YifeiWang

SkillClaw. Let Skills Evolve Collectively with Agentic Evolver

AutoResearchClaw. Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

skills. Public repository for Agent Skills

openclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

verl. verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

SkillRL. SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

MemAgent. A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.

Wan2.2. Wan: Open and Advanced Large-Scale Video Generative Models

ViLoMem. ViLoMem: Agentic Learner with Grow-and-Refine Multimodal Semantic Memory

large-qa-datasets. A collection of large question answering datasets

AutoDeco. Python

Pos2Distill-. [EMNLP25] Official code for "POSITION BIAS MITIGATES POSITION BIAS: Mitigate Position Bias Through Inter-Position Knowledge Distillation"

Glyph. Official Repository for "Glyph: Scaling Context Windows via Visual-Text Compression"

DeepSeek-OCR. Contexts Optical Compression

D2O. [ICLR 2025🔥] D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models

loki. Algorithms for approximate attention in LLMs

hydra. Hydra is a framework for elegantly configuring complex applications

streaming-llm. [ICLR 2024] Efficient Streaming Language Models with Attention Sinks

Quest. [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference

ASVD4LLM. Activation-aware Singular Value Decomposition for Compressing Large Language Models

VideoRoPE. [ICML 2025 Oral] An official implementation of VideoRoPE & VideoRoPE++

LLaVA-NeXT. Python

needle-in-a-haystack. Doing simple retrieval from LLM models at various context lengths to measure accuracy

Awesome-LLM-KV-Cache. Awesome-LLM-KV-Cache: A curated list of 📙Awesome LLM KV Cache Papers with Codes.

MInference. [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filling on an A100 while maintaining accuracy.

WUDI-Merging. The official repository of "Whoever Started the Interference Should End It: Guiding Data-Free Model Merging via Task Vectors""

Block-Attention. Python

Awesome-LLM-Long-Context-Modeling. 📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥

DeepEP. DeepEP: an efficient expert-parallel communication library

OpenRLHF. An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

trl. Train transformer language models with reinforcement learning.

open-r1. Fully open reproduction of DeepSeek-R1

lost-in-the-middle. Code and data for "Lost in the Middle: How Language Models Use Long Contexts"

BIG-Bench-Hard. Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

Rank-Calibration. This is the repo for constructing a comprehensive and rigorous evaluation framework for LLM calibration.

FollowRAG. The demo, code and data of FollowRAG

SaySelf. Public code repo for paper "SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales"

fMRLRec. [EMNLP 2024 Findings] Official Implementation of Full-Scale Matryoshka Representation Learning for Multimodal Recommendation (fMRLRec).

Awesome-LLM-Uncertainty-Reliability-Robustness. Awesome-LLM-Robustness: a curated list of Uncertainty, Reliability and Robustness in Large Language Models

TransformerLens. A library for mechanistic interpretability of GPT-style language models

csbench. Python

llm-hallucination-survey. Reading list of hallucination in LLMs. Check out our new survey paper: "Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models"

How-To-Think-Step-by-Step. How to think step-by-step: A mechanistic understanding of chain-of-thought reasoning

Awesome-Reasoning-Foundation-Models. ✨✨Latest Papers and Benchmarks in Reasoning with Foundation Models

MQuAKE. [EMNLP 2023] MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions

RippleEdits. Evaluating the Ripple Effects of Knowledge Editing in Language Models

LRURec. [WSDM 2024] Official PyTorch Implementation of Linear Recurrent Units for Sequential Recommendation (LRURec)

reasoning-teacher. Large Language Models Are Reasoning Teachers (ACL 2023)

char-rnn. Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch

DeepLearning. 深度学习入门教程, 优秀文章, Deep Learning Tutorial

ABL-HED. Handwritten Equations Decipherment with Abductive Learning