PPaperPicks

Xiaohan Zhang

20 papers at tracked venues · 17 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Hilbert Curve-Encoded Rotation-Equivariant Oriented Object Detector with Locality-Preserving Spatial Mapping
  2. Learning Better UAV-Based Cross-View Object Geo-Localization from Multi-Modal Prompts: MoP-UAV Benchmark and MoPT Framework
    AAAI 2026 · Xiaohan Zhang
  3. Melodia: Training-Free Music Editing Guided by Attention Probing in Diffusion Models
  4. SceneJailEval: A Scenario-Adaptive Multi-Dimensional Framework for Jailbreak Evaluation
  5. Semantic-Augmented Image Clustering via Adaptive Multi-Modal Collaboration
    AAAI 2026 · Xiaohan Zhang
  6. VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation
  7. Your Prompts Are Not Safe: Output-Free Membership Inference via Prompt Vectors in Vision-Language Tuning
  8. AlignMMBench: Evaluating Chinese Multimodal Alignment in Large Vision-Language Models
  9. CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
  10. LVBench: An Extreme Long Video Understanding Benchmark
  11. Toy-GS: Assembling Local Gaussians for Precisely Rendering Large-Scale Free Camera Trajectories
    AAAI 2025 · Xiaohan Zhang
  12. AlignBench: Benchmarking Chinese Alignment of Large Language Models
  13. AutoWebGLM: A Large Language Model-based Web Navigating Agent
  14. CharacterGLM: Customizing Social Characters with Large Language Models
  15. ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline
  16. KoLA: Carefully Benchmarking World Knowledge of Large Language Models
  17. MapGuide: A Simple yet Effective Method to Reconstruct Continuous Language from Brain Activities
  18. Medusa: Unveil Memory Exhaustion DoS Vulnerabilities in Protocol Implementations
  19. SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation
  20. Token-Level Contrastive Learning with Modality-Aware Prompting for Multimodal Intent Recognition