PPaperPicks

Fanhua Shang

17 papers at tracked venues · 16 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. FLASH: Focused Layer Attention Sink Hijacking
  2. FedAdamW: A Communication-Efficient Optimizer with Convergence and Generalization Guarantees for Federated Large Models
  3. Beyond Background Shift: Rethinking Instance Replay in Continual Semantic Segmentation
  4. Consistency of Local and Global Flatness for Federated Learning
  5. Dual Semantic Guidance for Open Vocabulary Semantic Segmentation
  6. FedAGC: Federated Continual Learning with Asymmetric Gradient Correction
  7. Greg: GEometry-Aware RegIon Refinement for Sign Language Video Generation
  8. Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging
  9. QBasicVSR: Temporal Awareness Adaptation Quantization for Video Super-Resolution
  10. Tight High-Probability Bounds for Nonconvex Heavy-Tailed Scenario under Weaker Assumptions
  11. Unsupervised Degradation Representation Aware Transform for Real-World Blind Image Super-Resolution
  12. Deep Correlated Prompting for Visual Recognition with Missing Modalities
  13. FedBCGD: Communication-Efficient Accelerated Block Coordinate Gradient Descent for Federated Learning
  14. Long-Tailed Learning as Multi-Objective Optimization
  15. Pose-Guided Fine-Grained Sign Language Video Generation
  16. Robust and Faster Zeroth-Order Minimax Optimization: Complexity and Applications
  17. SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network