Stars
Self-study on Larry Wasserman's "All of Statistics"
[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-filli…
Student version of Assignment 1 for Stanford CS336 - Language Modeling From Scratch
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥
Democratizing Reinforcement Learning for LLMs
Efficient Triton Kernels for LLM Training
Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"
[AAAI 2025]This repo contains evaluation code for the paper “UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarios”
A general AI agent framework that can be adapted to various tasks and environments.
Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.
OpenCodeInterpreter is a suite of open-source code generation systems aimed at bridging the gap between large language models and sophisticated proprietary systems like the GPT-4 Code Interpreter. …
A natural language interface for computers
Enforce the output format (JSON Schema, Regex etc) of a language model
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & LoRA & vLLM & RFT)
My learning notes/codes for ML SYS.
A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.
[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"
The official implementation of the paper “Street-to-Satellite Image Synthesis with Diffusion Models and BEV Paradigm”
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Code repository for paper: "G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Models"
[ICLR 2025 Spotlight] The official implementation of the paper “LOKI：A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models”
This is the repo for the paper Multi-Agent Collaborative Data Selection for Efficient LLM Pretraining.
Python implementation of OpenAI's realtime API
Awesome lists about framework figures in papers