Yansong Tang

Segment Anything with Motion, Geometry, and Semantic Adaptation for Complex Nonlinear Visual Object Tracking

arXiv 2026

TAIHRI: Task-Aware 3D Human Keypoints Localization for Close-Range Human-Robot Interaction

arXiv 2026

Meta-CoT: Enhancing Granularity and Generalization in Image Editing

arXiv 2026

VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning

arXiv 2025

GaussianToken: An Effective Image Tokenizer with 2D Gaussian Splatting

arXiv 2025

FlexiAct: Towards Flexible Action Control in Heterogeneous Scenarios

arXiv 2025

VG-Refiner: Towards Tool-Refined Referring Grounded Reasoning via Agentic Reinforcement Learning

arXiv 2025

UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning

arXiv 2025

KV-Edit: Training-Free Image Editing for Precise Background Preservation

arXiv 2025

Flash-VStream: Efficient Real-Time Understanding for Long Video Streams

arXiv 2025

MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model

arXiv 2024

Momentum-GS: Momentum Gaussian Self-Distillation for High-Quality Large Scene Reconstruction

arXiv 2024

Q-VLM: Post-training Quantization for Large Vision-Language Models

arXiv 2024

ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulation

arXiv 2024

DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery

CVPR 2024 1

Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression

CVPR 2024 1

VoCo-LLaMA: Towards Vision Compression with Large Language Models

CVPR 2025 1

Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer

ICCV 2023 1

SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation

soc-semantic-assisted-object-cluster-for-1

Efficient Meshy Neural Fields for Animatable Human Avatars

arXiv 2023

Segment and Caption Anything

CVPR 2024 1

MCUFormer: Deploying Vision Transformers on Microcontrollers with Limited Memory

mcuformer-deploying-vision-tranformers-on

HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions

arXiv 2022

FineDance: A Fine-grained Choreography Dataset for 3D Full Body Dance Generation

ICCV 2023 1

DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting

CVPR 2022 1

Jiwen Lu

Jie zhou

Shiyi Zhang

Yong liu

Ziwei Wang

Haoji Zhang

Wenliang Zhao

Xiaoke Huang

Xiu Li

Yuji Wang