[Arxiv 2025: MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation]

From Handcrafted to Deep Features for Pedestrian Detection: A Survey (TPAMI 2021)

Official PyTorch Implementation of Unified Video Action Model (RSS 2025)

[CVPR 2025]Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulation

[CVPR 2024] The repository contains the official implementation of "Open-Vocabulary Segmentation with Semantic-Assisted Calibration"

[CVPR2025] Official implementation of the paper "Multi-Layer Visual Feature Fusion in Multimodal LLMs: Methods, Analysis, and Best Practices". (by Junyan Lin)

The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems

DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping

Implementation of π₀, the robotic foundation model architecture proposed by Physical Intelligence

Conditional Convolutions for Instance Segmentation, achives 37.1mAP on coco val

[ICLR 2025] Glad: A Streaming Scene Generator for Autonomous Driving

A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation

OpenVLA: An open-source vision-language-action model for robotic manipulation.

FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)

Open-vocabulary Semantic Segmentation

[NeurIPS'24 Oral] HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning

A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!

[ICLR 2024 Spotlight] "Negative Label Guided OOD Detection with Pretrained Vision-Language Models"

ECCV2024, LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language Models

The official implementation of CVPR 24' Paper "Learning Transferable Negative Prompts for Out-of-Distribution Detection"

ICCV 2023: CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No

Official Implementation of "Test-Time Optimization for Domain Adaptive Open Vocabulary Segmentation"

New repo collection for NVIDIA Cosmos: https://github.com/nvidia-cosmos

Code base of the BEVDet series .

AcadHomepage: A Modern and Responsive Academic Personal Homepage

[CVPR 2025] Official repository of the paper "Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation"