Dongsheng Li

DMHM: Density-aware Manifold Learning and Hybrid Mahalanobis Energy for LLMs-generated Text Detection ACL 2026 WALKSAFE: Risk-aware Graph Random Walk with Bi-GRPO for LLM Safety AAAI 2026 Improving Long-Context Summarization with Multi-Granularity Retrieval Optimization AAAI 2026 Knowledge Injection Exists in MoE? Exploring Expert-Aware Contrast Decoding in MoE for Mitigating LLMs’ Hallucinations ACL 2026 Sparrow: Text-Anchored Window Attention with Visual-Semantic Glimpsing for Speculative Decoding in Video LLMs ACL 2026 Alloc-MoE: Budget-Aware Expert Activation Allocation for Efficient Mixture-of-Experts Inference ACL 2026 CTTA-T: Continual Test-Time Adaptation for Text Understanding via Teacher-Student with a Domain-aware and Generalized Teacher ACL 2026 MONTROSE: LLM-driven Monte Carlo Tree Search Self-Refinement for Cross-Domain Rumor Detection ACL 2025 DYNTEXT: Semantic-Aware Dynamic Text Sanitization for Privacy-Preserving LLM Inference ACL 2025 DPGA-TextSyn: Differentially Private Genetic Algorithm for Synthetic Text Generation ACL 2025 Mitigate Position Bias in LLMs via Scaling a Single Hidden States Channel ACL 2025 LLM-based Rumor Detection via Influence Guided Sample Selection and Game-based Perspective Analysis ACL 2025 AGD: Adversarial Game Defense Against Jailbreak Attacks in Large Language Models ACL 2025 DreamDistribution: Learning Prompt Distribution for Diverse In-distribution Generation ICLR 2025 EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms NAACL 2025 EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction NAACL 2025 Oracle-MoE: Locality-preserving Routing in the Oracle Space for Memory-constrained Large Language Model Inference ICML 2025 What Makes a Good Diffusion Planner for Decision Making? ICLR 2025 pMoE: Prompting Diverse Experts Together Wins More in Visual Adaptation ICLR 2025 NeuroLM: A Universal Multi-task Foundation Model for Bridging the Gap between Language and EEG Signals ICLR 2025 SeCom: On Memory Construction and Retrieval for Personalized Conversational Agents ICLR 2025 SCBench: A KV Cache-Centric Analysis of Long-Context Methods ICLR 2025 How Do Large Language Models Understand Graph Patterns? A Benchmark for Graph Pattern Comprehension ICLR 2025 VisRL: Intention-Driven Visual Perception via Reinforced Reasoning ICCV 2025 GCML: Gradient Coherence Guided Meta-Learning for Cross-Domain Emerging Topic Rumor Detection EMNLP 2025 Correlation-Aware Example Selection for In-Context Learning with Nonsymmetric Determinantal Point Processes EMNLP 2025 Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference EMNLP 2025 Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key CVPR 2025 Habitizing Diffusion Planning for Efficient and Effective Decision Making ICML 2025 MMInference: Accelerating Pre-filling for Long-Context Visual Language Models via Modality-Aware Permutation Sparse Attention ICML 2025 Zero-resource Hallucination Detection for Text Generation via Graph-based Contextual Knowledge Triples Modeling AAAI 2025 Adversarial Domain Prompt Tuning and Generation for Single Domain Generalization CVPR 2025 Two-stage Generative Question Answering on Temporal Knowledge Graph Using Large Language Models ACL 2024 TaskBench: Benchmarking Large Language Models for Task Automation NIPS 2024 Can Graph Learning Improve Planning in LLM-based Agents? NIPS 2024 Stability and Generalization of Asynchronous SGD: Sharper Bounds Beyond Lipschitz and Smoothness NIPS 2024 Advancing Spiking Neural Networks for Sequential Modeling with Central Pattern Generators NIPS 2024 Towards Editing Time Series NIPS 2024 MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention NIPS 2024 EEG2Video: Towards Decoding Dynamic Visual Perception from EEG Signals NIPS 2024 Perception of