PPaperPicks

Wei Wang

55 papers at tracked venues · 30 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. AdapThink: Adaptive Thinking Preferences for Reasoning Language Models
  2. Alloc-MoE: Budget-Aware Expert Activation Allocation for Efficient Mixture-of-Experts Inference
  3. ByteGraph-Dione: An Adaptive Dual-Format Graph Engine with Hotspot Awareness and Transaction Efficiency for Production-Scale Workloads
  4. CoordAR: One-Reference 6D Pose Estimation of Novel Objects via Autoregressive Coordinate Map Generation
  5. DGPO: Beyond Pairwise Preferences with Directional Consistent Groupwise Optimization
  6. Dynamic Generation of Multi LLM Agents Communication Topologies with Graph Diffusion Models
  7. Federated LoRA Fine-Tuning with Pipelined Error-Mitigated Aggregation and Matrix-Wise Freezing
  8. From Mathematical Reasoning to Code: Generalization of Process Reward Models in Test-Time Scaling
  9. MPA: Multimodal Prototype Augmentation for Few-Shot Learning
  10. Mind the Gap: The Divergence Between Human and LLM-Generated Tasks
  11. Quantization Meets Projection: A Happy Marriage for Approximate k-Nearest Neighbor Search
  12. RiskLab: A Controlled Toolkit for Probing Emergent Risks in LLM-Based Multi-Agent Systems
  13. SLCFormer: Spectral-Local Context Transformer with Physics-Grounded Flare Synthesis for Nighttime Flare Removal
  14. Taxon: Hierarchical Tax Code Prediction with Semantically Aligned LLM Expert Guidance
  15. A Data-Efficient Progressive Learning Framework for Robot Scooping Task
  16. A novel event-based structured light system for high-precision and high-speed depth sensing
  17. Accelerate Parallelizable Reasoning via Parallel Decoding within One Sequence
  18. AgentRefine: Enhancing Agent Generalization through Refinement Tuning
  19. An Inflatable Deployable Origami Grasper for Adaptive and High-Load Grasping
  20. CSR-Bench: Benchmarking LLM Agents in Deployment of Computer Science Research Repositories
  21. ComRAG: Retrieval-Augmented Generation with Dynamic Vector Stores for Real-time Community Question Answering in Industry
  22. DatawiseAgent: A Notebook-Centric LLM Agent Framework for Adaptive and Robust Data Science Automation
  23. Detoxifying Large Language Models via the Diversity of Toxic Samples
  24. Disentangle Nighttime Lens Flares: Self-supervised Generation-based Lens Flare Removal
  25. Enhancing the Performance of Global Model by Improving the Adaptability of Local Models in Federated Learning
  26. Hierarchical Frequency Tagging Probe (HFTP): A Unified Approach to Investigate Syntactic Structure Representations in Large Language Models and the Human Brain
  27. HyperTrans: Efficient Hypergraph-Driven Cross-Domain Pattern Transfer in Image Anomaly Detection
  28. IntelliCockpitBench: A Comprehensive Benchmark to Evaluate VLMs for Intelligent Cockpit
  29. InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct
  30. Learning 3D Medical Image Models from Brain Functional Connectivity Network Supervision for Mental Disorder Diagnosis
  31. Lightweight Front-end Enhancement for Robust ASR via Frame Resampling and Sub-Band Pruning
  32. Localized Data Shapley: Accelerating Valuation for Nearest Neighbor Algorithms
  33. Long-context Language Models Fail in Basic Retrieval Tasks Without Sufficient Reasoning Steps
  34. NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: Methods and Results
  35. Online Residual Model Learning for Model Predictive Control of Autonomous Surface Vehicles in Real-World Environments
  36. PUER: Boosting Few-shot Positive-Unlabeled Entity Resolution with Reinforcement Learning
  37. Private Online Learning against an Adaptive Adversary: Realizable and Agnostic Settings
  38. Private Realizable-to-Agnostic Transformation with Near-Optimal Sample Complexity
  39. QCRD: Quality-guided Contrastive Rationale Distillation for Large Language Models
    EMNLP 2025 · Wei Wang
  40. RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering
  41. UltraAD: Fine-Grained Ultrasound Anomaly Classification via Few-Shot CLIP Adaptation
  42. When Inverse Data Outperforms: Exploring the Pitfalls of Mixed Data in Multi-Stage Fine-Tuning
  43. BG3: A Cost Effective and I/O Efficient Graph Database in Bytedance
  44. CLAT: Convolutional Local Attention Tracker for Real-time UAV Target Tracking System with Feedback Information
  45. Deep Learning-Based Liver Vessel Separation with Plug-and-Play Modules: Skeleton Tracking and Graph Attention
  46. IDF-MFL: Infrastructure-free and Drift-free Magnetic Field Localization for Mobile Robot
  47. Learning from Long-Tailed Noisy Data with Sample Selection and Balanced Loss
  48. LucidAction: A Hierarchical and Multi-model Dataset for Comprehensive Action Quality Assessment
  49. MM4MM: Map Matching Framework for Multi-Session Mapping in Ambiguous and Perceptually-Degraded Environments
  50. MSGNN: Masked Schema based Graph Neural Networks
  51. Multi-Attention Based Visual-Semantic Interaction for Few-Shot Learning
  52. NTIRE 2024 Challenge on Blind Enhancement of Compressed Image: Methods and Results
  53. No More Ambiguity in 360° Room Layout via Bi-Layout Estimation
  54. Proving Olympiad Algebraic Inequalities without Human Demonstrations
  55. Solving General Natural-Language-Description Optimization Problems with Large Language Models