Kun Kuang

Think Then Rewrite: Reasoning Enhanced Query Rewriting for Domain Specific Retrieval AAAI 2026 Tailoring Diagnostic Modeling to Individual Learners: Personalized Distractor Generation via MCTS-Guided Reasoning Reconstruction ACL 2026 P2S: Probabilistic Process Supervision for General-Domain Reasoning Question Answering AAAI 2026 Detecting Unobserved Confounders: A Kernelized Regression Approach AAAI 2026 LeCoDe: A Benchmark Dataset for Interactive Legal Consultation Dialogue Evaluation ACL 2026 Decoding Correlation-Induced Misalignment in the Stable Diffusion Workflow for Text-to-Image Generation ICCV 2025 Evaluating Test-Time Scaling LLMs for Legal Reasoning: OpenAI o1, DeepSeek-R1, and Beyond EMNLP 2025 ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation EMNLP 2025 CoEvo: Coevolution of LLM and Retrieval Model for Domain-Specific Information Retrieval EMNLP 2025 CAT: Causal Attention Tuning For Injecting Fine-grained Causal Knowledge into Large Language Models EMNLP 2025 RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution EMNLP 2025 MergeNet: Knowledge Migration Across Heterogeneous Models, Tasks, and Modalities AAAI 2025 FedCFA: Alleviating Simpson’s Paradox in Model Aggregation with Counterfactual Federated Learning AAAI 2025 Learning Causal Transition Matrix for Instance-dependent Label Noise AAAI 2025 Optimize Incompatible Parameters Through Compatibility-aware Knowledge Integration AAAI 2025 Latent Score-Based Reweighting for Robust Classification on Imbalanced Tabular Data ICML 2025 Generalizing Causal Effects from Randomized Controlled Trials to Target Populations across Diverse Environments ICML 2025 D-Fusion: Direct Preference Optimization for Aligning Diffusion Models with Visually Consistent Samples ICML 2025 Legal Judgment Prediction based on Knowledge-enhanced Multi-Task and Multi-Label Text Classification NAACL 2025 Learning to Solve Domain-Specific Calculation Problems with Knowledge-Intensive Programs Generator NAACL 2025 Rethinking Causal Ranking: A Balanced Perspective on Uplift Model Evaluation ICML 2025 OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use ACL 2025 Embracing Imperfection: Simulating Students with Diverse Cognitive Levels Using LLM-based Agents ACL 2025 UniLR: Unleashing the Power of LLMs on Multiple Legal Tasks with a Unified Legal Retriever ACL 2025 Rewrite to Jailbreak: Discover Learnable and Transferable Implicit Harmfulness Instruction ACL 2025 Arrow: Accelerator for Time Series Causal Discovery with Time Weaving ICML 2025 Fine-tuning Large Language Models for Improving Factuality in Legal Question Answering COLING 2025 Advancing Personalized Learning with Neural Collapse for Long-Tail Challenge ICML 2025 Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards CVPR 2025 ERICT: Enhancing Robustness by Identifying Concept Tokens in Zero-Shot Vision Language Models ICML 2025 Distributionally Generative Augmentation for Fair Facial Attribute Classification CVPR 2024 CGMGM: A Cross-Gaussian Mixture Generative Model for Few-Shot Semantic Segmentation AAAI 2024 Learning to Reweight for Generalizable Graph Neural Network AAAI 2024 CoreRec: A Counterfactual Correlation Inference for Next Set Recommendation AAAI 2024 Contrastive Balancing Representation Learning for Heterogeneous Dose-Response Curves Estimation AAAI 2024 De-biased Attention Supervision for Text Classification with Causality AAAI 2024 LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild ACL 2024 Latent Learningscape Guided In-context Learning ACL 2024 Chain-of-Quizzes: Pedagogy-inspired Example Selection in In-Context-Learning ACL 2024 Enhancing Court View Generation with Knowledge Injection and Guidance COLING 2024 Evolving Knowledge Distillation with Large Language Models and Active Learning COLING 2024 From Graph to Word Bag: Introducing Domain Knowledge to Confusing