PPaperPicks

Shuhui Wang

20 papers at tracked venues · 19 at CORE A* · active 20242025

Venues

Frequent coauthors

Papers

  1. Dis²Booth: Learning Image Distribution with Disentangled Features for Text-to-Image Diffusion Models
  2. Divide-and-Conquer: Tree-structured Strategy with Answer Distribution Estimator for Goal-Oriented Visual Dialogue
  3. Edit Less, Achieve More: Dynamic Sparse Neuron Masking for Lifelong Knowledge Editing in LLMs
  4. Enhancing Pre-trained Representation Classifiability can Boost its Interpretability
  5. Image-to-video Adaptation with Outlier Modeling and Robust Self-learning
  6. Learning Fine-Grained Representations through Textual Token Disentanglement in Composed Video Retrieval
  7. MSR: A Multifaceted Self-Retrieval Framework for Microscopic Cascade Prediction
  8. Masked Temporal Interpolation Diffusion for Procedure Planning in Instructional Videos
  9. Relieving the Over-Aggregating Effect in Graph Transformers
  10. SVDLoRA: Data-Driven Low-Rank Adaptation via Spectral Decomposition
  11. VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set
  12. Video Language Model Pretraining with Spatio-temporal Masking
  13. Bias-Conflict Sample Synthesis and Adversarial Removal Debias Strategy for Temporal Sentence Grounding in Video
  14. Confusing Pair Correction Based on Category Prototype for Domain Adaptation under Noisy Environments
  15. Data-free Neural Representation Compression with Riemannian Neural Dynamics
  16. Expanding Sparse Tuning for Low Memory Usage
  17. Modeling Language Tokens as Functionals of Semantic Fields
  18. R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation
  19. Towards Dynamic Message Passing on Graphs
  20. Unsupervised Image-to-Video Adaptation via Category-aware Flow Memory Bank and Realistic Video Generation