6 papers
Revealing and Enhancing Core Visual Regions: Harnessing Internal Attention Dynamics for Hallucination Mitigation in LVLMs
Guangtao Lyu, Qi Liu, Chenghao Xu +5
LVLMs have achieved strong multimodal reasoning capabilities but remain prone to hallucinations, producing outputs inconsistent with visual inputs or user instructions. Existing tr…
Towards Arbitrary Motion Completing via Hierarchical Continuous Representation
Chenghao Xu, Guangtao Lyu, Qi Liu +3
Physical motions are inherently continuous, and higher camera frame rates typically contribute to improved smoothness and temporal coherence. For the first time, we explore continu…
A Turn Toward Better Alignment: Few-Shot Generative Adaptation with Equivariant Feature Rotation
Chenghao Xu, Qi Liu, Jiexi Yan +2
Few-shot image generation aims to effectively adapt a source generative model to a target domain using very few training images. Most existing approaches introduce consistency cons…
Revealing Perception and Generation Dynamics in LVLMs: Mitigating Hallucinations via Validated Dominance Correction
Guangtao Lyu, Xinyi Cheng, Chenghao Xu +7
Large Vision-Language Models (LVLMs) have shown remarkable capabilities, yet hallucinations remain a persistent challenge. This work presents a systematic analysis of the internal…
Tempo as the Stable Cue: Hierarchical Mixture of Tempo and Beat Experts for Music to 3D Dance Generation
Guangtao Lyu, Chenghao Xu, Qi Liu +4
Music to 3D dance generation aims to synthesize realistic and rhythmically synchronized human dance from music. While existing methods often rely on additional genre labels to furt…
A Tale of Two Experts: Cooperative Learning for Source-Free Unsupervised Domain Adaptation
Jiaping Yu, Muli Yang, Jiapeng Ji +2
Source-Free Unsupervised Domain Adaptation (SFUDA) addresses the realistic challenge of adapting a source-trained model to a target domain without access to the source data, driven…