commonsense, and linguistic relations. However, we also identify many cases in which LM predictions capture relational knowledge accurately, but this knowledge is not linearly encoded in their representations. Our results thus reveal a simple, interpretable, but heterogeneously deployed knowledge representation strategy in transformer LMs.

Claude’s extended thinking

  • https://www.anthropic.com/news/visible-extended-thinking

Mapping the Mind of a Large Language Model

Using Dictionary Learning Features as Classifiers

Jailbreaking LLM-Controlled Robots

  • [Submitted on 17 Oct 2024 (v1), last revised 9 Nov 2024 (this version, v2)]
  • Alexander Robey, Zachary Ravichandran, Vijay Kumar, Hamed Hassani, George J. Pappas
  • The recent introduction of large language models (LLMs) has revolutionized the field of robotics by enabling contextual reasoning and intuitive human-robot interaction in domains as varied as manipulation, locomotion, and self-driving vehicles. When viewed as a stand-alone technology, LLMs are known to be vulnerable to jailbreaking attacks, wherein malicious prompters elicit harmful text by bypassing LLM safety guardrails. To assess the risks of deploying LLMs in robotics, in this paper, we introduce RoboPAIR, the first algorithm designed to jailbreak LLM-controlled robots. Unlike existing, textual attacks on LLM chatbots, RoboPAIR elicits harmful physical actions from LLM-controlled robots, a phenomenon we experimentally demonstrate in three scenarios: (i) a white-box setting, wherein the attacker has full access to the NVIDIA Dolphins self-driving LLM, (ii) a gray-box setting, wherein the attacker has partial access to a Clearpath Robotics Jackal UGV robot equipped with a GPT-4o planner, and (iii) a black-box setting, wherein the attacker has only query access to the GPT-3.5-integrated Unitree Robotics Go2 robot dog. In each scenario and across three new datasets of harmful robotic actions, we demonstrate that RoboPAIR, as well as several static baselines, finds jailbreaks quickly and effectively, often achieving 100% attack success rates. Our results reveal, for the first time, that the risks of jailbroken LLMs extend far beyond text generation, given the distinct possibility that jailbroken robots could cause physical damage in the real world. Indeed, our results on the Unitree Go2 represent the first successful jailbreak of a deployed commercial robotic system. Addressing this emerging vulnerability is critical for ensuring the safe deployment of LLMs in robotics. Additional media is available at: this https URL

Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities

  • Zora Che, Stephen Casper, Robert Kirk, Anirudh Satheesh, Stewart Slocum, Lev E McKinney, Rohit Gandikota, Aidan Ewart, Domenic Rosati, Zichu Wu, Zikui Cai, Bilal Chughtai, Yarin Gal, Furong Huang, Dylan Hadfield-Menell
  • Evaluations of large language model (LLM) risks and capabilities are increasingly being incorporated into AI risk management and governance frameworks. Currently, most risk evaluations are conducted by designing inputs that elicit harmful behaviors from the system. However, a fundamental limitation of this approach is that the harmfulness of the behaviors identified during any particular evaluation can only lower bound the model’s worst-possible-case behavior. As a complementary method for eliciting harmful behaviors, we propose evaluating LLMs with model tampering attacks which allow for modifications to latent activations or weights. We pit state-of-the-art techniques for removing harmful LLM capabilities against a suite of 5 input-space and 6 model tampering attacks. In addition to benchmarking these methods against each other, we show that (1) model resilience to capability elicitation attacks lies on a low-dimensional robustness subspace; (2) the attack success rate of model tampering attacks can empirically predict and offer conservative estimates for the success of held-out input-space attacks; and (3) state-of-the-art unlearning methods can easily be undone within 16 steps of fine-tuning. Together these results highlight the difficulty of removing harmful LLM capabilities and show that model tampering attacks enable substantially more rigorous evaluations than input-space attacks alone. We release models at this https URL

[4]: multimodal FMs - video / audio

read on: - 09 Apr 2025
Multimodal

In this session, our readings cover:

Required Readings:

A Survey on Speech Large Language Models

  • Jing Peng, Yucheng Wang, Yu Xi, Xu Li, Xizhuo Zhang, Kai Yu
  • [Submitted on 24 Oct 2024 (v1), last revised 25 Oct 2024 (this version, v2)]
  • Large Language Models (LLMs) exhibit strong contextual understanding and remarkable multi-task performance. Therefore, researchers have been seeking to integrate LLMs in the broad sense of Spoken Language Understanding (SLU) field. Different from the traditional method of cascading LLMs to process text generated by Automatic Speech Recognition(ASR), new efforts have focused on designing architectures centered around Audio Feature Extraction - Multimodal Information Fusion - LLM Inference(Speech LLMs). This approach enables richer audio feature extraction while simultaneously facilitating end-to-end fusion of audio and text modalities, thereby achieving deeper understanding and reasoning from audio data. This paper elucidates the development of Speech LLMs, offering an in-depth analysis of system architectures and training strategies. Through extensive research and a series of targeted experiments, the paper assesses Speech LLMs’ advancements in Rich Audio Transcription and its potential for Cross-task Integration within the SLU field. Additionally, it indicates key challenges uncovered through experimentation, such as the Dormancy of LLMs under certain conditions. The paper further delves into the training strategies for Speech LLMs, proposing potential solutions based on these findings, and offering valuable insights and references for future research in this domain, as well as LLM applications in multimodal contexts.

