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…
Beyond Global Alignment: Fine-Grained Motion-Language Retrieval via Pyramidal Shapley-Taylor Learning
Hanmo Chen, Guangtao Lyu, Chenghao Xu +3
As a foundational task in human-centric cross-modal intelligence, motion-language retrieval aims to bridge the semantic gap between natural language and human motion, enabling intu…
Towards Interpretable Hallucination Analysis and Mitigation in LVLMs via Contrastive Neuron Steering
Guangtao Lyu, Xinyi Cheng, Qi Liu +5
LVLMs achieve remarkable multimodal understanding and generation but remain susceptible to hallucinations. Existing mitigation methods predominantly focus on output-level adjustmen…
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…
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…