0

Wei-Shi Zheng

Papers
20

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
20papers

Authored papers

20

VLANeXt: Recipes for Building Strong VLA Models

arXiv 2026

2026

ObjEmbed: Towards Universal Multimodal Object Embeddings

arXiv 2026

2026

Seg-ReSearch: Segmentation with Interleaved Reasoning and External Search

arXiv 2026

2026

LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models

CVPR 2025 1

2025

Reinforcing Video Reasoning with Focused Thinking

arXiv 2025

2025

ViSpeak: Visual Instruction Feedback in Streaming Videos

ICCV 2025

2025

IRG-MotionLLM: Interleaving Motion Generation, Assessment and Refinement for Text-to-Motion Generation

arXiv 2025

2025

LOVE-R1: Advancing Long Video Understanding with an Adaptive Zoom-in Mechanism via Multi-Step Reasoning

arXiv 2025

2025

VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness

arXiv 2025

2025

Progressive Human Motion Generation Based on Text and Few Motion Frames

arXiv 2025

2025

ProEdit: Inversion-based Editing From Prompts Done Right

arXiv 2025

2025

ParGo: Bridging Vision-Language with Partial and Global Views

arXiv 2024

2024

InTraGen: Trajectory-controlled Video Generation for Object Interactions

arXiv 2024

2024

Grasp as You Say: Language-guided Dexterous Grasp Generation

arXiv 2024

2024

NECA: Neural Customizable Human Avatar

CVPR 2024 1

2024

EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding

arXiv 2024

2024

Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training

ICCV 2023 1

2023

ASAG: Building Strong One-Decoder-Layer Sparse Detectors via Adaptive Sparse Anchor Generation

ICCV 2023 1

2023

When Prompt-based Incremental Learning Does Not Meet Strong Pretraining

ICCV 2023 1

2023

Shape-Erased Feature Learning for Visible-Infrared Person Re-Identification

CVPR 2023 1

2023

Affiliations

No known affiliations.

Frequent co-authors

10

from 20 papers