Knowledge Boundary for Large Language Models through Semi-open-ended Question Answering NIPS 2024 Once Read is Enough: Domain-specific Pretraining-free Language Models with Cluster-guided Sparse Experts for Long-tail Domain Knowledge NIPS 2024 Understanding and Improving Training-free Loss-based Diffusion Guidance NIPS 2024 Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models AAAI 2024 Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery AAAI 2024 LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression ACL 2024 Improving Large Language Models in Event Relation Logical Prediction ACL 2024 POMP: Probability-driven Meta-graph Prompter for LLMs in Low-resource Unsupervised Neural Machine Translation ACL 2024 Emancipating Event Extraction from the Constraints of Long-Tailed Distribution Data Utilizing Large Language Models COLING 2024 KC-GenRe: A Knowledge-constrained Generative Re-ranking Method Based on Large Language Models for Knowledge Graph Completion COLING 2024 Disentangled Prompt Representation for Domain Generalization CVPR 2024 MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks EACL 2024 Online Video Quality Enhancement with Spatial-Temporal Look-up Tables ECCV 2024 Unified Medical Image Pre-training in Language-Guided Common Semantic Space ECCV 2024 Context-aware Watermark with Semantic Balanced Green-red Lists for Large Language Models EMNLP 2024 CNN Kernels Can Be the Best Shapelets ICLR 2024 Training-free Multi-objective Diffusion Model for 3D Molecule Generation ICLR 2024 Addressing Signal Delay in Deep Reinforcement Learning ICLR 2024 Efficient and Effective Time-Series Forecasting with Spiking Neural Networks ICML 2024 LLMs Can Find Mathematical Reasoning Mistakes by Pedagogical Chain-of-Thought IJCAI 2024 Exploring the Inefficiency of Heavy Ball as Momentum Parameter Approaches 1 IJCAI 2024 Meta-Tsallis-Entropy Minimization: A New Self-Training Approach for Domain Adaptation on Text Classification IJCAI 2023 Rotation-Invariant Transformer for Point Cloud Matching CVPR 2023 Similarity Distribution Based Membership Inference Attack on Person Re-identification AAAI 2023 Self-Evolution Learning for Mixup: Enhance Data Augmentation on Few-Shot Text Classification Tasks EMNLP 2023 GROVE: A Retrieval-augmented Complex Story Generation Framework with A Forest of Evidence EMNLP 2023 Adaptive Policy Learning for Offline-to-Online Reinforcement Learning AAAI 2023 Towards Inference Efficient Deep Ensemble Learning AAAI 2023 Learning Decomposed Spatial Relations for Multi-Variate Time-Series Modeling AAAI 2023 Stability-Based Generalization Analysis of the Asynchronous Decentralized SGD AAAI 2023 Explaining Temporal Graph Models through an Explorer-Navigator Framework ICLR 2023 Over-parameterized Model Optimization with Polyak-{\L}ojasiewicz Condition ICLR 2023 SIMPLE: Specialized Model-Sample Matching for Domain Generalization ICLR 2023 Data Continuity Matters: Improving Sequence Modeling with Lipschitz Regularizer ICLR 2023 EA-HAS-Bench: Energy-aware Hyperparameter and Architecture Search Benchmark ICLR 2023 Learning Topology-Agnostic EEG Representations with Geometry-Aware Modeling NIPS 2023 Momentum Ensures Convergence of SIGNSGD under Weaker Assumptions ICML 2023 CircuitNet: A Generic Neural Network to Realize Universal Circuit Motif Modeling ICML 2023 ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling NIPS 2023 HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face NIPS 2023 Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models NIPS 2023 A Canonicalization-Enhanced Known Fact-Aware Framework For Open Knowledge Graph Link Prediction IJCAI 2023 GRACE: Gradient-guided Controllable Retrieval for Augmenting Attribute-based Text Generation ACL 2023 Learning Joint Structural and