PPaperPicks

Xiang Wang

University of Science and Technology of China, CCCD Key Lab of Ministry of Culture and Tourism, Hefei, China

77 papers at tracked venues · 68 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Causal-HalBench: Uncovering LVLMs Object Hallucinations Through Causal Intervention
  2. Delayed Feedback Modeling with Influence Functions
  3. Interpretable Reward Model via Sparse Autoencoder
  4. LPEdit: Locality-Preserving Knowledge Editing for MultiModal Large Language Models
  5. RMBRec: Robust Multi-Behavior Recommendation towards Target Behaviors
  6. Res-Bench: Benchmarking the Robustness of Multimodal Large Language Models to Dynamic Resolution Input
  7. SepSeq: A Training-Free Framework for Long Numerical Sequence Processing in LLMs
  8. Task-Aligned Unlearning for Multimodal Large Language Models
  9. 3D-GSRD: 3D Molecular Graph Auto-Encoder with Selective Re-mask Decoding
  10. A Unified Invariant Learning Framework for Graph Classification
  11. ACE: Concept Editing in Diffusion Models without Performance Degradation
  12. Addressing Missing Data Issue for Diffusion-based Recommendation
  13. AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization
  14. AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models
  15. AlphaFuse: Learn ID Embeddings for Sequential Recommendation in Null Space of Language Embeddings
  16. AnyEdit: Edit Any Knowledge Encoded in Language Models
  17. DAMA: Data- and Model-aware Alignment of Multi-modal LLMs
  18. DiffGAD: A Diffusion-based Unsupervised Graph Anomaly Detector
  19. Explainable and Efficient Editing for Large Language Models
  20. Fading to Grow: Growing Preference Ratios via Preference Fading Discrete Diffusion for Recommendation
  21. Generative Recommendation Models: Progress and Directions
  22. Geometric Alignment and Prior Modulation for View-Guided Point Cloud Completion on Unseen Categories
  23. Hello Again! LLM-powered Personalized Agent for Long-term Dialogue
  24. Intermediate Connectors and Geometric Priors for Language-Guided Affordance Segmentation on Unseen Object Categories
  25. LANCE: Exploration and Reflection for LLM-based Textual Attacks on News Recommender Systems
  26. LaMP-Val: Large Language Models Empower Personalized Valuation in Auction
  27. Language Representations Can be What Recommenders Need: Findings and Potentials
  28. Larger or Smaller Reward Margins to Select Preferences for LLM Alignment?
  29. Learning Bayesian Nash Equilibrium in Auction Games via Approximate Best Response
  30. Multi-Grained Patch Training for Efficient LLM-based Recommendation
  31. Multi-agent Architecture Search via Agentic Supernet
  32. NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation
  33. Neuron-Level Sequential Editing for Large Language Models
  34. On Efficiency-Effectiveness Trade-off of Diffusion-based Recommenders
  35. On Reasoning Strength Planning in Large Reasoning Models
  36. Personal Travel Solver: A Preference-Driven LLM-Solver System for Travel Planning
  37. Precise, Fast, and Low-cost Concept Erasure in Value Space: Orthogonal Complement Matters
  38. RePO: Understanding Preference Learning Through ReLU-Based Optimization
  39. Reinforced Lifelong Editing for Language Models
  40. Robust Preference Optimization via Dynamic Target Margins
  41. Route Sparse Autoencoder to Interpret Large Language Models
  42. START: Self-taught Reasoner with Tools
  43. SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding
  44. Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning
  45. Teaching Language Models to Reason with Tools
  46. Think before Recommendation: Autonomous Reasoning-enhanced Recommender
  47. Towards Large Generative Recommendation: A Tokenization Perspective
  48. Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization
  49. Towards Unified and Lossless Latent Space for 3D Molecular Latent Diffusion Modeling
  50. Unified Parameter-Efficient Unlearning for LLMs
  51. Auctionformer: A Unified Deep Learning Algorithm for Solving Equilibrium Strategies in Auction Games
  52. BSL: Understanding and Improving Softmax Loss for Recommendation
  53. CIRP: Cross-Item Relational Pre-training for Multimodal Product Bundling
  54. Customizing Language Models with Instance-wise LoRA for Sequential Recommendation
  55. Disentangling Masked Autoencoders for Unsupervised Domain Generalization
  56. Dynamicity-aware Social Bot Detection with Dynamic Graph Transformers
  57. EXGC: Bridging Efficiency and Explainability in Graph Condensation
  58. Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model
  59. General Debiasing for Graph-based Collaborative Filtering via Adversarial Graph Dropout
  60. Graph Anomaly Detection with Bi-level Optimization
  61. Invariant Graph Learning for Causal Effect Estimation
  62. LASO: Language-Guided Affordance Segmentation on 3D Object
  63. LLaRA: Large Language-Recommendation Assistant
  64. Let Me Do It For You: Towards LLM Empowered Recommendation via Tool Learning
  65. Leveraging Multimodal Features and Item-level User Feedback for Bundle Construction
  66. Masked Graph Modeling with Multi- View Contrast
  67. MolTC: Towards Molecular Relational Modeling In Language Models
  68. MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning
  69. On Generative Agents in Recommendation
  70. On Softmax Direct Preference Optimization for Recommendation
  71. ProtT3: Protein-to-Text Generation for Text-based Protein Understanding
  72. ReactXT: Understanding Molecular "Reaction-ship" via Reaction-Contextualized Molecule-Text Pretraining
  73. Simulating Human Society with Large Language Model Agents: City, Social Media, and Economic System
  74. Text-to-Image Generation for Abstract Concepts
  75. Towards 3D Molecule-Text Interpretation in Language Models
  76. Towards Neuron Attributions in Multi-Modal Large Language Models
  77. β-DPO: Direct Preference Optimization with Dynamic β