PPaperPicks

Kun Kuang

Zhejiang University, Lab of Artificial Intelligence, Zhejiang, China

69 papers at tracked venues · 57 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. Continuous-Time Counterfactual Quantile Learning for Risk-Sensitive Policy Optimization
  3. C²DLM: Causal Concept-Guided Diffusion Large Language Models
  4. Detecting Unobserved Confounders: A Kernelized Regression Approach
  5. Each Rank Could be an Expert: Single-Ranked Mixture of Experts LoRA for Multi-task Learning
  6. LeCoDe: A Benchmark Dataset for Interactive Legal Consultation Dialogue Evaluation
  7. P2S: Probabilistic Process Supervision for General-Domain Reasoning Question Answering
  8. SplitThenMerge: Token-Level Skill-Compositional Sparse Mixture-of-Experts for Complex Domain-Specific Tasks
  9. Tailoring Diagnostic Modeling to Individual Learners: Personalized Distractor Generation via MCTS-Guided Reasoning Reconstruction
  10. Think Then Rewrite: Reasoning Enhanced Query Rewriting for Domain Specific Retrieval
  11. Advancing Personalized Learning with Neural Collapse for Long-Tail Challenge
  12. Arrow: Accelerator for Time Series Causal Discovery with Time Weaving
  13. Augmenting Limited and Biased RCTs through Pseudo-Sample Matching-Based Observational Data Fusion Method
  14. CAT: Causal Attention Tuning For Injecting Fine-grained Causal Knowledge into Large Language Models
  15. ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation
  16. Classifying Treatment Responders: Bounds and Algorithms
  17. CoEvo: Coevolution of LLM and Retrieval Model for Domain-Specific Information Retrieval
  18. Collaboration of Large Language Models and Small Recommendation Models for Device-Cloud Recommendation
  19. D-Fusion: Direct Preference Optimization for Aligning Diffusion Models with Visually Consistent Samples
  20. Decoding Correlation-Induced Misalignment in the Stable Diffusion Workflow for Text-to-Image Generation
  21. ERICT: Enhancing Robustness by Identifying Concept Tokens in Zero-Shot Vision Language Models
  22. Embracing Imperfection: Simulating Students with Diverse Cognitive Levels Using LLM-based Agents
  23. Evaluating Test-Time Scaling LLMs for Legal Reasoning: OpenAI o1, DeepSeek-R1, and Beyond
  24. FedCFA: Alleviating Simpson's Paradox in Model Aggregation with Counterfactual Federated Learning
  25. Forward Once for All: Structural Parameterized Adaptation for Efficient Cloud-coordinated On-device Recommendation
  26. Generalizing Causal Effects from Randomized Controlled Trials to Target Populations across Diverse Environments
  27. Latent Score-Based Reweighting for Robust Classification on Imbalanced Tabular Data
  28. Learning Causal Transition Matrix for Instance-dependent Label Noise
  29. Learning to Solve Domain-Specific Calculation Problems with Knowledge-Intensive Programs Generator
  30. Legal Judgment Prediction based on Knowledge-enhanced Multi-Task and Multi-Label Text Classification
  31. Leveraging Invariant Principle for Heterophilic Graph Structure Distribution Shifts
  32. MS-Bench: Evaluating LMMs in Ancient Manuscript Study through a Dunhuang Case Study
  33. MergeNet: Knowledge Migration Across Heterogeneous Models, Tasks, and Modalities
  34. Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging
  35. OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use
  36. Optimize Incompatible Parameters Through Compatibility-aware Knowledge Integration
  37. RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution
  38. Rethinking Causal Ranking: A Balanced Perspective on Uplift Model Evaluation
  39. Rewrite to Jailbreak: Discover Learnable and Transferable Implicit Harmfulness Instruction
  40. Tackling Device Data Distribution Real-time Shift via Prototype-based Parameter Editing
  41. Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards
  42. UniLR: Unleashing the Power of LLMs on Multiple Legal Tasks with a Unified Legal Retriever
  43. A Generative Approach for Treatment Effect Estimation under Collider Bias: From an Out-of-Distribution Perspective
  44. AuG-KD: Anchor-Based Mixup Generation for Out-of-Domain Knowledge Distillation
  45. CGMGM: A Cross-Gaussian Mixture Generative Model for Few-Shot Semantic Segmentation
  46. Chain-of-Quizzes: Pedagogy-inspired Example Selection in In-Context-Learning
  47. Contrastive Balancing Representation Learning for Heterogeneous Dose-Response Curves Estimation
  48. CoreRec: A Counterfactual Correlation Inference for Next Set Recommendation
  49. De-biased Attention Supervision for Text Classification with Causality
  50. Distributionally Generative Augmentation for Fair Facial Attribute Classification
  51. Gold Panning in Vocabulary: An Adaptive Method for Vocabulary Expansion of Domain-Specific LLMs
  52. InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks
  53. Intelligent Model Update Strategy for Sequential Recommendation
  54. Latent Learningscape Guided In-context Learning
  55. Learning Causal Relations from Subsampled Time Series with Two Time-Slices
  56. Learning Shadow Variable Representation for Treatment Effect Estimation under Collider Bias
  57. Learning to Reweight for Generalizable Graph Neural Network
  58. LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild
  59. MetaCoCo: A New Few-Shot Classification Benchmark with Spurious Correlation
  60. Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models
  61. More Than Catastrophic Forgetting: Integrating General Capabilities For Domain-Specific LLMs
  62. Neural Collapse Anchored Prompt Tuning for Generalizable Vision-Language Models
  63. Optimizing Language Models with Fair and Stable Reward Composition in Reinforcement Learning
  64. Semantic Alignment for Multimodal Large Language Models
  65. Stable Heterogeneous Treatment Effect Estimation across Out-of-Distribution Populations
  66. Two-Stage Shadow Inclusion Estimation: An IV Approach for Causal Inference under Latent Confounding and Collider Bias
  67. Unleashing the Power of LLMs in Court View Generation by Stimulating Internal Knowledge and Incorporating External Knowledge
  68. Xinyu: An Efficient LLM-based System for Commentary Generation
  69. Your Neighbor Matters: Towards Fair Decisions Under Networked Interference