12 papers
Evidence-Guided Counterfactual Learning for Long-Tailed Robotic Policies
Weiwei Chen, Chenghao Xu, Meiling Yu +2
In the practical deployment of vision--language--action policies, handling long-tailed task distributions is a common challenge due to the highly imbalanced composition of robot de…
Hear the World in Stereo: Learning Dynamic Spatial Correspondence for Immersive Joint Video-Audio Generation
Hanmo Chen, Chengcheng Liu, Tianxiao Chen +8
Recent joint video-audio generation models have achieved strong semantic correspondence and temporal synchronization. However, applications such as AR/VR and interactive gaming fur…
Remember Smarter: Visual History Compressor and Hyperbolic Experience Space for Robotic Memory
Dai Zhou, Jiexi Yan, Tong Li +2
Long-horizon robot policies require compact access to recent observations and reusable experience without expanding the vision-language-action (VLA) context. We introduce Remember…
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…
Past- and Future-Informed KV Cache Policy with Salience Estimation in Autoregressive Video Diffusion
Hanmo Chen, Chenghao Xu, Xu Yang +2
Video generation is pivotal to digital media creation, and recent advances in autoregressive video generation have markedly enhanced the efficiency of real-time video synthesis. Ho…
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…
DSCD-Nav: Dual-Stance Cooperative Debate for Object Navigation
Weitao An, Qi Liu, Chenghao Xu +4
Adaptive navigation in unfamiliar indoor environments is crucial for household service robots. Despite advances in zero-shot perception and reasoning from vision-language models, e…
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…