Lists (22)
3DV
serving for 3D world models4 repositories
benchmark
6 repositories
Data Collection
Some valuable data analysis, like data of papers ratings, weather condtions.... things like that4 repositories
Dataset Curations
Data influence, Data distillations, Data selections12 repositories
diffusion
5 repositories
Diffusion Acceleration
2 repositories
GomokuAI
AI agent collection for AI course projects5 repositories
Interview
2 repositories
LLM Editing
1 repository
LongContextLLM
6 repositories
MLSys
10 repositories
MoE
2 repositories
PaperList
1 repository
RLHF
2 repositories
Template
3 repositories
Tools
12 repositories
Tutorials
5 repositories
video-post-processing-tools
1 repository
VideoData
This list contains some useful tools & datasets relevant to video data curating & making4 repositories
VideoUnderstanding
14 repositories
Web Deveploment
前端/后端资料1 repository
WorldModel
23 repositories
Starred repositories
A pixel desktop pet that watches Claude Code, Codex, Cursor & other AI coding agents — so you don't have to.
Code for Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers (https://arxiv.org/abs/2606.31779)
EdgeBench: Unveiling scaling laws of learning from real-world environments
DFlash: Block Diffusion for Flash Speculative Decoding
GPU-optimized framework for training diffusion language models at any scale. The backend of Quokka, Super Data Learners, and OpenMoE 2 training.
Skill package for ML/CV/NLP paper writing, curated and adapted from Prof. Peng Sida's open notes for Codex, Claude Code, and Gemini.
Lifting Monocular Video for 4D Multi-Object Interactions via Human-Agent Collaboration
7
Updated Jun 30, 2026
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
A tutorial on modern GPU programming for machine learning systems
Official repository for the paper "LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code"
AI 时代的伯克希尔：基于 Claude Code / Codex 的价值投资研究框架。巴菲特·芒格·段永平·李录四大师方法论 + 多Agent并行研究。| AI-era Berkshire: a value investing research framework built for Claude Code / Codex. 4 masters' methodologies + multi…
A curated, non-BS library of the best resources for building and evaluating AI agents — papers, blogs, talks, tools, benchmarks. Maintained by BenchFlow.
DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…
Skills for Real Engineers. Straight from my .agents directory.
Student version of Assignment 1 for Stanford CS336 - Language Modeling From Scratch
Solve puzzles. Improve your pytorch.
Official codebase for "Next-Latent Prediction Transformers Learn Compact World Models"