Repo for Implicit Diffusion Q-Learning

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.

Code for the paper "Offline Reinforcement Learning as One Big Sequence Modeling Problem"

verl: Volcano Engine Reinforcement Learning for LLMs

OpenMMLab Detection Toolbox and Benchmark

[NeurIPS 2025] The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

A programming framework for agentic AI

Official implementation of T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition

[ICLR 2025 Oral🔥] SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning

PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models(NeurIPS 2024 Spotlight)

Official PyTorch implementation of the paper "Dataset Distillation with Neural Characteristic Function: A Minmax Perspective" (NCFM) in CVPR 2025 (Full Score, Highlight).

Code for ACL 2025 Main paper "Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning".

This is the repo for the paper Multi-Agent Collaborative Data Selection for Efficient LLM Pretraining.

[ICML 2024] Official implementation of "LeaPformer: Enabling Linear Transformers for Autoregressive and Simultaneous Tasks via Learned Proportions."

Guangneng Hu, Assoc. Prof. @ Xidian Univ, PhD at HKUST, BA/MS at Nanjing Univ.

Code that accompanies the paper Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning - Accepted to ICML2024

[ECCV 2024] ShareGPT4V: Improving Large Multi-modal Models with Better Captions

Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team, Alibaba Cloud.

MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversation

Build effective agents using Model Context Protocol and simple workflow patterns

Benchmarks of approximate nearest neighbor libraries in Python

MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understanding

The model, data and code for the visual GUI Agent SeeClick

On the Hidden Mystery of OCR in Large Multimodal Models (OCRBench)

An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & TIS & vLLM & Ray & Dynamic Sampling & Async Agentic RL)