NVLM: Open Frontier-Class Multimodal LLMs

  • [Submitted on 17 Sep 2024 (v1), last revised 22 Oct 2024 (this version, v2)]
  • Wenliang Dai, Nayeon Lee, Boxin Wang, Zhuolin Yang, Zihan Liu, Jon Barker, Tuomas Rintamaki, Mohammad Shoeybi, Bryan Catanzaro, Wei Ping

  • We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks, rivaling the leading proprietary models (e.g., GPT-4o) and open-access models (e.g., Llama 3-V 405B and InternVL 2). Remarkably, NVLM 1.0 shows improved text-only performance over its LLM backbone after multimodal training. In terms of model design, we perform a comprehensive comparison between decoder-only multimodal LLMs (e.g., LLaVA) and cross-attention-based models (e.g., Flamingo). Based on the strengths and weaknesses of both approaches, we propose a novel architecture that enhances both training efficiency and multimodal reasoning capabilities. Furthermore, we introduce a 1-D tile-tagging design for tile-based dynamic high-resolution images, which significantly boosts performance on multimodal reasoning and OCR-related tasks. Regarding training data, we meticulously curate and provide detailed information on our multimodal pretraining and supervised fine-tuning datasets. Our findings indicate that dataset quality and task diversity are more important than scale, even during the pretraining phase, across all architectures. Notably, we develop production-grade multimodality for the NVLM-1.0 models, enabling them to excel in vision-language tasks while maintaining and even improving text-only performance compared to their LLM backbones. To achieve this, we craft and integrate a high-quality text-only dataset into multimodal training, alongside a substantial amount of multimodal math and reasoning data, leading to enhanced math and coding capabilities across modalities. To advance research in the field, we release the model weights at this https URL and will open-source the training code for the community soon.

  • There are two main approaches to building multimodal LLMs: - Method A: Unified Embedding Decoder Architecture approach;
    • Method B: Cross-modality Attention Architecture approach.
  • Directly compared:
    • Method A: The Unified Embedding Decoder Architecture (“decoder-only architecture,” NVLM-D),
    • Method B: The Cross-Modality Attention Architecture (“cross-attention-based architecture,” NVLM-X),
    • A hybrid approach (NVLM-H).
  • Key findings are as follows:
    • NVLM-X: Offers superior computational efficiency for high-resolution images.
    • NVLM-D: Delivers higher accuracy for OCR-related tasks.
    • NVLM-H: Combines the strengths of both approaches for optimal performance.

LLMs Meet Multimodal Generation and Editing: A Survey

  • [Submitted on 29 May 2024 (v1), last revised 9 Jun 2024 (this version, v2)]
  • Yingqing He, Zhaoyang Liu, Jingye Chen, Zeyue Tian, Hongyu Liu, Xiaowei Chi, Runtao Liu, Ruibin Yuan, Yazhou Xing, Wenhai Wang, Jifeng Dai, Yong Zhang, Wei Xue, Qifeng Liu, Yike Guo, Qifeng Chen
  • With the recent advancement in large language models (LLMs), there is a growing interest in combining LLMs with multimodal learning. Previous surveys of multimodal large language models (MLLMs) mainly focus on multimodal understanding. This survey elaborates on multimodal generation and editing across various domains, comprising image, video, 3D, and audio. Specifically, we summarize the notable advancements with milestone works in these fields and categorize these studies into LLM-based and CLIP/T5-based methods. Then, we summarize the various roles of LLMs in multimodal generation and exhaustively investigate the critical technical components behind these methods and the multimodal datasets utilized in these studies. Additionally, we dig into tool-augmented multimodal agents that can leverage existing generative models for human-computer interaction. Lastly, we discuss the advancements in the generative AI safety field, investigate emerging applications, and discuss future prospects. Our work provides a systematic and insightful overview of multimodal generation and processing, which is expected to advance the development of Artificial Intelligence for Generative Content (AIGC) and world models. A curated list of all related papers can be found at this https URL

More Readings:

Video Understanding with Large Language Models: A Survey

  • Yunlong Tang, Jing Bi, Siting Xu, Luchuan Song, Susan Liang, Teng Wang, Daoan Zhang, Jie An, Jingyang Lin, Rongyi Zhu, Ali Vosoughi, Chao Huang, Zeliang Zhang, Pinxin Liu, Mingqian Feng, Feng Zheng, Jianguo Zhang, Ping Luo, Jiebo Luo, Chenliang Xu
  • [Submitted on 29 Dec 2023 (v1), last revised 24 Jul 2024 (this version, v4)]
  • With the burgeoning growth of online video platforms and the escalating volume of video content, the demand for proficient video understanding tools has intensified markedly. Given the remarkable capabilities of large language models (LLMs) in language and multimodal tasks, this survey provides a detailed overview of recent advancements in video understanding that harness the power of LLMs (Vid-LLMs). The emergent capabilities of Vid-LLMs are surprisingly advanced, particularly their ability for open-ended multi-granularity (general, temporal, and spatiotemporal) reasoning combined with commonsense knowledge, suggesting a promising path for future video understanding. We examine the unique characteristics and capabilities of Vid-LLMs, categorizing the approaches into three main types: Video Analyzer x LLM, Video Embedder x LLM, and (Analyzer + Embedder) x LLM. Furthermore, we identify five sub-types based on the functions of LLMs in Vid-LLMs: LLM as Summarizer, LLM as Manager, LLM as Text Decoder, LLM as Regressor, and LLM as Hidden Layer. Furthermore, this survey presents a comprehensive study of the tasks, datasets, benchmarks, and evaluation methodologies for Vid-LLMs. Additionally, it explores the expansive applications of Vid-LLMs across various domains, highlighting their remarkable scalability and versatility in real-world video understanding challenges. Finally, it summarizes the limitations of existing Vid-LLMs and outlines directions for future research. For more information, readers are recommended to visit the repository at this https URL.

Beta Release of Zonos-v0.1

FEBRUARY 10, 2025 PALO ALTO, CALIFORNIA We are excited to announce the release of Zonos-v0.1 beta, featuring two expressive and real-time text-to-speech (TTS) models with high-fidelity voice cloning. We are releasing our 1.6B transformer and 1.6B hybrid under an Apache 2.0 license.

