← authors · overview

• EventBind: Learning a Unified Representation to Bind Them All for Event-based Open-world Understanding
  2023 · 5 citations
• Image Anything: Towards Reasoning-coherent and Training-free Multi-modal Image Generation
  2024 · 3 citations
• EventDance++: Language-guided Unsupervised Source-free Cross-modal Adaptation for Event-based Object Recognition
  2024 · 1 citations
• FedWeave: Rethinking the Unit of Specialization in Heterogeneous Federated MoE-LoRA
  2026
• FedWeave: Rethinking the Unit of Specialization in Heterogeneous Federated MoE-LoRA
  2026
• SatireDecoder: Visual Cascaded Decoupling for Enhancing Satirical Image Comprehension
  2025
• PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era
  2025
• Marrying Autoregressive Transformer and Diffusion with Multi-Reference Autoregression
  2025
• Bixformer: A Robust Framework For Maximizing Modality Effectiveness In Multi-modal Semantic Segmentation
  2025
• Split Matching For Inductive Zero-shot Semantic Segmentation
  2025
• MLLMs are Deeply Affected by Modality Bias
  2025
• Shifting AI Efficiency From Model-Centric to Data-Centric Compression
  2025
• Robust Multimodal Semantic Segmentation With Balanced Modality Contributions
  2025
• Omnidirectional Spatial Modeling From Correlated Panoramas
  2025
• Mllms Are Deeply Affected By Modality Bias
  2025