PPaperPicks

Kele Xu

43 papers at tracked venues · 41 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Perturbing to Preserve: Defending Fragile Knowledge in Online Continual Learning
  2. Analytic Synaptic Dynamic Scaling Balancer for Multimodal Deepfake Continual Detection
  3. AudioSet-R: A Refined AudioSet with Multi-Stage LLM Label Reannotation
  4. Debiased Active Learning with Variational Gradient Rectifier
  5. Empowering Large Language Model Agent through Step-Level Self-Critique and Self-Training
  6. Enhancing Decision-Making for LLM Agents via Step-Level Q-Value Models
  7. Higher-Order Vision-Language Fusion for Video Popularity Prediction
    ACM MM 2025 · Kele Xu
  8. Improving the Continuity of Goal-Achievement Ability via Policy Self-Regularization for Goal-Conditioned Reinforcement Learning
  9. IntentVCNet: Bridging Spatio-Temporal Gaps for Intention-Oriented Controllable Video Captioning
  10. Investigating the Role of Weight Decay in Enhancing Nonconvex SGD
  11. Knowledge Memorization and Rumination for Pre-trained Model-based Class-Incremental Learning
  12. MER 2025: When Affective Computing Meets Large Language Models
  13. Maintaining Fairness in Logit-based Knowledge Distillation for Class-Incremental Learning
  14. Multi-view Fusion and Parameter Perturbation for Few-Shot Class-Incremental Audio Classification
  15. NTIRE 2025 Challenge on Event-Based Image Deblurring: Methods and Results
  16. NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfaces
  17. NTIRE 2025 Challenge on Image Super-Resolution (x4): Methods and Results
  18. NTIRE 2025 Challenge on Night Photography Rendering
  19. NTIRE 2025 Challenge on RAW Image Restoration and Super-Resolution
  20. NTIRE 2025 Image Shadow Removal Challenge Report
    CVPR 2025 ·
    Florin-Alexandru Vasluianu
  21. NTIRE 2025 challenge on Text to Image Generation Model Quality Assessment
  22. Preference-Strength-Aware Self-Improving Alignment with Generative Preference Models
  23. Relieving Universal Label Noise for Unsupervised Visible-Infrared Person Re-Identification by Inferring from Neighbors
  24. V-Pilot: A Velocity Vector Control Agent for Fixed-Wing UAVs from Imperfect Demonstrations
  25. VVC-Gym: A Fixed-Wing UAV Reinforcement Learning Environment for Multi-Goal Long-Horizon Problems
  26. Contrastive Learning-based Chaining-Cluster for Multilingual Voice-Face Association
  27. Deep RAW Image Super-Resolution. A NTIRE 2024 Challenge Survey
  28. Demonstrative Instruction Following in Multimodal LLMs via Integrating Low-Rank Adaptation with Ensemble Learning
  29. Enhancing Unsupervised Visible-Infrared Person Re-Identification with Bidirectional-Consistency Gradual Matching
  30. Goal-Conditioned On-Policy Reinforcement Learning
  31. Higher-Order Vision-Language Alignment for Social Media Prediction
  32. Iterative Regularized Policy Optimization with Imperfect Demonstrations
  33. MER 2024: Semi-Supervised Learning, Noise Robustness, and Open-Vocabulary Multimodal Emotion Recognition
  34. MRAC'24 Track 2: 2nd International Workshop on Multimodal and Responsible Affective Computing
  35. NTIRE 2024 Challenge on HR Depth from Images of Specular and Transparent Surfaces
  36. NTIRE 2024 Challenge on Image Super-Resolution (×4): Methods and Results
  37. NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results
  38. NTIRE 2024 Dense and Non-Homogeneous Dehazing Challenge Report
  39. Optimistic Model Rollouts for Pessimistic Offline Policy Optimization
  40. Stabilizing Zero-Shot Prediction: A Novel Antidote to Forgetting in Continual Vision-Language Tasks
  41. THE-FD: Task Hierarchical Emotion-aware for Fake Detection
  42. The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report
  43. Tracing Training Progress: Dynamic Influence Based Selection for Active Learning