PPaperPicks

Bo Du

Wuhan University, School of Computer Science, China

84 papers at tracked venues · 64 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. GoT-R1: Internalizing Graph-of-Thought via Structural Reinforcement for High-Density Reasoning
  2. Hierarchical Prompt Contrastive Learning for Weakly Supervised Histopathology Segmentation
  3. HistCore: Scalable $k$-Core Decomposition on GPUs with Locality-Aware Computation
  4. MTGenRec: An Efficient Distributed Training System for Generative Recommendation Models in Meituan
  5. Rethinking Visual Token Reduction in LVLMs Under Cross-Modal Misalignment
  6. AiDE-Q: Synthetic Labeled Datasets Can Enhance Learning Models for Quantum Property Estimation
  7. Anatomy-Conserving Unpaired CBCT-to-CT Translation via Schrödinger Bridge
  8. Backdoor Cleaning without External Guidance in MLLM Fine-tuning
  9. Be Confident: Uncovering Overfitting in MLLM Multi-Task Tuning
  10. Brain Wiring Knowledge Graph Reasoning: A Region Embedding Approach for Logical Neuronal Relation Inference
  11. Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient
  12. CSDN: CLIP-Driven Similarity-Aligned Distillation Network for Weakly-Supervised Object Localization
  13. Cheb-GR: Rethinking K-nearest Neighbor Search in Re-ranking for Person Re-identification
  14. CogNav: Cognitive Process Modeling for Object Goal Navigation with LLMs
  15. CollagePrompt: A Benchmark for Budget-Friendly Visual Recognition with GPT-4V
  16. DGSolver: Diffusion Generalist Solver with Universal Posterior Sampling for Image Restoration
  17. DNASpeech: A Contextualized and Situated Text-to-Speech Dataset with Dialogues, Narratives and Actions
  18. Decision Mixer: Integrating Long-term and Local Dependencies via Dynamic Token Selection for Decision-Making
  19. Dynamic Parallel Tree Search for Efficient LLM Reasoning
  20. Enhancing Medical Dialogue Generation through Knowledge Refinement and Dynamic Prompt Adjustment
  21. Exploiting Text Semantics for Few and Zero Shot Node Classification on Text-attributed Graph
  22. From Parameters to Performance: A Data-Driven Study on LLM Structure and Development
  23. GHOST: Generalizable One-Shot Federated Graph Learning with Proxy-Based Topology Knowledge Retention
  24. GPU Architectures in Graph Analytics: A Comparative Experimental Study
  25. GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution
  26. HYPERION: Fine-Grained Hypersphere Alignment for Robust Federated Graph Learning
  27. Hounding Data Diversity: Towards Participant Selection in Vertical Federated Learning
  28. Improving Complex Reasoning over Knowledge Graph with Logic-Aware Curriculum Tuning
  29. KaFT: Knowledge-aware Fine-tuning for Boosting LLMs' Domain-specific Question-Answering Performance
  30. Learn from Downstream and Be Yourself in Multimodal Large Language Models Fine-Tuning
  31. Learning to Exploit Leg Odometry Enables Terrain-Aware Quadrupedal Locomotion
  32. MOTION: Multi-Sculpt Evolutionary Coarsening for Federated Continual Graph Learning
  33. Merging on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging
  34. MobileSteward: Integrating Multiple App-Oriented Agents with Self-Evolution to Automate Cross-App Instructions
  35. Multi-order Orchestrated Curriculum Distillation for Model-Heterogeneous Federated Graph Learning
  36. Neighborhood-Consistent Binary Transformation for Domain-Invariant Chest X-Ray Diagnosis
  37. Noise-Robust Tuning of SAM for Domain Generalized Ultrasound Image Segmentation
  38. OASIS: One-Shot Federated Graph Learning via Wasserstein Assisted Knowledge Integration
  39. Pixel-wise Divide and Conquer for Federated Vessel Segmentation
  40. Pseudo-label Enhanced TransUNet for Robust Landmark Localization in Intrapartum Ultrasound
  41. Rethink Sparse Signals for Pose-Guided Text-to-Image Generation
