EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

Model Context Protocol Servers

RePlan: Reasoning-Guided Region Planning for Complex Instruction-Based Image Editing

Official inference repo for FLUX.2 models

An open-source AI agent that lives in your terminal.

Official implementation of "Cutting Through Privacy: A Hyperplane-Based Data Reconstruction Attack in Federated Learning" (UAI 2025)

Official code for "Epistemic uncertainty in conformal scores: a unified approach", UAI 2025

Official code for paper "Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning"

The implementation of FedCADO (Classifier-Assisted Diffusion for One-shot Federated learning method)

[ICML 2025] MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding

Code of “Multi-Modal Deep Learning Enables Ultrafast and Accurate Annotation of Enzymatic Active Sites”

Official repository for NeurIPS 2025 paper "Understanding and Improving Adversarial Robustness of Neural Probabilistic Circuits"

Official code for FaCT: Faithful Concept Traces for Explaining Neural Network Decisions. NeurIPS 2025

[NeurIPS 2025] Robustness in Both Domains: CLIP Needs a Robust Text Encoder

MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image Reasoning [NeurIPS 2025 Poster]

[NeurIPS 2025] An official source code for paper "Continual Multimodal Contrastive Learning"

[NeurIPS 2025] Leveraging Depth and Language for Open-Vocabulary Domain-Generalized Semantic Segmentation

[Neurips 2025 NextVid Workshop Oral✨] Official Implementation of VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention

[NeurIPS'25][OralGPT & MMOral] The official repo of OralGPT & MMOral Bench.

Compressed Radiation Treatment Planning [NeurIPS'24, MP'2025, PMB'23]

Official implementation of Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents (NeurIPS 2025)

[NeurIPS 2025 Official Codes] Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D Rewards