PPaperPicks

Zhendong Mao

University of Science and Technology of China, School of Cyberspace Science and Technology, Hefei, China

55 papers at tracked venues · 50 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Align Documents to Questions: Question-Oriented Document Rewriting for Retrieval-Augmented Generation
  2. CodeRipple: Wavelet-Based Detection of LLM-Generated Code
  3. FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based Agents
  4. GraphSynthQA: Knowledge-Graph-Guided Query Synthesis and Step-Level Preference Optimization for Web Agents
  5. LAFaCT: Attribution-based Localization and Focused Sequential Analysis of Fact-Critical Tokens for Hallucination Detection
  6. LayerEdit: Disentangled Multi-Object Editing via Conflict-Aware Multi-Layer Learning
  7. MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools
  8. SparseRM: A Lightweight Preference Modeling with Sparse Autoencoder
  9. WildGraphBench: Benchmarking GraphRAG with Wild-Source Corpora
  10. Zero-Shot Detection of LLM-Generated Text using Temperature Sensitivity
  11. A4A: Adapter for Adapter Transfer via All-for-All Mapping for Cross-Architecture Models
  12. Alleviating Hallucinations in Large Language Models via Truthfulness-driven Rank-adaptive LoRA
  13. Automated Creativity Evaluation for Large Language Models: A Reference-Based Approach
  14. CustomContrast: A Multilevel Contrastive Perspective for Subject-Driven Text-to-Image Customization
  15. D2iT: Dynamic Diffusion Transformer for Accurate Image Generation
  16. Dragin3D: Image Editing by Dragging in 3D Space
  17. DualReal: Adaptive Joint Training for Lossless Identity-Motion Fusion in Video Customization
  18. ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA
  19. FeedEdit: Text-Based Image Editing with Dynamic Feedback Regulation
  20. Fine-grained Knowledge Enhancement for Retrieval-Augmented Generation
  21. From Real to Synthetic: Synthesizing Millions of Diversified and Complicated User Instructions with Attributed Grounding
  22. Graph Mixture of Experts and Memory-augmented Routers for Multivariate Time Series Anomaly Detection
  23. Hierarchy-Aware Pseudo Word Learning with Text Adaptation for Zero-Shot Composed Image Retrieval
  24. Improve Safety Training of Large Language Models with Safety-Critical Singular Vectors Localization
  25. Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models
  26. Leveraging robust optimization for llm alignment under distribution shifts
  27. LongAnimation: Long Animation Generation with Dynamic Global-Local Memory
  28. M-RangeDetector: Enhancing Generalization in Machine-Generated Text Detection through Multi-Range Attention Masks
  29. MIRROR: Multi-agent Intra- and Inter-Reflection for Optimized Reasoning in Tool Learning
  30. Mitigating Biases in Language Models via Bias Unlearning
  31. Multi-round Mutual Emotion-Cause Pair Extraction for Emotion-Attributed Video Captioning
  32. NeuraLeaf: Neural Parametric Leaf Models with Shape and Deformation Disentanglement
  33. On-the-fly Preference Alignment via Principle-Guided Decoding
  34. Pro3D-Editor: A Progressive-Views Perspective for Consistent and Precise 3D Editing
  35. Rationales Are Not Silver Bullets: Measuring the Impact of Rationales on Model Performance and Reliability
  36. Realgeneral: Unifying Visual Generation Via Temporal in-Context Learning With Video Models
  37. Rethinking Pseudo Word Learning in Zero-Shot Composed Image Retrieval: From an Object-Aware Perspective
  38. SVLTA: Benchmarking Vision-Language Temporal Alignment via Synthetic Video Situation
  39. Benchmarking Large Language Models on Controllable Generation under Diversified Instructions
  40. Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation
  41. Chain-of-Question: A Progressive Question Decomposition Approach for Complex Knowledge Base Question Answering
  42. Disentangled Learning with Synthetic Parallel Data for Text Style Transfer
  43. DreamIdentity: Enhanced Editability for Efficient Face-Identity Preserved Image Generation
  44. Dual-path Collaborative Generation Network for Emotional Video Captioning
  45. Feature-Adaptive and Data-Scalable In-Context Learning
  46. FlipGuard: Defending Preference Alignment against Update Regression with Constrained Optimization
  47. Gradual Residuals Alignment: A Dual-Stream Framework for GAN Inversion and Image Attribute Editing
  48. Homology Consistency Constrained Efficient Tuning for Vision-Language Models
  49. Identification of Necessary Semantic Undertakers in the Causal View for Image-Text Matching
  50. KNN-Instruct: Automatic Instruction Construction with K Nearest Neighbor Deduction
  51. Knowledge Context Modeling with Pre-trained Language Models for Contrastive Knowledge Graph Completion
  52. LIRE: listwise reward enhancement for preference alignment
  53. Linguistic-Aware Patch Slimming Framework for Fine-Grained Cross-Modal Alignment
  54. RESEMO: A Benchmark Chinese Dataset for Studying Responsive Emotion from Social Media Content
  55. RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customization