  42. Retrieval-Augmented Perception: High-resolution Image Perception Meets Visual RAG
  43. Segment First or Comprehend First? Explore the Limit of Unsupervised Word Segmentation with Large Language Models
  44. Self-Evolving Pseudo-Rehearsal for Catastrophic Forgetting with Task Similarity in LLMs
  45. Spotlighting Partially Visible Cinematic Language for Video-to-Audio Generation via Self-distillation
  46. Unsupervised Visible-Infrared Person Re-Identification Under Unpaired Settings
  47. Value-Guided Decision Transformer: A Unified Reinforcement Learning Framework for Online and Offline Settings
  48. WaterDiffusion: Learning a Prior-involved Unrolling Diffusion for Joint Underwater Saliency Detection and Visual Restoration
  49. When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Need
  50. All in One Framework for Multimodal Re-Identification in the Wild
  51. Cloth-aware Augmentation for Cloth-generalized Person Re-identification
  52. Cycle Self-Refinement for Multi-Source Domain Adaptation
  53. Fisher Calibration for Backdoor-Robust Heterogeneous Federated Learning
  54. Generative and Contrastive Paradigms Are Complementary for Graph Self-Supervised Learning
  55. GoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matching
  56. Imitation Learning from Purified Demonstrations
  57. Improving Bird's Eye View Semantic Segmentation by Task Decomposition
  58. Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names
  59. Joint Learning Neuronal Skeleton and Brain Circuit Topology with Permutation Invariant Encoders for Neuron Classification
  60. LeMeViT: Efficient Vision Transformer with Learnable Meta Tokens for Remote Sensing Image Interpretation
  61. Learning from Imperfect Data: Towards Efficient Knowledge Distillation of Autoregressive Language Models for Text-to-SQL
  62. MMSite: A Multi-modal Framework for the Identification of Active Sites in Proteins
  63. MOKD: Cross-domain Finetuning for Few-shot Classification via Maximizing Optimized Kernel Dependence
  64. MoreStyle: Relax Low-Frequency Constraint of Fourier-Based Image Reconstruction in Generalizable Medical Image Segmentation
  65. Multi-modal Auto-regressive Modeling via Visual Tokens
  66. OOP: Object-Oriented Programming Evaluation Benchmark for Large Language Models
  67. Online GNN Evaluation Under Test-time Graph Distribution Shifts
  68. Parameter Disparities Dissection for Backdoor Defense in Heterogeneous Federated Learning
  69. Parameter-Efficient Multi-Task Model Fusion with Partial Linearization
  70. ROSE Doesn't Do That: Boosting the Safety of Instruction-Tuned Large Language Models with Reverse Prompt Contrastive Decoding
  71. Revisiting Knowledge Distillation for Autoregressive Language Models
  72. SAT3D: Image-driven Semantic Attribute Transfer in 3D
  73. Self-Driven Entropy Aggregation for Byzantine-Robust Heterogeneous Federated Learning
  74. Self-Supervised Learning for Graph Dataset Condensation
  75. Self-supervised Contrastive Graph Views for Learning Neuron-Level Circuit Network
  76. Shifted Autoencoders for Point Annotation Restoration in Object Counting
  77. Sparse is Enough in Fine-tuning Pre-trained Large Language Models
  78. Spatial-Aware Attention Generative Adversarial Network for Semi-supervised Anomaly Detection in Medical Image
  79. Temporal Uplift Modeling for Online Marketing
  80. Toward Real Ultra Image Segmentation: Leveraging Surrounding Context to Cultivate General Segmentation Model
  81. UniGS: Unified Representation for Image Generation and Segmentation
  82. WIA-LD2ND: Wavelet-Based Image Alignment for Self-supervised Low-Dose CT Denoising
  83. What If the Input is Expanded in OOD Detection?
  84. When ControlNet Meets Inexplicit Masks: A Case Study of ControlNet on its Contour-following Ability