PPaperPicks

Xin Geng

Southeast University, Key Lab of Computer Network and Information Integration, Nanjing, China

42 papers at tracked venues · 37 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Adaptive-Learngene: Continual Expansion and Task-Aware Selection of Learngenes for Dynamic Environments
  2. DivControl: Knowledge Diversion for Controllable Image Generation
  3. Extracting Multimodal Learngene in CLIP: Unveiling the Multimodal Generalizable Knowledge
  4. Learngene: Inheritable 'Genes' in Intelligent Agents (Abstract Reprint)
  5. MageBench: Bridging Large Multimodal Models to Agents
  6. Stratified Knowledge-Density Super-Network for Scalable Vision Transformers
  7. Can Class-Priors Help Single-Positive Multi-Label Learning?
  8. ECO: Evolving Core Knowledge for Efficient Transfer
  9. Enhancing Multimodal In-Context Learning for Image Classification through Coreset Optimization
  10. Fast Large Language Model Collaborative Decoding via Speculation
  11. FlowPrune: Accelerating Attention Flow Calculation by Pruning Flow Network
  12. Improved Noise Schedule for Diffusion Training
  13. Inheriting Generalized Learngene for Efficient Knowledge Transfer across Multiple Tasks
  14. KIND: Knowledge Integration and Diversion for Training Decomposable Models
  15. Label Distribution Learning with Biased Annotations Assisted by Multi-Label Learning
  16. Learngene Tells You How to Customize: Task-Aware Parameter Initialization at Flexible Scales
  17. Mimic In-Context Learning for Multimodal Tasks
  18. One-Shot Knowledge Transfer for Scalable Person Re-Identification
  19. Progressively Label Enhancement for Large Language Model Alignment
  20. RankMatch: A Novel Approach to Semi-Supervised Label Distribution Learning Leveraging Rank Correlation between Labels
  21. Redefining in Dictionary: Towards an Enhanced Semantic Understanding of Creative Generation
  22. Reduction-based Pseudo-label Generation for Instance-dependent Partial Label Learning
  23. Selective Label Enhancement Learning for Test-Time Adaptation
  24. SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimization
  25. VADIS: Investigating Inter-View Representation Biases for Multi-View Partial Multi-Label Learning
  26. WAVE: Weight Templates for Adaptive Initialization of Variable-sized Models
  27. Aligned Objective for Soft-Pseudo-Label Generation in Supervised Learning
  28. Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms
  29. Building Variable-Sized Models via Learngene Pool
  30. Cluster-Learngene: Inheriting Adaptive Clusters for Vision Transformers
  31. Correlation-Induced Label Prior for Semi-Supervised Multi-Label Learning
  32. Exploiting Multi-Label Correlation in Label Distribution Learning
  33. Exploring Learngene via Stage-wise Weight Sharing for Initializing Variable-sized Models
  34. Initializing Variable-sized Vision Transformers from Learngene with Learnable Transformation
  35. LIVE: Learnable In-Context Vector for Visual Question Answering
  36. Learning with Partial-Label and Unlabeled Data: A Uniform Treatment for Supervision Redundancy and Insufficiency
  37. Linearly Decomposing and Recomposing Vision Transformers for Diverse-Scale Models
  38. See Widely, Think Wisely: Toward Designing a Generative Multi-agent System to Burst Filter Bubbles
  39. Transformer as Linear Expansion of Learngene
  40. ULAREF: A Unified Label Refinement Framework for Learning with Inaccurate Supervision
  41. Vision Transformers as Probabilistic Expansion from Learngene
  42. What Makes Partial-Label Learning Algorithms Effective?