LeapLabTHU

Official Repository of Absolute Zero Reasoner

Official Repository of Cooragent.

Repository of Vision Transformer with Deformable Attention (CVPR2022) and DAT++: Spatially Dynamic Vision Transformerwith Deformable Attention

[ECCV 2024] Official repository of Agent Attention

[ICCV 2023] Official repository of FLatten Transformer

Official repository of ACmix (CVPR2022)

[CVPR 2026] [Best Paper Finalist] [Oral] Official repository of Vision Test-Time Training

[NeurIPS 2024] Official repository of MLLA

repo for paper https://arxiv.org/abs/2504.13837

[Nature Communications 2025] Towards Expert-level Autonomous Carotid Ultrasonography with Large-scale Learning-based Robotic System

[ICML 2026 Outstanding Paper] Minimalist RL for Diffusion LLMs. 89.1% on GSM8K.

1.5−3.0× lossless training or pre-training speedup. An off-the-shelf, easy-to-implement algorithm for the efficient training of foundation visual backbones.

Official repository of Slide-Transformer (CVPR2023)

[CVPR2024] GSVA: Generalized Segmentation via Multimodal Large Language Models

[Nature Machine Intelligence 2025] Emulating Human-like Adaptive Vision for Efficient and Flexible Machine Visual Perception

[CVPR 2022] Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding

[ICCV 2023] Adaptive Rotated Convolution for Rotated Object Detection

[Pattern Recognition 2025] Cross-Modal Adapter for Vision-Language Retrieval

Official repository of ActiveNeRF (ECCV2022)

[NeurIPS 2023] Rank-DETR for High Quality Object Detection

Pytorch implementation of DAPrompt: https://arxiv.org/abs/2202.06687

[TPAMI 2024] Probabilistic Contrastive Learning for Long-Tailed Visual Recognition

[CVPR 2022] Official repository of AdaFocusV2.

Code release for Deep Incubation (https://arxiv.org/abs/2212.04129)

Official implementation of "What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling"

[AAAI 2026] Official repository of Circulant Attention

[NeurIPS 2024] Official repository of InLine attention

[CVPR 2025] CheXWorld: Exploring Image World Modeling for Radiograph Representation Learning

Official repository of Uni-AdaFocus (TPAMI 2024).

[CVPR 2025] EchoWorld: Learning Motion-Aware World Models for Echocardiography Probe Guidance

🔥 Regeneration over editing: unlocking more effective image refinement!

[IEEE TPAMI] Latency-aware Unified Dynamic Networks for Efficient Image Recognition