Charge Prediction COLING 2024 Gold Panning in Vocabulary: An Adaptive Method for Vocabulary Expansion of Domain-Specific LLMs EMNLP 2024 More Than Catastrophic Forgetting: Integrating General Capabilities For Domain-Specific LLMs EMNLP 2024 Optimizing Language Models with Fair and Stable Reward Composition in Reinforcement Learning EMNLP 2024 MetaCoCo: A New Few-Shot Classification Benchmark with Spurious Correlation ICLR 2024 AuG-KD: Anchor-Based Mixup Generation for Out-of-Domain Knowledge Distillation ICLR 2024 InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks ICML 2024 A Generative Approach for Treatment Effect Estimation under Collider Bias: From an Out-of-Distribution Perspective ICML 2024 Learning Shadow Variable Representation for Treatment Effect Estimation under Collider Bias ICML 2024 Two-Stage Shadow Inclusion Estimation: An IV Approach for Causal Inference under Latent Confounding and Collider Bias ICML 2024 Learning Causal Relations from Subsampled Time Series with Two Time-Slices ICML 2024 Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models ICML 2024 Unleashing the Power of LLMs in Court View Generation by Stimulating Internal Knowledge and Incorporating External Knowledge NAACL 2024 Two Heads are Better Than One: A Simple Exploration Framework for Efficient Multi-Agent Reinforcement Learning NIPS 2023 RexUIE: A Recursive Method with Explicit Schema Instructor for Universal Information Extraction EMNLP 2023 Learning Instrumental Variable from Data Fusion for Treatment Effect Estimation AAAI 2023 Focus-aware Response Generation in Inquiry Conversation ACL 2023 MAP: Towards Balanced Generalization of IID and OOD through Model-Agnostic Adapters ICCV 2023 Learning from Good Trajectories in Offline Multi-Agent Reinforcement Learning AAAI 2023 Fairness-aware Contrastive Learning with Partially Annotated Sensitive Attributes ICLR 2023 Causal Structure Learning for Latent Intervened Non-stationary Data ICML 2023 Stable Estimation of Heterogeneous Treatment Effects ICML 2023 Learning Chemical Rules of Retrosynthesis with Pre-training AAAI 2023 Universal Domain Adaptation via Compressive Attention Matching ICCV 2023 Precedent-Enhanced Legal Judgment Prediction with LLM and Domain-Model Collaboration EMNLP 2023 Exploiting Contrastive Learning and Numerical Evidence for Confusing Legal Judgment Prediction EMNLP 2023 HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception NIPS 2023 GRASP: Navigating Retrosynthetic Planning with Goal-driven Policy NIPS 2022 ConfounderGAN: Protecting Image Data Privacy with Causal Confounder NIPS 2022 The Role of Deconfounding in Meta-learning ICML 2022 Deconfounded Value Decomposition for Multi-Agent Reinforcement Learning ICML 2022 Instrumental Variable Regression with Confounder Balancing ICML 2022 Dependency Parsing as MRC-based Span-Span Prediction ACL 2022 Investigating the Robustness of Natural Language Generation from Logical Forms via Counterfactual Samples EMNLP 2022 Towards Interactivity and Interpretability: A Rationale-based Legal Judgment Prediction Framework EMNLP 2022 BertGCN: Transductive Text Classification by Combining GNN and BERT IJCNLP 2021 Semi-Supervised Active Learning for Semi-Supervised Models: Exploit Adversarial Examples With Graph-Based Virtual Labels ICCV 2021 Judgment Prediction via Injecting Legal Knowledge into Neural Networks AAAI 2021 Explainable Automated Graph Representation Learning with Hyperparameter Importance ICML 2021 BertGCN: Transductive Text Classification by Combining GNN and BERT ACL 2021 Stable Adversarial Learning under Distributional Shifts AAAI 2021 De-Biased Court’s View Generation with Causality EMNLP 2020 Stable Prediction with Model Misspecification and Agnostic Distribution Shift AAAI 2020 Decorrelated Clustering with Data Selection Bias IJCAI 2020 Disentangled Graph Convolutional Networks ICML 2019