PPaperPicks

Fei Wu

Zhejiang University, College of Computer Science and Technology, Hangzhou, China

88 papers at tracked venues · 70 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. "I Don't Know What to Say": A Fact-Filling Questionnaire Method to Help Non-Experts Talk to LegalAI Assistant
  2. C²DLM: Causal Concept-Guided Diffusion Large Language Models
  3. DAC-Bench: A Decision-Aware Benchmark for Compositional Mobile GUI Tasks
  4. Each Rank Could be an Expert: Single-Ranked Mixture of Experts LoRA for Multi-task Learning
  5. FlashANNS: GPU-Driven Asynchronous I/O Pipelining for Eliminating Storage-Compute Bottlenecks in Billion-Scale Similarity Search
  6. InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization
  7. InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection
  8. JELV: A Judge of Edit-Level Validity for Evaluation and Automated Reference Expansion in Grammatical Error Correction
  9. Mitigating Structural Knowledge Collapse in Domain-Specific LLMs via Morpheme-Aware KV-Aggregation
  10. Tailoring Diagnostic Modeling to Individual Learners: Personalized Distractor Generation via MCTS-Guided Reasoning Reconstruction
  11. ThinkRec: Thinking-based recommendation via LLM
  12. Towards Meta-Cognitive Knowledge Editing for Multimodal LLMs
  13. Advancing Personalized Learning with Neural Collapse for Long-Tail Challenge
  14. Benchmarking Multimodal CoT Reward Model Stepwise by Visual Program
  15. CAM: Asynchronous GPU-Initiated, CPU-Managed SSD Management for Batching Storage Access
  16. CHORD: Customizing Hybrid-precision On-device Model for Sequential Recommendation with Device-cloud Collaboration
  17. Causal Graph Transformer for Treatment Effect Estimation Under Unknown Interference
  18. ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation
  19. CoEvo: Coevolution of LLM and Retrieval Model for Domain-Specific Information Retrieval
  20. Collaboration of Large Language Models and Small Recommendation Models for Device-Cloud Recommendation
  21. Curriculum Model Merging: Harmonizing Chemical LLMs for Enhanced Cross-Task Generalization
  22. Device-Cloud Collaborative Correction for On-Device Recommendation
  23. Discriminator-Guided Embodied Planning for LLM Agent
  24. Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs
  25. ERICT: Enhancing Robustness by Identifying Concept Tokens in Zero-Shot Vision Language Models
  26. EcoFace: Audio-Visual Emotional Co-Disentanglement Speech-Driven 3D Talking Face Generation
  27. EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT
  28. Embracing Imperfection: Simulating Students with Diverse Cognitive Levels Using LLM-based Agents
  29. Evaluating Test-Time Scaling LLMs for Legal Reasoning: OpenAI o1, DeepSeek-R1, and Beyond
  30. ExpTalk: Diverse Emotional Expression via Adaptive Disentanglement and Refined Alignment for Speech-Driven 3D Facial Animation
  31. FedCFA: Alleviating Simpson's Paradox in Model Aggregation with Counterfactual Federated Learning
  32. GPT-NER: Named Entity Recognition via Large Language Models
  33. Hyperion: Co-Optimizing SSD Access and GPU Computation for Cost-Efficient GNN Training
  34. InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models
  35. InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion
  36. Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning
  37. Knowledge Is Power: Harnessing Large Language Models for Enhanced Cognitive Diagnosis
  38. Learning to Solve Domain-Specific Calculation Problems with Knowledge-Intensive Programs Generator
  39. Legal Judgment Prediction based on Knowledge-enhanced Multi-Task and Multi-Label Text Classification
  40. MRSAudio: A Large-Scale Multimodal Recorded Spatial Audio Dataset with Refined Annotations
  41. MS-Bench: Evaluating LMMs in Ancient Manuscript Study through a Dunhuang Case Study
  42. MadaKV: Adaptive Modality-Perception KV Cache Eviction for Efficient Multimodal Long-Context Inference
