Profiles2020-2026ORCID 0000-0002-7118-6733
Di Hu
Renmin University of China
24Papers
16Last author
50Unique co-authors
1First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers24
- When would Vision-Proprioception Policies Fail in Robotic Manipulation?Author 5 of 5ICLR 2026 · 11 citations
- APPO: Attention-guided Perception Policy Optimization for Video ReasoningAuthor 4 of 4CVPR 2026 · 3 citations
- Information-Theoretic Decomposition for Multimodal Interaction LearningAuthor 5 of 5CVPR 2026 · 1 citation
- MokA: Multimodal Low-Rank Adaptation for MLLMsAuthor 4 of 4NeurIPS 2025 · 8 citations
- Adaptive Unimodal Regulation for Balanced Multimodal Information AcquisitionAuthor 4 of 4CVPR 2025
- Crab: A Unified Audio-Visual Scene Understanding Model with Explicit CooperationAuthor 6 of 6CVPR 2025
- Efficient Quantification of Multimodal Interaction at Sample LevelAuthor 3 of 3ICML 2025
- Patch Matters: Training-free Fine-grained Image Caption Enhancement via Local PerceptionAuthor 5 of 5CVPR 2025
- RollingQ: Reviving the Cooperation Dynamics in Multimodal TransformerAuthor 7 of 7ICML 2025
- MMPareto: Boosting Multimodal Learning with Innocent Unimodal AssistanceAuthor 2 of 2ICML 2024 · 86 citations
- Prompting Segmentation with Sound Is Generalizable Audio-Visual Source LocalizerAuthor 5 of 6AAAI 2024 · 42 citations
- Quantifying and Enhancing Multi-modal Robustness with Modality PreferenceAuthor 4 of 4ICLR 2024 · 27 citations
- Enhancing Multimodal Cooperation via Sample-Level Modality ValuationAuthor 4 of 4CVPR 2024 · 24 citations
- SphereDiffusion: Spherical Geometry-Aware Distortion Resilient Diffusion ModelAuthor 4 of 7AAAI 2024 · 24 citations
- Boosting Audio Visual Question Answering via Key Semantic-Aware CuesAuthor 3 of 3ACM MM 2024 · 16 citations
- Unveiling and Mitigating Bias in Audio Visual SegmentationAuthor 3 of 3ACM MM 2024 · 7 citations
- Progressive Spatio-temporal Perception for Audio-Visual Question AnsweringAuthor 3 of 3ACM MM 2023 · 39 citations
- TikTalk: A Video-Based Dialogue Dataset for Multi-Modal Chitchat in Real WorldAuthor 7 of 10ACM MM 2023 · 10 citations
- Learning to Answer Questions in Dynamic Audio-Visual ScenariosAuthor 6 of 6CVPR 2022 · 101 citations
- SepFusion: Finding Optimal Fusion Structures for Visual Sound SeparationAuthor 3 of 7AAAI 2022 · 14 citations
- Temporal Relational Modeling with Self-Supervision for Action SegmentationAuthor 2 of 4AAAI 2021 · 63 citations
- Cyclic Co-Learning of Sounding Object Visual Grounding and Sound SeparationAuthor 2 of 3CVPR 2021
- Unsupervised Multi-Source Domain Adaptation for Person Re-IdentificationAuthor 4 of 5CVPR 2021
- Discriminative Sounding Objects Localization via Self-supervised Audiovisual MatchingAuthor 1 of 8NeurIPS 2020 · 156 citations
