PPaperPicks

Yunhai Tong

18 papers at tracked venues · 16 at CORE A* · active 20242025

Venues

Frequent coauthors

Papers

  1. Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs
  2. Conditional Panoramic Image Generation via Masked Autoregressive Modeling
  3. Decouple and Track: Benchmarking and Improving Video Diffusion Transformers for Motion Transfer
  4. DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation
  5. DreamRelation: Bridging Customization and Relation Generation
  6. Explore In-Context Segmentation via Latent Diffusion Models
  7. MMaDA: Multimodal Large Diffusion Language Models
  8. MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning
  9. RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything
  10. Towards Scalable and Deep Graph Neural Networks via Noise Masking
  11. Training-Free Heterogeneous Graph Condensation via Data Selection
  12. HGAMLP: Heterogeneous Graph Attention MLP with De-Redundancy Mechanism
  13. MotionBooth: Motion-Aware Customized Text-to-Video Generation
  14. SEFraud: Graph-based Self-Explainable Fraud Detection via Interpretative Mask Learning
  15. SemFlow: Binding Semantic Segmentation and Image Synthesis via Rectified Flow
  16. Towards Language-Driven Video Inpainting via Multimodal Large Language Models
  17. VG4D: Vision-Language Model Goes 4D Video Recognition
  18. You Can't Ignore Either: Unifying Structure and Feature Denoising for Robust Graph Learning