[5]: More Model Serving Readings - SGlang + Chunked Prefill

read on: - 04 Apr 2025

In this session, our readings cover:

Readings on Efficient Model Serving :

SGLang: Efficient Execution of Structured Language Model Programs

  • [Submitted on 12 Dec 2023 (v1), last revised 6 Jun 2024 (this version, v2)]
  • SGLang: https://arxiv.org/pdf/2312.07104
  • Lianmin Zheng, Liangsheng Yin, Zhiqiang Xie, Chuyue Sun, Jeff Huang, Cody Hao Yu, Shiyi Cao, Christos Kozyrakis, Ion Stoica, Joseph E. Gonzalez, Clark Barrett, Ying Sheng
  • Large language models (LLMs) are increasingly used for complex tasks that require multiple generation calls, advanced prompting techniques, control flow, and structured inputs/outputs. However, efficient systems are lacking for programming and executing these applications. We introduce SGLang, a system for efficient execution of complex language model programs. SGLang consists of a frontend language and a runtime. The frontend simplifies programming with primitives for generation and parallelism control. The runtime accelerates execution with novel optimizations like RadixAttention for KV cache reuse and compressed finite state machines for faster structured output decoding. Experiments show that SGLang achieves up to 6.4x higher throughput compared to state-of-the-art inference systems on various large language and multi-modal models on tasks including agent control, logical reasoning, few-shot learning benchmarks, JSON decoding, retrieval-augmented generation pipelines, and multi-turn chat. The code is publicly available at this https URL

Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

  • Chunked Prefill: https://www.usenix.org/system/files/osdi24-agrawal.pdf
  • [Submitted on 4 Mar 2024 (v1), last revised 17 Jun 2024 (this version, v3)]
  • Amey Agrawal, Nitin Kedia, Ashish Panwar, Jayashree Mohan, Nipun Kwatra, Bhargav S. Gulavani, Alexey Tumanov, Ramachandran Ramjee
  • Each LLM serving request goes through two phases. The first is prefill which processes the entire input prompt and produces the first output token and the second is decode which generates the rest of output tokens, one-at-a-time. Prefill iterations have high latency but saturate GPU compute due to parallel processing of the input prompt. In contrast, decode iterations have low latency but also low compute utilization because a decode iteration processes only a single token per request. This makes batching highly effective for decodes and consequently for overall throughput. However, batching multiple requests leads to an interleaving of prefill and decode iterations which makes it challenging to achieve both high throughput and low latency. We introduce an efficient LLM inference scheduler, Sarathi-Serve, to address this throughput-latency tradeoff. Sarathi-Serve introduces chunked-prefills which splits a prefill request into near equal sized chunks and creates stall-free schedules that adds new requests in a batch without pausing ongoing decodes. Stall-free scheduling unlocks the opportunity to improve throughput with large batch sizes while minimizing the effect of batching on latency. Furthermore, uniform batches in Sarathi-Serve ameliorate the imbalance between iterations resulting in minimal pipeline bubbles. Our techniques yield significant improvements in inference performance across models and hardware under tail latency constraints. For Mistral-7B on single A100 GPUs, we achieve 2.6x higher serving capacity and up to 3.7x higher serving capacity for the Yi-34B model on two A100 GPUs as compared to vLLM. When used with pipeline parallelism on Falcon-180B, Sarathi-Serve provides up to 5.6x gain in the end-to-end serving capacity. The source code for Sarathi-Serve is available at this https URL.

More Readings :

Orca: A Distributed Serving System for Transformer-Based Generative Models

  • Continuous Batching: https://www.usenix.org/system/files/osdi22-yu.pdf
  • Gyeong-In Yu and Joo Seong Jeong, Seoul National University; Geon-Woo Kim, FriendliAI and Seoul National University; Soojeong Kim, FriendliAI; Byung-Gon Chun, FriendliAI and Seoul National University
  • Large-scale Transformer-based models trained for generation tasks (e.g., GPT-3) have recently attracted huge interest, emphasizing the need for system support for serving models in this family. Since these models generate a next token in an autoregressive manner, one has to run the model multiple times to process an inference request where each iteration of the model generates a single output token for the request. However, existing systems for inference serving do not perform well on this type of workload that has a multi-iteration characteristic, due to their inflexible scheduling mechanism that cannot change the current batch of requests being processed; requests that have finished earlier than other requests in a batch cannot return to the client, while newly arrived requests have to wait until the current batch completely finishes. In this paper, we propose iteration-level scheduling, a new scheduling mechanism that schedules execution at the granularity of iteration (instead of request) where the scheduler invokes the execution engine to run only a single iteration of the model on the batch. In addition, to apply batching and iteration-level scheduling to a Transformer model at the same time, we suggest selective batching, which applies batching only to a selected set of operations. Based on these two techniques, we have implemented a distributed serving system called ORCA, with additional designs for scalability to models with hundreds of billions of parameters. Our evaluation on a GPT-3 175B model shows that ORCA can significantly outperform NVIDIA FasterTransformer in terms of both latency and throughput: 36:9× throughput improvement at the same level of latency.

FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU

  • FlexGen: https://arxiv.org/pdf/2303.06865 +[Submitted on 13 Mar 2023 (v1), last revised 12 Jun 2023 (this version, v2)]
  • Ying Sheng, Lianmin Zheng, Binhang Yuan, Zhuohan Li, Max Ryabinin, Daniel Y. Fu, Zhiqiang Xie, Beidi Chen, Clark Barrett, Joseph E. Gonzalez, Percy Liang, Christopher Ré, Ion Stoica, Ce Zhang
  • The high computational and memory requirements of large language model (LLM) inference make it feasible only with multiple high-end accelerators. Motivated by the emerging demand for latency-insensitive tasks with batched processing, this paper initiates the study of high-throughput LLM inference using limited resources, such as a single commodity GPU. We present FlexGen, a high-throughput generation engine for running LLMs with limited GPU memory. FlexGen can be flexibly configured under various hardware resource constraints by aggregating memory and computation from the GPU, CPU, and disk. By solving a linear programming problem, it searches for efficient patterns to store and access tensors. FlexGen further compresses the weights and the attention cache to 4 bits with negligible accuracy loss. These techniques enable FlexGen to have a larger space of batch size choices and thus significantly increase maximum throughput. As a result, when running OPT-175B on a single 16GB GPU, FlexGen achieves significantly higher throughput compared to state-of-the-art offloading systems, reaching a generation throughput of 1 token/s for the first time with an effective batch size of 144. On the HELM benchmark, FlexGen can benchmark a 30B model with a 16GB GPU on 7 representative sub-scenarios in 21 hours. The code is available at this https URL

Neo: https://arxiv.org/pdf/2411.01142

  • [Submitted on 2 Nov 2024]
  • NEO: Saving GPU Memory Crisis with CPU Offloading for Online LLM Inference
  • Xuanlin Jiang, Yang Zhou, Shiyi Cao, Ion Stoica, Minlan Yu
  • Online LLM inference powers many exciting applications such as intelligent chatbots and autonomous agents. Modern LLM inference engines widely rely on request batching to improve inference throughput, aiming to make it cost-efficient when running on expensive GPU accelerators. However, the limited GPU memory has largely limited the batch size achieved in practice, leaving significant GPU compute resources wasted. We present NEO, an online LLM inference system that offloads part of attention compute and KV cache states from the GPU to the local host CPU, effectively increasing the GPU batch size and thus inference throughput. To this end, NEO proposes asymmetric GPU-CPU pipelining and load-aware scheduling to balance GPU and CPU loads and fully utilize their compute and memory resources. We evaluate NEO on a wide range of workloads (i.e., code generation, text summarization), GPUs (i.e., T4, A10G, H100), and LLM models (i.e., 7B, 8B, 70B). NEO achieves up to 7.5×, 26%, and 14% higher throughput compared to GPU-only approach on T4, A10G, and H100 GPUs, respectively, while maintaining the same latency; with more powerful CPUs, NEO achieves up to 79.3% throughput gain on A10G GPU.

Shortest Job First: https://arxiv.org/pdf/2408.15792

  • [Submitted on 28 Aug 2024]
  • Efficient LLM Scheduling by Learning to Rank
  • Yichao Fu, Siqi Zhu, Runlong Su, Aurick Qiao, Ion Stoica, Hao Zhang
  • In Large Language Model (LLM) inference, the output length of an LLM request is typically regarded as not known a priori. Consequently, most LLM serving systems employ a simple First-come-first-serve (FCFS) scheduling strategy, leading to Head-Of-Line (HOL) blocking and reduced throughput and service quality. In this paper, we reexamine this assumption – we show that, although predicting the exact generation length of each request is infeasible, it is possible to predict the relative ranks of output lengths in a batch of requests, using learning to rank. The ranking information offers valuable guidance for scheduling requests. Building on this insight, we develop a novel scheduler for LLM inference and serving that can approximate the shortest-job-first (SJF) schedule better than existing approaches. We integrate this scheduler with the state-of-the-art LLM serving system and show significant performance improvement in several important applications: 2.8x lower latency in chatbot serving and 6.5x higher throughput in synthetic data generation. Our code is available at this https URL

[6]: LLM Alignment - PPO

read on: - 02 Apr 2025
Customization

In this session, our readings cover:

Required Model serving Readings:

PPO Readings:

a simple blogpost: Preference Tuning LLMs: PPO, DPO, GRPO — A Simple Guide

A Comprehensive Survey of LLM Alignment Techniques: RLHF, RLAIF, PPO, DPO and More

  • [Submitted on 23 Jul 2024]
  • Zhichao Wang, Bin Bi, Shiva Kumar Pentyala, Kiran Ramnath, Sougata Chaudhuri, Shubham Mehrotra, Zixu (James)Zhu, Xiang-Bo Mao, Sitaram Asur, Na (Claire)Cheng
  • With advancements in self-supervised learning, the availability of trillions tokens in a pre-training corpus, instruction fine-tuning, and the development of large Transformers with billions of parameters, large language models (LLMs) are now capable of generating factual and coherent responses to human queries. However, the mixed quality of training data can lead to the generation of undesired responses, presenting a significant challenge. Over the past two years, various methods have been proposed from different perspectives to enhance LLMs, particularly in aligning them with human expectation. Despite these efforts, there has not been a comprehensive survey paper that categorizes and details these approaches. In this work, we aim to address this gap by categorizing these papers into distinct topics and providing detailed explanations of each alignment method, thereby helping readers gain a thorough understanding of the current state of the field.

OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework

  • [Submitted on 20 May 2024 (v1), last revised 24 Nov 2024 (this version, v4)]
  • Jian Hu, Xibin Wu, Zilin Zhu, Xianyu, Weixun Wang, Dehao Zhang, Yu Cao
  • As large language models (LLMs) continue to grow by scaling laws, reinforcement learning from human feedback (RLHF) has gained significant attention due to its outstanding performance. However, unlike pretraining or fine-tuning a single model, scaling reinforcement learning from human feedback (RLHF) for training large language models poses coordination challenges across four models. We present OpenRLHF, an open-source framework enabling efficient RLHF scaling. Unlike existing RLHF frameworks that co-locate four models on the same GPUs, OpenRLHF re-designs scheduling for the models beyond 70B parameters using Ray, vLLM, and DeepSpeed, leveraging improved resource utilization and diverse training approaches. Integrating seamlessly with Hugging Face, OpenRLHF provides an out-of-the-box solution with optimized algorithms and launch scripts, which ensures user-friendliness. OpenRLHF implements RLHF, DPO, rejection sampling, and other alignment techniques. Empowering state-of-the-art LLM development, OpenRLHF’s code is available at \url{this https URL}.

