The original implementation of the Fast-2DGS paper

Aligning LMMs with Factually Augmented RLHF

The most open diffusion language model for code generation — releasing pretraining, evaluation, inference, and checkpoints.

Code for paper: LLaDA-MedV: Exploring Large Language Diffusion Models for Biomedical Image Understanding

Official implementation of BLIP3o-Series

Official repo for ICCV'25 paper: Cracking Instance Jigsaw Puzzles: An Alternative to Multiple Instance Learning for Whole Slide Image Analysis

OneShot Learning-based hotword detection.

Official code for the paper: DRA-GRPO: Exploring Diversity-Aware Reward Adjustment for R1-Zero-Like Training of Large Language Models

Code for paper: Talk Before You Retrieve: Agent-Led Discussions for Better RAG in Medical QA

A project to improve skills of large language models

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

Code for paper: How Effective Can Dropout Be in Multiple Instance Learning? (ICML 2025)

This is the first paper to explore how to effectively use R1-like RL for MLLMs and introduce Vision-R1, a reasoning MLLM that leverages cold-start initialization and RL training to incentivize reas…

No fortress, purely open ground. OpenManus is Coming.

Official repo for paper: "Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't"

[NeurIPS 2025] What Makes a Reward Model a Good Teacher? An Optimization Perspective

Code for paper: Prompt-OT: An Optimal Transport Regularization Paradigm for Knowledge Preservation in Vision-Language Model Adaptation

A fork to add multimodal model training to open-r1

Witness the aha moment of VLM with less than $3.

Explore the Multimodal “Aha Moment” on 2B Model

LLaVA-Mini is a unified large multimodal model (LMM) that can support the understanding of images, high-resolution images, and videos in an efficient manner.

Official implementation for NeurIPS'24 paper: MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making

$100K or 100 Days: Trade-offs when Pre-Training with Academic Resources

Code for paper: STA-Unet: Rethink the semantic redundant for Medical Imaging Segmentation

(WACV 2024) Code for paper: CUNSB-RFIE: Context-aware Unpaired Neural Schr¨odinger Bridge in Retinal Fundus Image Enhancement

Code for the paper "Context-Aware Optimal Transport Learning for Retinal Fundus Image Enhancement"