  43. MergeNet: Knowledge Migration Across Heterogeneous Models, Tasks, and Modalities
  44. Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering
  45. Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace
  46. Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging
  47. Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning
  48. Non-Natural Image Understanding with Advancing Frequency-based Vision Encoders
  49. OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use
  50. Optimize Incompatible Parameters Through Compatibility-aware Knowledge Integration
  51. Ratel: Optimizing Holistic Data Movement to Fine-tune 100B Model on a Consumer GPU
  52. Rethinking Causal Ranking: A Balanced Perspective on Uplift Model Evaluation
  53. Rewrite to Jailbreak: Discover Learnable and Transferable Implicit Harmfulness Instruction
  54. STARS: A Unified Framework for Singing Transcription, Alignment, and Refined Style Annotation
  55. T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts
  56. Tackling Device Data Distribution Real-time Shift via Prototype-based Parameter Editing
  57. Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration
  58. Training-free LLM-generated Text Detection by Mining Token Probability Sequences
  59. UniLR: Unleashing the Power of LLMs on Multiple Legal Tasks with a Unified Legal Retriever
  60. Vinci: Deep Thinking in Text-to-Image Generation using Unified Model with Reinforcement Learning
  61. Action Imitation in Common Action Space for Customized Action Image Synthesis
  62. Active Retrosynthetic Planning Aware of Route Quality
  63. Adapting Pre-trained Generative Model to Medical Image for Data Augmentation
  64. An Expert is Worth One Token: Synergizing Multiple Expert LLMs as Generalist via Expert Token Routing
  65. AuG-KD: Anchor-Based Mixup Generation for Out-of-Domain Knowledge Distillation
  66. Contrastive Balancing Representation Learning for Heterogeneous Dose-Response Curves Estimation
  67. Cross-Modality Cardiac Insight Transfer: A Contrastive Learning Approach to Enrich ECG with CMR Features
  68. De-biased Attention Supervision for Text Classification with Causality
  69. E3: Exploring Embodied Emotion Through A Large-Scale Egocentric Video Dataset
  70. GaussianTalker: Speaker-specific Talking Head Synthesis via 3D Gaussian Splatting
  71. Gold Panning in Vocabulary: An Adaptive Method for Vocabulary Expansion of Domain-Specific LLMs
  72. InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks
  73. LLMCO4MR: LLMs-Aided Neural Combinatorial Optimization for Ancient Manuscript Restoration from Fragments with Case Studies on Dunhuang
  74. Learning Causal Relations from Subsampled Time Series with Two Time-Slices
  75. Learning Shadow Variable Representation for Treatment Effect Estimation under Collider Bias
  76. Learning to Reweight for Generalizable Graph Neural Network
  77. LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild
  78. MPOD123: One Image to 3D Content Generation Using Mask-Enhanced Progressive Outline-to-Detail Optimization
  79. MetaCoCo: A New Few-Shot Classification Benchmark with Spurious Correlation
  80. More Than Catastrophic Forgetting: Integrating General Capabilities For Domain-Specific LLMs
  81. Non-confusing Generation of Customized Concepts in Diffusion Models
  82. PhiloGPT: A Philology-Oriented Large Language Model for Ancient Chinese Manuscripts with Dunhuang as Case Study
  83. Physical-Priors-Guided Aortic Dissection Detection Using Non-Contrast-Enhanced CT Images
  84. RetroOOD: Understanding Out-of-Distribution Generalization in Retrosynthesis Prediction
  85. Revisiting Score Propagation in Graph Out-of-Distribution Detection
  86. Semantic Alignment for Multimodal Large Language Models
  87. Semantic Codebook Learning for Dynamic Recommendation Models
  88. Unleashing the Power of LLMs in Court View Generation by Stimulating Internal Knowledge and Incorporating External Knowledge