Towards a Unified View of Preference Learning for Large Language Models: A Survey

  • [Submitted on 4 Sep 2024 (v1), last revised 31 Oct 2024 (this version, v5)]
  • Bofei Gao, Feifan Song, Yibo Miao, Zefan Cai, Zhe Yang, Liang Chen, Helan Hu, Runxin Xu, Qingxiu Dong, Ce Zheng, Shanghaoran Quan, Wen Xiao, Ge Zhang, Daoguang Zan, Keming Lu, Bowen Yu, Dayiheng Liu, Zeyu Cui, Jian Yang, Lei Sha, Houfeng Wang, Zhifang Sui, Peiyi Wang, Tianyu Liu, Baobao Chang
  • Large Language Models (LLMs) exhibit remarkably powerful capabilities. One of the crucial factors to achieve success is aligning the LLM’s output with human preferences. This alignment process often requires only a small amount of data to efficiently enhance the LLM’s performance. While effective, research in this area spans multiple domains, and the methods involved are relatively complex to understand. The relationships between different methods have been under-explored, limiting the development of the preference alignment. In light of this, we break down the existing popular alignment strategies into different components and provide a unified framework to study the current alignment strategies, thereby establishing connections among them. In this survey, we decompose all the strategies in preference learning into four components: model, data, feedback, and algorithm. This unified view offers an in-depth understanding of existing alignment algorithms and also opens up possibilities to synergize the strengths of different strategies. Furthermore, we present detailed working examples of prevalent existing algorithms to facilitate a comprehensive understanding for the readers. Finally, based on our unified perspective, we explore the challenges and future research directions for aligning large language models with human preferences.

Insights into Alignment: Evaluating DPO and its Variants Across Multiple Tasks

  • [Submitted on 23 Apr 2024 (v1), last revised 8 Feb 2025 (this version, v2)]
  • Amir Saeidi, Shivanshu Verma, Md Nayem Uddin, Chitta Baral
  • This study evaluates Direct Preference Optimization (DPO) and its variants for aligning Large Language Models (LLMs) with human preferences, testing three configurations: (1) with Supervised Fine Tuning (SFT), (2) without SFT, and (3) without SFT but using an instruction tuned model. We further investigate how training set size influences model performance. Our evaluation spans 13 benchmarks covering dialogue, reasoning, mathematical problem-solving, question answering, truthfulness, MT-Bench, Big Bench, and the Open LLM Leaderboard. We find that: (1) alignment methods often achieve near optimal performance even with smaller subsets of training data; (2) although they offer limited improvements on complex reasoning tasks, they enhance mathematical problem-solving; and (3) using an instruction tuned model improves truthfulness. These insights highlight the conditions under which alignment methods excel, as well as their limitations.

More Readings:

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

  • [Submitted on 22 Jan 2025]
  • DeepSeek-AI, (100 additional authors not shown)
  • We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrates remarkable reasoning capabilities. Through RL, DeepSeek-R1-Zero naturally emerges with numerous powerful and intriguing reasoning behaviors. However, it encounters challenges such as poor readability, and language mixing. To address these issues and further enhance reasoning performance, we introduce DeepSeek-R1, which incorporates multi-stage training and cold-start data before RL. DeepSeek-R1 achieves performance comparable to OpenAI-o1-1217 on reasoning tasks. To support the research community, we open-source DeepSeek-R1-Zero, DeepSeek-R1, and six dense models (1.5B, 7B, 8B, 14B, 32B, 70B) distilled from DeepSeek-R1 based on Qwen and Llama.

[7]: more LLM basics - a survey

read on: - 20 Jan 2025
BasicLLM

In this session, our readings cover:

Required Readings:

Large Language Models: A Survey

  • Shervin Minaee, Tomas Mikolov, Narjes Nikzad, Meysam Chenaghlu, Richard Socher, Xavier Amatriain, Jianfeng Gao
  • [Submitted on 9 Feb 2024 (v1), last revised 20 Feb 2024 (this version, v2)]
  • Large Language Models (LLMs) have drawn a lot of attention due to their strong performance on a wide range of natural language tasks, since the release of ChatGPT in November 2022. LLMs’ ability of general-purpose language understanding and generation is acquired by training billions of model’s parameters on massive amounts of text data, as predicted by scaling laws \cite{kaplan2020scaling,hoffmann2022training}. The research area of LLMs, while very recent, is evolving rapidly in many different ways. In this paper, we review some of the most prominent LLMs, including three popular LLM families (GPT, LLaMA, PaLM), and discuss their characteristics, contributions and limitations. We also give an overview of techniques developed to build, and augment LLMs. We then survey popular datasets prepared for LLM training, fine-tuning, and evaluation, review widely used LLM evaluation metrics, and compare the performance of several popular LLMs on a set of representative benchmarks. Finally, we conclude the paper by discussing open challenges and future research directions.

Extra Readings:

[8]: LLM basics - emergent ability and GenAI platform

read on: - 15 Jan 2025
BasicLLM

Readings:

Emergent Abilities of Large Language Models

  • URL
  • “an ability to be emergent if it is not present in smaller models but is present in larger models. Thus, emergent abilities cannot be predicted simply by extrapolating the performance of smaller models.”

Language Models are Few-Shot Learners

  • URL
  • “GPT-3, 175B autoregerssive LLM; show that scaling up language models greatly improves task-agnostic, few-shot performance, sometimes even reaching competitiveness with prior state-of-the-art fine-tuning approaches.”

GenAI Platform

Extra Readings:

A survey of Generative AI Applications

  • https://arxiv.org/abs/2306.02781
  • Generative AI has experienced remarkable growth in recent years, leading to a wide array of applications across diverse domains. In this paper, we present a comprehensive survey of more than 350 generative AI applications, providing a structured taxonomy and concise descriptions of various unimodal and even multimodal generative AIs. The survey is organized into sections, covering a wide range of unimodal generative AI applications such as text, images, video, gaming and brain information. Our survey aims to serve as a valuable resource for researchers and practitioners to navigate the rapidly expanding landscape of generative AI, facilitating a better understanding of the current state-of-the-art and fostering further innovation in the field.