Temporal Contextualized Knowledge Embeddings for Temporal Knowledge Graph Completion ACL 2023 Towards Understanding Omission in Dialogue Summarization ACL 2023 DiffusionNER: Boundary Diffusion for Named Entity Recognition ACL 2023 DaMSTF: Domain Adversarial Learning Enhanced Meta Self-Training for Domain Adaptation ACL 2023 End-to-End Word-Level Pronunciation Assessment with MASK Pre-training INTERSPEECH 2023 Transcormer: Transformer for Sentence Scoring with Sliding Language Modeling NIPS 2022 Bootstrapped Transformer for Offline Reinforcement Learning NIPS 2022 VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning NIPS 2022 Empathetic and Emotionally Positive Conversation Systems with an Emotion-specific Query-Response Memory EMNLP 2022 Reinforcement Learning with Automated Auxiliary Loss Search NIPS 2022 Neural Piecewise-Constant Delay Differential Equations AAAI 2022 Invariant Information Bottleneck for Domain Generalization AAAI 2022 RendNet: Unified 2D/3D Recognizer With Latent Space Rendering CVPR 2022 Finite-Time Analysis of Adaptive Temporal Difference Learning with Deep Neural Networks NIPS 2022 Variational oracle guiding for reinforcement learning ICLR 2022 Recursive Disentanglement Network ICLR 2022 Towards Applicable Reinforcement Learning: Improving the Generalization and Sample Efficiency with Policy Ensemble IJCAI 2022 Modeling Precursors for Temporal Knowledge Graph Reasoning via Auto-encoder Structure IJCAI 2022 Finding Global Homophily in Graph Neural Networks When Meeting Heterophily ICML 2022 Adaptive Random Walk Gradient Descent for Decentralized Optimization ICML 2022 Parameter-free Dynamic Graph Embedding for Link Prediction NIPS 2022 Improving Hypernasality Estimation with Automatic Speech Recognition in Cleft Palate Speech INTERSPEECH 2022 Improving Few-Shot Relation Classification by Prototypical Representation Learning with Definition Text NAACL 2022 Social Bot-Aware Graph Neural Network for Early Rumor Detection COLING 2022 Reinforcement Learning Enhanced Explainer for Graph Neural Networks NIPS 2021 Stability and Generalization of Decentralized Stochastic Gradient Descent AAAI 2021 Scalable and Explainable 1-Bit Matrix Completion via Graph Signal Learning AAAI 2021 Recognizing Vector Graphics without Rasterization NIPS 2021 Diversity and Consistency: Exploring Visual Question-Answer Pair Generation EMNLP 2021 Learning Invariant Representations and Risks for Semi-Supervised Domain Adaptation CVPR 2021 Energy-Based Open-World Uncertainty Modeling for Confidence Calibration ICCV 2021 NENN: Incorporate Node and Edge Features in Graph Neural Networks ACML 2020 Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification ACL 2019 Exploring Pre-trained Language Models for Event Extraction and Generation ACL 2019 A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning IJCNLP 2019 Non-Ergodic Convergence Analysis of Heavy-Ball Algorithms AAAI 2019 Read + Verify: Machine Reading Comprehension with Unanswerable Questions AAAI 2019 A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning EMNLP 2019 General Proximal Incremental Aggregated Gradient Algorithms: Better and Novel Results under General Scheme NIPS 2019 Heavy-ball Algorithms Always Escape Saddle Points IJCAI 2019 Correlation Congruence for Knowledge Distillation ICCV 2019 Towards Precise End-to-End Weakly Supervised Object Detection Network ICCV 2019 Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension ACL 2019 Attention-Guided Answer Distillation for Machine Reading Comprehension EMNLP 2018 Mixture-Rank Matrix Approximation for Collaborative Filtering NIPS 2017 Low-Rank Matrix Approximation with Stability ICML 2016 CubicRing: Enabling One-Hop Failure Detection and Recovery for Distributed In-Memory Storage Systems NSDI 2015