Agent Trading Arena has been accepted to EMNLP 2025. DecoupledMarket is our follow-up work accepted to ICML 2026.

[NeurIPS2025] ReID5o: Achieving Omni Multi-modal Person Re-identification in a Single Model

Dual Pseudo-Labels Interactive Self-Training for Semi-Supervised Visible-Infrared Person Re-Identification

[AAAI 2025] PAT: Pruning-Aware Tuning for Large Language Models

This repo is the official implementation of "Retrieval-Augmented Dynamic Prompt Tuning for Incomplete Multimodal Learning" accepted by AAAI 2025.

Official implementation of the paper "Attentive Eraser: Unleashing Diffusion Model’s Object Removal Potential via Self-Attention Redirection Guidance" (AAAI 2025 Oral)

【AAAI2025】MambaPro: Multi-Modal Object Re-Identification with Mamba Aggregation and Synergistic Prompt

[AAAI 2025] RhythmMamba

[AAAI 2025] Official implementation of the paper "Exploring Semantic Consistency and Style Diversity for Domain Generalized Semantic Segmentation"

【AAAI2025】DeMo: Decoupled Feature-Based Mixture of Experts for Multi-Modal Object Re-Identification

[AAAI2025] FedCFA: Alleviating Simpson’s Paradox in Model Aggregation with Counterfactual Federated Learning

✨ [AAAI 2025] Queryable Prototype Multiple Instance Learning with Vision-Language Models for Incremental Whole Slide Image Classification

[2025] Language-driven Motion Prior Knowledge Learning for Moving Infrared Small Target Detection

[AAAI2025] Offical code implementation of "Context-aware Inductive Knowledge Graph Completion with Latent Type Constraints and Subgraph Reasoning"

An official implementation of "Re-Attentional Controllable Video Diffusion Editing" in PyTorch. (AAAI 2025)

Code implement for FastToG

Official repository for paper "MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement"

BoxMOT: Pluggable python and c++ SOTA multi-object tracking modules with support for axis-aligned and oriented bounding boxes

⚡️ 10x - Up to 20x faster AI coding with multi-step Superpowers. Open-source agent with smart model routing, BYOK, fully self-hosted.

[NeurIPS2024] Cross-video Identity Correlating for Person Re-identification Pre-training

COALA: A Practical and Vision-Centric Federated Learning Platform, accepted to ICML'24

[CVPR 2024] Official Repository for "Efficient Test-Time Adaptation of Vision-Language Models"