[9]: Introduction

read on: - 13 Jan 2025
BasicLLM

Readings:

Basics of ML and DL:

Basics of NLP

  • URL
  • Typical NLP tasks / Challenges / Pipeline
  • f() on natural language
    • Before Deep NLP (Pre 2012) • (BOW / LSI / Topic Modeling LDA )
    • Word2Vec (2013-2016) • (GloVe/ FastText)
    • Recurrent NN (2014-2016) • LSTM
    • Seq2Seq
    • Attention
    • Self-Attention (2016 – now )
    • Transformer (attention only Seq2Seq)
    • BERT / RoBERTa/ XLNet/ GPT / …
  • A good code walk through on transformer at URL

∂

[10]: Open Source LLM - Mistral Data preparation

read on: - 08 Feb 2024
BasicLLM

In this session, our readings cover:

Required Readings:

Mistral 7B

  • https://mistral.ai/news/announcing-mistral-7b/
  • We introduce Mistral 7B v0.1, a 7-billion-parameter language model engineered for superior performance and efficiency. Mistral 7B outperforms Llama 2 13B across all evaluated benchmarks, and Llama 1 34B in reasoning, mathematics, and code generation. Our model leverages grouped-query attention (GQA) for faster inference, coupled with sliding window attention (SWA) to effectively handle sequences of arbitrary length with a reduced inference cost. We also provide a model fine-tuned to follow instructions, Mistral 7B – Instruct, that surpasses the Llama 2 13B – Chat model both on human and automated benchmarks. Our models are released under the Apache 2.0 license.

More Readings:

OLMo: Accelerating the Science of Language Models

  • https://arxiv.org/abs/2402.00838

Language models (LMs) have become ubiquitous in both NLP research and in commercial product offerings. As their commercial importance has surged, the most powerful models have become closed off, gated behind proprietary interfaces, with important details of their training data, architectures, and development undisclosed. Given the importance of these details in scientifically studying these models, including their biases and potential risks, we believe it is essential for the research community to have access to powerful, truly open LMs. To this end, this technical report details the first release of OLMo, a state-of-the-art, truly Open Language Model and its framework to build and study the science of language modeling. Unlike most prior efforts that have only released model weights and inference code, we release OLMo and the whole framework, including training data and training and evaluation code. We hope this release will empower and strengthen the open research community and inspire a new wave of innovation.

Mixtral of Experts

  • https://arxiv.org/abs/2401.04088
  • We introduce Mixtral 8x7B, a Sparse Mixture of Experts (SMoE) language model. Mixtral has the same architecture as Mistral 7B, with the difference that each layer is composed of 8 feedforward blocks (i.e. experts). For every token, at each layer, a router network selects two experts to process the current state and combine their outputs. Even though each token only sees two experts, the selected experts can be different at each timestep. As a result, each token has access to 47B parameters, but only uses 13B active parameters during inference. Mixtral was trained with a context size of 32k tokens and it outperforms or matches Llama 2 70B and GPT-3.5 across all evaluated benchmarks. In particular, Mixtral vastly outperforms Llama 2 70B on mathematics, code generation, and multilingual benchmarks. We also provide a model fine-tuned to follow instructions, Mixtral 8x7B - Instruct, that surpasses GPT-3.5 Turbo, Claude-2.1, Gemini Pro, and Llama 2 70B - chat model on human benchmarks. Both the base and instruct models are released under the Apache 2.0 license.

- Llama 2: Open Foundation and Fine-Tuned Chat Models

  • In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama 2-Chat, are optimized for dialogue use cases. Our models outperform open-source chat models on most benchmarks we tested, and based on our human evaluations for helpfulness and safety, may be a suitable substitute for closed-source models. We provide a detailed description of our approach to fine-tuning and safety improvements of Llama 2-Chat in order to enable the community to build on our work and contribute to the responsible development of LLMs.

The Pile: An 800GB Dataset of Diverse Text for Language Modeling

  • https://arxiv.org/abs/2101.00027
  • Recent work has demonstrated that increased training dataset diversity improves general cross-domain knowledge and downstream generalization capability for large-scale language models. With this in mind, we present \textit{the Pile}: an 825 GiB English text corpus targeted at training large-scale language models. The Pile is constructed from 22 diverse high-quality subsets – both existing and newly constructed – many of which derive from academic or professional sources. Our evaluation of the untuned performance of GPT-2 and GPT-3 on the Pile shows that these models struggle on many of its components, such as academic writing. Conversely, models trained on the Pile improve significantly over both Raw CC and CC-100 on all components of the Pile, while improving performance on downstream evaluations. Through an in-depth exploratory analysis, we document potentially concerning aspects of the data for prospective users. We make publicly available the code used in its construction.

[11]: Survey human alignment

read on: - 06 Feb 2024
Alignment

In this session, our readings cover:

Required Readings:

Aligning Large Language Models with Human: A Survey

  • https://arxiv.org/abs/2307.12966
  • https://huggingface.co/blog/the_n_implementation_details_of_rlhf_with_ppo
  • https://huggingface.co/blog/stackllama

More readings

Github Awesome-RLHF

The Flan Collection: Designing Data and Methods for Effective Instruction Tuning

  • https://arxiv.org/abs/2301.13688
  • We study the design decisions of publicly available instruction tuning methods, and break down the development of Flan 2022 (Chung et al., 2022). Through careful ablation studies on the Flan Collection of tasks and methods, we tease apart the effect of design decisions which enable Flan-T5 to outperform prior work by 3-17%+ across evaluation settings. We find task balancing and enrichment techniques are overlooked but critical to effective instruction tuning, and in particular, training with mixed prompt settings (zero-shot, few-shot, and chain-of-thought) actually yields stronger (2%+) performance in all settings. In further experiments, we show Flan-T5 requires less finetuning to converge higher and faster than T5 on single downstream tasks, motivating instruction-tuned models as more computationally-efficient starting checkpoints for new tasks. Finally, to accelerate research on instruction tuning, we make the Flan 2022 collection of datasets, templates, and methods publicly available at this https URL.

