PPaperPicks

Liang Li

Chinese Academy of Sciences, Institute of Computing Technology, Key Laboratory of Intelligent Information Processing, Beijing, China

35 papers at tracked venues · 34 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Forgetting Knowledge Localization and Isolation for Continual Forgetting of Pre-trained Vision Models
  2. InstructDubber: Instruction-based Alignment for Zero-shot Movie Dubbing
  3. STaR: Sensitive Trajectory Regulation for Unlearning in Large Reasoning Models
  4. Temporal Calibrating and Distilling for Scene-Text Aware Text-Video Retrieval
  5. Change Entity-guided Heterogeneous Representation Disentangling for Change Captioning
  6. DCTMamba: Advancing JPEG Image Restoration Through Long-Sequence Modeling and Adaptive Frequency Strategy
  7. Debiased Teacher for Day-to-Night Domain Adaptive Object Detection
  8. EmoDubber: Towards High Quality and Emotion Controllable Movie Dubbing
  9. FlowDubber: Movie Dubbing with LLM-based Semantic-aware Learning and Flow Matching based Voice Enhancing
  10. Frequency Dynamic Convolution for Dense Image Prediction
  11. Frequency-aware Correlation Discovering and Spatial Forgery Clue Distilling for Synthetic Image Detection
  12. From Language to Instance: Generative Visual Prompting for Zero-shot Camouflaged Object Detection
  13. Generalizing Single-Frame Supervision to Event-Level Understanding for Video Anomaly Detection
  14. Heterogeneous Prompt-Guided Entity Inferring and Distilling for Scene-Text Aware Cross-Modal Retrieval
  15. Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation
  16. Progressive Homeostatic and Plastic Prompt Tuning for Audio-Visual Multi-Task Incremental Learning
  17. Prosody-Enhanced Acoustic Pre-training and Acoustic-Disentangled Prosody Adapting for Movie Dubbing
  18. Query-centric Audio-Visual Cognition Network for Moment Retrieval, Segmentation and Step-Captioning
  19. Region-aware Difference Distilling with Attribute-guided Contrastive Regularization for Change Captioning
  20. SafeCFG: Controlling Harmful Features with Dynamic Safe Guidance for Safe Generation
  21. Separation of Powers: On Segregating Knowledge from Observation in LLM-enabled Knowledge-based Visual Question Answering
  22. Context-aware Difference Distilling for Multi-change Captioning
  23. Distractors-Immune Representation Learning with Cross-Modal Contrastive Regularization for Change Captioning
  24. Domain Shared and Specific Prompt Learning for Incremental Monocular Depth Estimation
  25. From Speaker to Dubber: Movie Dubbing with Prosody and Duration Consistency Learning
  26. Leveraging Catastrophic Forgetting to Develop Safe Diffusion Models against Malicious Finetuning
  27. LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection
  28. Make RepVGG Greater Again: A Quantization-Aware Approach
  29. Norm Tweaking: High-Performance Low-Bit Quantization of Large Language Models
    AAAI 2024 · Liang Li
  30. Pick-and-Draw: Training-free Semantic Guidance for Text-to-Image Personalization
  31. Prompt-Enhanced Multiple Instance Learning for Weakly Supervised Video Anomaly Detection
  32. R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation
  33. Stochastic Context Consistency Reasoning for Domain Adaptive Object Detection
  34. StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbing
  35. SynSP: Synergy of Smoothness and Precision in Pose Sequences Refinement