PPaperPicks

Wenqiang Zhang

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

Venues

Frequent coauthors

Papers

  1. CADiff: Context-Aware Diffusion for Controllable Anomaly Generation in Anomaly Detection
  2. Commonality in Few: Few-Shot Multimodal Anomaly Detection via Hypergraph-Enhanced Memory
  3. Seeing Is Believing: Rich-Context Hallucination Detection for MLLMs via Backward Visual Grounding
  4. Agentic RL Scaling Law: Spontaneous Code Execution for Mathematical Problem Solving
  5. Boosting Adversarial Transferability with Spatial Adversarial Alignment
  6. Component-Aware Unsupervised Logical Anomaly Generation for Industrial Anomaly Detection
  7. D2SP: Dynamic Dual-Stage Purification Framework for Dual Noise Mitigation in Vision-based Affective Recognition
  8. Dynamic Semantic-Aware Correlation Modeling for UAV Tracking
  9. Enhancing Diffusion-based Unrestricted Adversarial Attacks via Adversary Preferences Alignment
  10. ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulation
  11. General Compression Framework for Efficient Transformer Object Tracking
  12. NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results
  13. Noise Fusion-based Distillation Learning for Anomaly Detection in Complex Industrial Environments
  14. OUS: Bridging Scene Context and Facial Features to Overcome the Rigid Cognitive Problem
  15. OpenVIS: Open-vocabulary Video Instance Segmentation
  16. Progressive Representation Learning for Weakly-Supervised Camouflaged Object Detection
  17. Scoring, Remember, and Reference: Catching Camouflaged Objects in Videos
  18. Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection
  19. VideoSAM: Open-World Video Segmentation
  20. A User-Friendly Framework for Generating Model-Preferred Prompts in Text-to-Image Synthesis
  21. Adaptive Multi-modal Fusion of Spatially Variant Kernel Refinement with Diffusion Model for Blind Image Super-Resolution
  22. All rivers run into the sea: Unified Modality Brain-Inspired Emotional Central Mechanism
  23. De-Confounded Data-Free Knowledge Distillation for Handling Distribution Shifts
  24. DeTrack: In-model Latent Denoising Learning for Visual Object Tracking
  25. FD-UAD: Unsupervised Anomaly Detection Platform Based on Defect Autonomous Imaging and Enhancement
  26. LCGen: Mining in Low-Certainty Generation for View-consistent Text-to-3D
  27. MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution
  28. OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning
  29. OneVOS: Unifying Video Object Segmentation with All-in-One Transformer Framework
  30. Out of Thin Air: Exploring Data-Free Adversarial Robustness Distillation
  31. PanoVOS: Bridging Non-panoramic and Panoramic Views with Transformer for Video Segmentation
  32. Pixel-Level Semantic Correspondence Through Layout-Aware Representation Learning and Multi-Scale Matching Integration
  33. Sampling to Distill: Knowledge Transfer from Open-World Data
  34. Suppressing Uncertainties in Degradation Estimation for Blind Super-Resolution
  35. TagOOD: A Novel Approach to Out-of-Distribution Detection via Vision-Language Representations and Class Center Learning
  36. Visual-Language Collaborative Representation Network for Broad-Domain Few-Shot Image Classification
  37. X-Prompt: Multi-modal Visual Prompt for Video Object Segmentation