No. |
Date-Read |
Title and Information |
Tags |
1 |
2025, Apr, 25 |
LLM Post-training |
customization
|
2 |
2025, Apr, 20 |
Model serving - Efficiency Inference |
serving
|
3 |
2025, Apr, 18 |
Inference test time scaling law |
scaling
|
4 |
2025, Apr, 13 |
Model Interpretibility for FM |
safety
|
5 |
2025, Apr, 11 |
More on LLM based agents |
scaling
|
6 |
2025, Apr, 9 |
multimodal FMs - video / audio |
multimodal
|
7 |
2025, Apr, 4 |
More Model Serving Readings - SGlang + Chunked Prefill |
|
8 |
2025, Apr, 2 |
LLM Alignment - PPO |
customization
|
9 |
2025, Mar, 31 |
Agent - multiagent collaboration |
multiagent
|
10 |
2025, Mar, 26 |
Agent Safety |
safety
agent
|
11 |
2025, Mar, 24 |
Agent - Planning / World Model |
planning
|
12 |
2025, Mar, 19 |
Platform - long context vs RAG + Hallucination |
rag
longcontext
|
13 |
2025, Mar, 17 |
Agent - In Healthcare |
applications
|
14 |
2025, Mar, 12 |
Extra readings - Agent Guardrailing |
safety
|
15 |
2025, Mar, 10 |
Extra - BioLLM |
applications
|
16 |
2025, Mar, 5 |
Platform - Model Serving |
serving
|
17 |
2025, Mar, 3 |
Platform - Model Customization - instruction tuning / LoRA |
customization
|
18 |
2025, Feb, 26 |
Platform - VLM Jailbreaking / Probing |
jailbreaking
safety
|
19 |
2025, Feb, 24 |
Platform - Model Jailbreaking / Safeguarding |
jailbreaking
safety
|
20 |
2025, Feb, 19 |
Platform - More agent related |
agent
|
21 |
2025, Feb, 17 |
Platform - Agent Tooling |
agent
|
22 |
2025, Feb, 12 |
Platform - Context construction via RAG and Agent |
rag
agent
|
23 |
2025, Feb, 10 |
Platform - Prompting Engineering tools / Prompt Compression |
prompting
|
24 |
2025, Feb, 5 |
advanced LLM - Math reasoning |
reasoning
|
25 |
2025, Feb, 3 |
advanced LLM - for code reasoning |
reasoning
|
26 |
2025, Jan, 29 |
Survey - FMs in Robotics |
applications
|
27 |
2025, Jan, 27 |
Survey - FMs in healthcare |
applications
|
28 |
2025, Jan, 22 |
Survey - BioScience LLMs |
applications
|
29 |
2025, Jan, 20 |
more LLM basics - a survey |
basicllm
|
30 |
2025, Jan, 15 |
LLM basics - emergent ability and GenAI platform |
basicllm
|
31 |
2025, Jan, 13 |
Introduction |
basicllm
|
32 |
2024, Jun, 20 |
Privacy |
efficiency
llmevaluate
train
|
33 |
2024, Jun, 6 |
Gradient for LLM |
efficiency
llmevaluate
train
|
34 |
2024, May, 6 |
Gradient for LLM |
efficiency
llmevaluate
train
|
35 |
2024, May, 3 |
Safety Benchmark WMDP |
safety
mitigate
llmevaluate
adversarial
|
36 |
2024, Apr, 30 |
KV Cache and Tooling |
efficiency
|
37 |
2024, Apr, 25 |
Advanced Transformer Architectures |
efficiency
|
38 |
2024, Apr, 23 |
LLM fine tuning |
alignment
|
39 |
2024, Apr, 18 |
Recent LLM basics |
efficiency
basicllm
|
40 |
2024, Apr, 16 |
MultiAgent LLMs |
agent
|
41 |
2024, Apr, 11 |
LLM Agents |
agent
|
42 |
2024, Apr, 9 |
Self-exam LLM and reasoning |
reasoning
|
43 |
2024, Apr, 4 |
Prompt Engineering |
prompting
|
44 |
2024, Apr, 2 |
LLM Scaling law and Efficiency |
efficiency
|
45 |
2024, Mar, 28 |
LLM interpretibility, trust and knowledge conflicts |
interpretibility
|
46 |
2024, Mar, 26 |
Model editing and Disgorgement |
modeledit
|
47 |
2024, Mar, 21 |
Domain Centered FMs |
domainadapt
|
48 |
2024, Mar, 19 |
LLM Hallucination |
hallucination
|
49 |
2024, Mar, 14 |
Knowledge Augmented FMs |
rag
|
50 |
2024, Mar, 12 |
More FM risk |
safety
adversarial
|
51 |
2024, Feb, 29 |
LLM multimodal harm responses |
safety
adversarial
|
52 |
2024, Feb, 27 |
FM toxicity / harmful outputs |
safety
adversarial
|
53 |
2024, Feb, 22 |
FM fairness / bias issues |
bias
adversarial
|
54 |
2024, Feb, 20 |
FM privacy leakage issues |
mitigate
llmevaluate
adversarial
|
55 |
2024, Feb, 15 |
FM copyright infrigement |
mitigate
llmevaluate
adversarial
|
56 |
2024, Feb, 13 |
Survey AI Risk framework |
mitigate
llmevaluate
adversarial
|
57 |
2024, Feb, 8 |
Open Source LLM - Mistral Data preparation |
basicllm
|
58 |
2024, Feb, 6 |
Survey human alignment |
alignment
|
59 |
2024, Feb, 1 |
GenAI Guardrails |
mitigate
adversarial
|
60 |
2024, Jan, 30 |
LLM evaluating framework |
llmevaluate
|
61 |
2024, Jan, 25 |
Survey LLMs and Multimodal FMs |
basicllm
|
62 |
2024, Jan, 23 |
LLM basics |
basicllm
|
63 |
2022, Dec, 3 |
RLHF + InstructGPT |
rl
agi
language model
human alignment
|
64 |
2022, Dec, 1 |
Stable diffusion + DreamBooth + LoRA |
diffusion
image synthesis
efficiency
|
65 |
2022, Oct, 1 |
Emergent Abilities of LLM |
language model
|
66 |
2022, Sep, 1 |
DiffDock + ESMfold |
protein
language model
|
67 |
2022, Jun, 3 |
Decision Transformers |
rl
agi
|
68 |
2022, May, 3 |
A Generalist Agent + offline RL + UniMask |
rl
agi
|