DPO Direct Preference Optimization: Your Language Model is Secretly a Reward Model

  • https://arxiv.org/abs/2305.18290
  • https://huggingface.co/blog/dpo-trl
  • While large-scale unsupervised language models (LMs) learn broad world knowledge and some reasoning skills, achieving precise control of their behavior is difficult due to the completely unsupervised nature of their training. Existing methods for gaining such steerability collect human labels of the relative quality of model generations and fine-tune the unsupervised LM to align with these preferences, often with reinforcement learning from human feedback (RLHF). However, RLHF is a complex and often unstable procedure, first fitting a reward model that reflects the human preferences, and then fine-tuning the large unsupervised LM using reinforcement learning to maximize this estimated reward without drifting too far from the original model. In this paper we introduce a new parameterization of the reward model in RLHF that enables extraction of the corresponding optimal policy in closed form, allowing us to solve the standard RLHF problem with only a simple classification loss. The resulting algorithm, which we call Direct Preference Optimization (DPO), is stable, performant, and computationally lightweight, eliminating the need for sampling from the LM during fine-tuning or performing significant hyperparameter tuning. Our experiments show that DPO can fine-tune LMs to align with human preferences as well as or better than existing methods. Notably, fine-tuning with DPO exceeds PPO-based RLHF in ability to control sentiment of generations, and matches or improves response quality in summarization and single-turn dialogue while being substantially simpler to implement and train.

Training language models to follow instructions with human feedback

  • https://arxiv.org/abs/2203.02155)
  • “further fine-tune this supervised model using reinforcement learning from human feedback. We call the resulting models InstructGPT.”

Deep reinforcement learning from human preferences

  • https://openreview.net/forum?id=GisHNaleWiA
  • “explore goals defined in terms of (non-expert) human preferences between pairs of trajectory segments. We show that this approach can effectively solve complex RL tasks without access to the reward function”

[12]: LLM evaluating framework

read on: - 30 Jan 2024
LLMEvaluate

In this session, our readings cover:

Required Readings:

Holistic Evaluation of Text-To-Image Models

  • https://arxiv.org/abs/2311.04287
  • The stunning qualitative improvement of recent text-to-image models has led to their widespread attention and adoption. However, we lack a comprehensive quantitative understanding of their capabilities and risks. To fill this gap, we introduce a new benchmark, Holistic Evaluation of Text-to-Image Models (HEIM). Whereas previous evaluations focus mostly on text-image alignment and image quality, we identify 12 aspects, including text-image alignment, image quality, aesthetics, originality, reasoning, knowledge, bias, toxicity, fairness, robustness, multilinguality, and efficiency. We curate 62 scenarios encompassing these aspects and evaluate 26 state-of-the-art text-to-image models on this benchmark. Our results reveal that no single model excels in all aspects, with different models demonstrating different strengths. We release the generated images and human evaluation results for full transparency at this https URL and the code at this https URL, which is integrated with the HELM codebase.

Holistic Evaluation of Language Models

  • https://arxiv.org/abs/2211.09110

More Readings:

Challenges in evaluating AI systems

  • https://www.anthropic.com/news/evaluating-ai-systems

Evaluating Large Language Models: A Comprehensive Survey

  • https://arxiv.org/abs/2310.19736
  • This survey endeavors to offer a panoramic perspective on the evaluation of LLMs. We categorize the evaluation of LLMs into three major groups: knowledge and capability evaluation, alignment evaluation and safety evaluation. In addition to the comprehensive review on the evaluation methodologies and benchmarks on these three aspects, we collate a compendium of evaluations pertaining to LLMs’ performance in specialized domains, and discuss the construction of comprehensive evaluation platforms that cover LLM evaluations on capabilities, alignment, safety, and applicability.

Evaluating Large Language Models Trained on Code

  • https://arxiv.org/abs/2107.03374

chatbot-arena-leaderboard

  • https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard

Leveraging Large Language Models for NLG Evaluation: A Survey

  • https://arxiv.org/abs/2401.07103

[13]: LLM basics

read on: - 23 Jan 2024
BasicLLM

Required Readings:

Emergent Abilities of Large Language Models

  • URL
  • “an ability to be emergent if it is not present in smaller models but is present in larger models. Thus, emergent abilities cannot be predicted simply by extrapolating the performance of smaller models.”

Language Models are Few-Shot Learners

  • URL
  • “GPT-3, 175B autoregerssive LLM; show that scaling up language models greatly improves task-agnostic, few-shot performance, sometimes even reaching competitiveness with prior state-of-the-art fine-tuning approaches.”

Extra Readings:

A survey of Generative AI Applications

  • https://arxiv.org/abs/2306.02781
  • Generative AI has experienced remarkable growth in recent years, leading to a wide array of applications across diverse domains. In this paper, we present a comprehensive survey of more than 350 generative AI applications, providing a structured taxonomy and concise descriptions of various unimodal and even multimodal generative AIs. The survey is organized into sections, covering a wide range of unimodal generative AI applications such as text, images, video, gaming and brain information. Our survey aims to serve as a valuable resource for researchers and practitioners to navigate the rapidly expanding landscape of generative AI, facilitating a better understanding of the current state-of-the-art and fostering further innovation in the field.

