Sibei Yang

19

Papers

122

Total Citations

1

Affiliations

Affiliations

The University of Hong Kong

Papers (19)

OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers

Curriculum Point Prompting for Weakly-Supervised Referring Image Segmentation

Dissecting and Mitigating Diffusion Bias via Mechanistic Interpretability

WildRefer: 3D Object Localization in Large-scale Dynamic Scenes with Multi-modal Visual Data and Natural Language

Rethinking Query-based Transformer for Continual Image Segmentation

Why LVLMs Are More Prone to Hallucinations in Longer Responses: The Role of Context

CityAnchor: City-scale 3D Visual Grounding with Multi-modality LLMs

Vision Function Layer in Multimodal LLMs

Intervene-All-Paths: Unified Mitigation of LVLM Hallucinations across Alignment Formats

Sim-DETR: Unlock DETR for Temporal Sentence Grounding

No More Sibling Rivalry: Debiasing Human-Object Interaction Detection

VTON 360: High-Fidelity Virtual Try-On from Any Viewing Direction

Free on the Fly: Enhancing Flexibility in Test-Time Adaptation with Online EM

SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model

Adaptive Part Learning for Fine-Grained Generalized Category Discovery: A Plug-and-Play Enhancement

Augmenting Moment Retrieval: Zero-Dependency Two-Stage Learning

VLDrive: Vision-Augmented Lightweight MLLMs for Efficient Language-grounded Autonomous Driving

Closed-Loop Transfer for Weakly-supervised Affordance Grounding

Penalizing Boundary Activation for Object Completeness in Diffusion Models