Posts by Year

LLM Post-training

2 minute read

In this session, our readings cover:

Model serving - Efficiency Inference

10 minute read

Model Serve Readings:

Inference test time scaling law

4 minute read

In this session, our readings cover:

Model Interpretibility for FM

6 minute read

In this session, our readings cover:

More on LLM based agents

9 minute read

In this session, our readings cover:

multimodal FMs - video / audio

5 minute read

In this session, our readings cover:

More Model Serving Readings - SGlang + Chunked Prefill

7 minute read

In this session, our readings cover:

LLM Alignment - PPO

4 minute read

In this session, our readings cover:

Agent - multiagent collaboration

6 minute read

In this session, our readings cover:

Agent Safety

9 minute read

In this session, our readings cover:

Agent - Planning / World Model

7 minute read

In this session, our readings cover:

Platform - long context vs RAG + Hallucination

5 minute read

In this session, our readings cover:

Agent - In Healthcare

8 minute read

In this session, our readings cover:

Extra readings - Agent Guardrailing

6 minute read

In this session, our readings cover:

Extra - BioLLM

11 minute read

In this session, our readings cover:

Platform - Model Serving

4 minute read

In this session, our readings cover:

Platform - Model Customization - instruction tuning / LoRA

2 minute read

In this session, our readings cover:

Platform - VLM Jailbreaking / Probing

5 minute read

In this session, our readings cover:

Platform - Model Jailbreaking / Safeguarding

5 minute read

In this session, our readings cover:

Platform - More agent related

1 minute read

In this session, our readings cover:

Platform - Agent Tooling

less than 1 minute read

In this session, our readings cover:

Platform - Context construction via RAG and Agent

2 minute read

In this session, our readings cover:

Platform - Prompting Engineering tools / Prompt Compression

2 minute read

In this session, our readings cover:

advanced LLM - Math reasoning

6 minute read

In this session, our readings cover:

advanced LLM - for code reasoning

3 minute read

In this session, our readings cover:

Survey - FMs in Robotics

3 minute read

In this session, our readings cover:

Survey - FMs in healthcare

4 minute read

In this session, our readings cover:

Survey - BioScience LLMs

2 minute read

In this session, our readings cover:

more LLM basics - a survey

1 minute read

In this session, our readings cover:

LLM basics - emergent ability and GenAI platform

less than 1 minute read

Readings:

Introduction

less than 1 minute read

Readings:

Privacy

1 minute read

Beyond Memorization: Violating Privacy Via Inference with Large Language Models

Gradient for LLM

less than 1 minute read

Gradient for LLM

1 minute read

TextGrad: Automatic “Differentiation” via Text

Safety Benchmark WMDP

1 minute read

The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning Nathaniel Li, Alexander Pan, Anjali Gopal, Summer Yue, Daniel Berrios, Alice Gatt...

KV Cache and Tooling

3 minute read

KV Caching in LLM:

Advanced Transformer Architectures

24 minute read

In this session, our readings cover:

LLM fine tuning

29 minute read

In this session, our readings cover:

Recent LLM basics

21 minute read

In this session, our readings cover:

MultiAgent LLMs

16 minute read

In this session, our readings cover:

LLM Agents

23 minute read

Required Readings:

Self-exam LLM and reasoning

19 minute read

In this session, our readings cover:

Prompt Engineering

26 minute read

In this session, our readings cover:

LLM Scaling law and Efficiency

39 minute read

In this session, our readings cover:

LLM interpretibility, trust and knowledge conflicts

15 minute read

Required Readings:

Model editing and Disgorgement

19 minute read

In this session, our readings cover:

Domain Centered FMs

23 minute read

In this session, our readings cover:

LLM Hallucination

15 minute read

In this session, our readings cover:

Knowledge Augmented FMs

17 minute read

In this session, our readings cover:

More FM risk

38 minute read

In this session, our readings cover:

LLM multimodal harm responses

14 minute read

In this session, our readings cover:

FM toxicity / harmful outputs

10 minute read

In this session, our readings cover:

FM fairness / bias issues

33 minute read

In this session, our readings cover:

FM privacy leakage issues

14 minute read

In this session, our readings cover:

FM copyright infrigement

26 minute read

In this session, our readings cover:

Survey AI Risk framework

14 minute read

In this session, our readings cover:

Open Source LLM - Mistral Data preparation

27 minute read

In this session, our readings cover:

Survey human alignment

18 minute read

In this session, our readings cover:

GenAI Guardrails

19 minute read

In this session, our readings cover:

LLM evaluating framework

16 minute read

In this session, our readings cover:

Survey LLMs and Multimodal FMs

2 minute read

In this session, our readings cover:

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 ...

Stable diffusion + DreamBooth + LoRA

1 minute read

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

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...

DiffDock + ESMfold

less than 1 minute read

Papers Paper URL Abstract Evolutionary-scale prediction of atomic level protein structure with a language mo...

Decision Transformers

1 minute read

Decision Transformer: Reinforcement Learning via Sequence Modeling Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin, Piet...

A Generalist Agent + offline RL + UniMask

less than 1 minute read

Papers Paper URL Abstract