Generative AI: Perspectives from Stanford HAI

  • https://hai.stanford.edu/generative-ai-perspectives-stanford-hai

[14]: RLHF + InstructGPT

read on: - 03 Dec 2022
RL AGI language model Human Alignment
Papers Paper URL Abstract
Training language models to follow instructions with human feedback URL “further fine-tune this supervised model using reinforcement learning from human feedback. We call the resulting models InstructGPT.”
Deep reinforcement learning from human preferences URL “explore goals defined in terms of (non-expert) human preferences between pairs of trajectory segments. We show that this approach can effectively solve complex RL tasks without access to the reward function”

[15]: Stable diffusion + DreamBooth + LoRA

read on: - 01 Dec 2022
Diffusion Image synthesis Efficiency

Stable diffusion

  • URL
  • “High-Resolution Image Synthesis with Latent Diffusion Models”

DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation

  • URL
  • “personalization” of text-to-image diffusion models. Given as input just a few images of a subject, we fine-tune a pretrained text-to-image model such that it learns to bind a unique identifier with that specific subject. .”

LoRA: Low-Rank Adaptation of Large Language Models

  • URL
  • “propose Low-Rank Adaptation, or LoRA, which freezes the pre-trained model weights and injects trainable rank decomposition matrices into each layer of the Transformer architecture, greatly reducing the number of trainable parameters for downstream tasks. Compared to GPT-3 175B fine-tuned with Adam, LoRA can reduce the number of trainable parameters by 10,000 times and the GPU memory requirement by 3 times.”

An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion

  • https://arxiv.org/abs/2208.01618
  • Rinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit H. Bermano, Gal Chechik, Daniel Cohen-Or
  • Text-to-image models offer unprecedented freedom to guide creation through natural language. Yet, it is unclear how such freedom can be exercised to generate images of specific unique concepts, modify their appearance, or compose them in new roles and novel scenes. In other words, we ask: how can we use language-guided models to turn our cat into a painting, or imagine a new product based on our favorite toy? Here we present a simple approach that allows such creative freedom. Using only 3-5 images of a user-provided concept, like an object or a style, we learn to represent it through new “words” in the embedding space of a frozen text-to-image model. These “words” can be composed into natural language sentences, guiding personalized creation in an intuitive way. Notably, we find evidence that a single word embedding is sufficient for capturing unique and varied concepts. We compare our approach to a wide range of baselines, and demonstrate that it can more faithfully portray the concepts across a range of applications and tasks.

[16]: Emergent Abilities of LLM

read on: - 01 Oct 2022
language model

Emergent Abilities of Large Language Models

  • URL
  • “an ability to be emergent if it is not present in smaller models but is present in larger models. Thus, emergent abilities cannot be predicted simply by extrapolating the performance of smaller models.”

Language Models are Few-Shot Learners

  • URL
  • “GPT-3, 175B autoregerssive LLM; show that scaling up language models greatly improves task-agnostic, few-shot performance, sometimes even reaching competitiveness with prior state-of-the-art fine-tuning approaches.”

On the Opportunities and Risks of Foundation Models

  • URL
  • ” a thorough account of the opportunities and risks of foundation models, ranging from their capabilities (e.g., language, vision, robotics, reasoning, human interaction) and technical principles(e.g., model architectures, training procedures, data, systems, security, evaluation, theory) to their applications (e.g., law, healthcare, education) and societal impact (e.g., inequity, misuse, economic and environmental impact, legal and ethical considerations).”

The Power of Scale for Parameter-Efficient Prompt Tuning

  • https://arxiv.org/abs/2104.08691
  • Brian Lester, Rami Al-Rfou, Noah Constant
  • In this work, we explore “prompt tuning”, a simple yet effective mechanism for learning “soft prompts” to condition frozen language models to perform specific downstream tasks. Unlike the discrete text prompts used by GPT-3, soft prompts are learned through backpropagation and can be tuned to incorporate signal from any number of labeled examples. Our end-to-end learned approach outperforms GPT-3’s “few-shot” learning by a large margin. More remarkably, through ablations on model size using T5, we show that prompt tuning becomes more competitive with scale: as models exceed billions of parameters, our method “closes the gap” and matches the strong performance of model tuning (where all model weights are tuned). This finding is especially relevant in that large models are costly to share and serve, and the ability to reuse one frozen model for multiple downstream tasks can ease this burden. Our method can be seen as a simplification of the recently proposed “prefix tuning” of Li and Liang (2021), and we provide a comparison to this and other similar approaches. Finally, we show that conditioning a frozen model with soft prompts confers benefits in robustness to domain transfer, as compared to full model tuning.

[17]: A Generalist Agent + offline RL + UniMask

read on: - 03 May 2022
RL AGI
Papers Paper URL Abstract
A Generalist Agent URL Gato, works as a multi-modal, multi-task, multi-embodiment generalist policy. The same network with the same weights can play Atari, caption images, chat, stack blocks with a real robot arm and much more, deciding based on its context whether to output text, joint torques, button presses, or other tokens.
Why should we prefer offline reinforcement learning over behavioral cloning? ICLR 2022 URL natural to ask: when can an offline RL method outperform BC with an equal amount of expert data, even when BC is a natural choice?
Uni[MASK]: Unified Inference in Sequential Decision Problems URL show how sequential decision making tasks can be thought of in terms of corresponding input maskings, enabling the training of a single model to perform all tasks at once. applies naturally to sequential decision making, where many well-studied tasks like behavior cloning, offline RL, inverse dynamics, and waypoint conditioning correspond to different sequence maskings over a sequence of states, actions, and returns.

Here is a name list of posts!


LLM basics

less than 1 minute read

Required Readings:

RLHF + InstructGPT

less than 1 minute read

Papers Paper URL Abstract Training language models to follow instructions with human feedback URL ...

Emergent Abilities of LLM

1 minute read

Emergent Abilities of Large Language Models URL “an ability to be emergent if it is not present in smaller models but is present in larger models. Thus...