Xiang Li

Human Cognition Inspired RAG with Knowledge Graph for Complex Problem Solving AAAI 2026 LPPG-RL: Lexicographically Projected Policy Gradient Reinforcement Learning with Subproblem Exploration AAAI 2026 RATE: Reviewer Profiling and Annotation-free Training for Expertise Ranking in Peer Review Systems ACL 2026 SwiftEP: Accelerating MoE Inference with Buffer Fusion and TMA Offloading NSDI 2026 Unsupervised Text Style Transfer for Controllable Intensity EACL 2026 Can Large Language Models Act as Ensembler for Multi-GNNs? EMNLP 2025 Enhancing Generalization of Speech Large Language Models with Multi-Task Behavior Imitation and Speech-Text Interleaving Interspeech 2025 Enhancing LLM-based Hatred and Toxicity Detection with Meta-Toxic Knowledge Graph ACL 2025 Holmes: Localizing Irregularities in LLM Training with Mega-scale GPU Clusters NSDI 2025 Initializing and Retrofitting Key-Value Adaptors for Traceable Model Editing ACL 2025 Let’s Be Self-generated via Step by Step: A Curriculum Learning Approach to Automated Reasoning with Large Language Models ACL 2025 Leveraging Large Language Models for Node Generation in Few-Shot Learning on Text-Attributed Graphs AAAI 2025 LogiGraph: Logical Reasoning with Contrastive Learning and Lightweight Graph Networks COLING 2025 Multi-level Relevance Document Identifier Learning for Generative Retrieval ACL 2025 PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization NAACL 2025 Permitted Knowledge Boundary: Evaluating the Knowledge-Constrained Responsiveness of Large Language Models EMNLP 2025 SEAGraph: Unveiling the Whole Story of Paper Review Comments IJCNLP 2025 Text Detoxification: Data Efficiency, Semantic Preservation and Model Generalization EMNLP 2025 TreeEval: Benchmark-Free Evaluation of Large Language Models through Tree Planning AAAI 2025 Unlocking ECMP Programmability for Precise Traffic Control NSDI 2025 AlphaFin: Benchmarking Financial Analysis with Retrieval-Augmented Stock-Chain Framework COLING 2024 Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis EMNLP 2024 Boosting Language Models Reasoning with Chain-of-Knowledge Prompting ACL 2024 Conjoin after Decompose: Improving Few-Shot Performance of Named Entity Recognition COLING 2024 Cross-model Control: Improving Multiple Large Language Models in One-time Training NeurIPS 2024 Make Prompt-based Black-Box Tuning Colorful: Boosting Model Generalization from Three Orthogonal Perspectives COLING 2024 Structure-aware Fine-tuning for Code Pre-trained Models COLING 2024 Training-free Multi-objective Diffusion Model for 3D Molecule Generation ICLR 2024 TransCoder: Towards Unified Transferable Code Representation Learning Inspired by Human Skills COLING 2024 UniAudio 1.5: Large Language Model-Driven Audio Codec is A Few-Shot Audio Task Learner NeurIPS 2024 DFRD: Data-Free Robustness Distillation for Heterogeneous Federated Learning NeurIPS 2023 DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language Models EMNLP 2023 Diverse and Expressive Speech Prosody Prediction with Denoising Diffusion Probabilistic Model Interspeech 2023 Evaluating and Enhancing the Robustness of Code Pre-trained Models through Structure-Aware Adversarial Samples Generation EMNLP 2023 Explaining Temporal Graph Models through an Explorer-Navigator Framework ICLR 2023 GradMA: A Gradient-Memory-Based Accelerated Federated Learning With Alleviated Catastrophic Forgetting CVPR 2023 LD2: Scalable Heterophilous Graph Neural Network with Decoupled Embeddings NeurIPS 2023 Pass-Tuning: Towards Structure-Aware Parameter-Efficient Tuning for Code Representation Learning EMNLP 2023 Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding EMNLP 2023 When Gradient Descent Meets Derivative-Free Optimization: A Match Made in Black-Box Scenario ACL 2023 A Neural Network Architecture for Program Understanding Inspired by Human Behaviors ACL 2022 CALM: Constrastive Cross-modal Speaking Style Modeling for Expressive Text-to-Speech Synthesis Interspeech 2022 CAT-probing: A Metric-based Approach to Interpret How Pre-trained Models for Programming Language Attend Code Structure EMNLP 2022 CGMN: A Contrastive Graph Matching Network for Self-Supervised Graph Similarity Learning IJCAI 2022 Content-Dependent Fine-Grained Speaker Embedding for Zero-Shot Speaker Adaptation in Text-to-Speech Synthesis Interspeech 2022 Finding Global Homophily in Graph Neural Networks When Meeting Heterophily ICML 2022 Knowledge Prompting in Pre-trained Language Model for Natural Language Understanding EMNLP 2022 Lexical Knowledge Internalization for Neural Dialog Generation ACL 2022 RAW-GNN: RAndom Walk Aggregation based Graph Neural Network IJCAI 2022 Towards Cross-speaker Reading Style Transfer on Audiobook Dataset Interspeech 2022 Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation ACL 2021 Reinforcement Learning Enhanced Explainer for Graph Neural Networks NeurIPS 2021 Towards Multi-Scale Style Control for Expressive Speech Synthesis Interspeech 2021 Spectral Clustering in Heterogeneous Information Networks AAAI 2019