Sheng Li

COMPASS: Enhancing Agent Long-Horizon Reasoning with Evolving Context ACL 2026 Reducing Token Redundancy in LVLMs: A Systematic Review of Token Pruning Methods ACL 2026 Doubly Robust Causal Estimation Under Multi-View Network Interference (Student Abstract) AAAI 2026 Mutual Effort for Efficiency: A Similarity-based Token Pruning for Vision Transformers in Self-Supervised Learning ICLR 2025 BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing ICML 2025 Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety ICML 2025 Mind Control through Causal Inference: Predicting Clean Images from Poisoned Data ICLR 2025 The Photographer's Eye: Teaching Multimodal Large Language Models to See, and Critique Like Photographers CVPR 2025 Unified Dense Prediction of Video Diffusion CVPR 2025 SpeechIQ: Speech-Agentic Intelligence Quotient Across Cognitive Levels in Voice Understanding by Large Language Models ACL 2025 Generative Error Correction for Emotion-aware Speech-to-text Translation ACL 2025 Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety CVPR 2025 Embedding Robust Watermarking into Pattern to Protect the Copyright of Ceramic Artifacts AAAI 2025 Bridging Knowledge Gap Between Image Inpainting and Large-Area Visible Watermark Removal AAAI 2025 Physical Marker: Revealing Invisible Hyperlinks Hidden in Printed Trademarks AAAI 2025 UFID: A Unified Framework for Black-box Input-level Backdoor Detection on Diffusion Models AAAI 2025 Trustworthy AI Meets Educational Assessment: Challenges and Opportunities AAAI 2025 Subspace Constraint and Contribution Estimation for Heterogeneous Federated Learning CVPR 2025 Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling NAACL 2025 Semi-Supervised Multi-Modal Medical Image Segmentation for Complex Situations MICCAI 2025 CoVoGER: A Multilingual Multitask Benchmark for Speech-to-text Generative Error Correction with Large Language Models EMNLP 2025 No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users EMNLP 2025 Watermarking One for All: A Robust Watermarking Scheme Against Partial Image Theft CVPR 2025 MoFRR: Mixture of Diffusion Models for Face Retouching Restoration ICCV 2025 Large Language Models for Causal Discovery: Current Landscape and Future Directions IJCAI 2025 Derailer-Rerailer: Adaptive Verification for Efficient and Reliable Language Model Reasoning ACL 2025 Open-Set Graph Domain Adaptation via Separate Domain Alignment AAAI 2024 Task-Driven Causal Feature Distillation: Towards Trustworthy Risk Prediction AAAI 2024 LLMRG: Improving Recommendations through Large Language Model Reasoning Graphs AAAI 2024 BadSAM: Exploring Security Vulnerabilities of SAM via Backdoor Attacks (Student Abstract) AAAI 2024 Purified and Unified Steganographic Network CVPR 2024 Easy Regional Contrastive Learning of Expressive Fashion Representations NIPS 2024 Tag-grounded Visual Instruction Tuning with Retrieval Augmentation EMNLP 2024 Waxing-and-Waning: a Generic Similarity-based Framework for Efficient Self-Supervised Learning ICLR 2024 Generalizing to Unseen Domains via Text-guided Augmentation ECCV 2024 Frozen CLIP Transformer Is an Efficient Point Cloud Encoder AAAI 2024 Disentangled Style Domain for Implicit $z$-Watermark Towards Copyright Protection NIPS 2024 FLIQS: One-Shot Mixed-Precision Floating-Point and Integer Quantization Search AUTOML 2024 Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs ICML 2024 Investigating ASR Error Correction with Large Language Model and Multilingual 1-best Hypotheses INTERSPEECH 2024 TripLe: Revisiting Pretrained Model Reuse and Progressive Learning for Efficient Vision Transformer Scaling and Searching ICCV 2023 Steganography of Steganographic Networks AAAI 2023 More Knowledge, Less Bias: Unbiasing Scene Graph Generation With Explicit Ontological Adjustment WACV 2023 Towards Speech Dialogue Translation Mediating Speakers of Different Languages ACL 2023 Multi-Domain Dialogue State Tracking with Disentangled Domain-Slot Attention ACL 2023 The Kyoto Speech-to-Speech Translation System for IWSLT 2023 ACL 2023 Dialogue State Tracking with Sparse Local Slot Attention ACL 2023 pTSE: A Multi-model Ensemble Method for Probabilistic Time Series Forecasting IJCAI 2023 Graph-based Semi-supervised Local Clustering with Few Labeled Nodes IJCAI 2023 SmartFRZ: An Efficient Training Framework using Attention-Based Layer Freezing ICLR 2023 Fair Attribute Completion on Graph with Missing Attributes ICLR 2023 Better Generative Replay for Continual Federated Learning ICLR 2023 Progressive Mix-Up for Few-Shot Supervised Multi-Source Domain Transfer ICLR 2023 DRAW: Defending Camera-shooted RAW Against Image Manipulation ICCV 2023 Frame Flexible Network CVPR 2023 Fusion of Self-supervised Learned Models for MOS Prediction INTERSPEECH 2022 CrossMatch: Cross-Classifier Consistency Regularization for Open-Set Single Domain Generalization ICLR 2022 Monaural Speech Enhancement Based on Spectrogram Decomposition for Convolutional Neural Network-sensitive Feature Extraction INTERSPEECH 2022 XDC: Adversarial Adaptive Cross Domain Face Clustering (Student Abstract) AAAI 2022 Global Signal-to-noise Ratio Estimation Based on Multi-subband Processing Using Convolutional Neural Network INTERSPEECH 2022 Augmented Adversarial Self-Supervised Learning for Early-Stage Alzheimer's Speech Detection INTERSPEECH 2022 Data Augmentation Using McAdams-Coefficient-Based Speaker Anonymization for Fake Audio Detection INTERSPEECH 2022 AgriBERT: Knowledge-Infused Agricultural Language Models for Matching Food and Nutrition IJCAI 2022 Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training NIPS 2022 Leveraging Simultaneous Translation for Enhancing Transcription of Low-resource Language via Cross Attention Mechanism INTERSPEECH 2022 Finer-grained Modeling units-based Meta-Learning for Low-resource Tibetan Speech Recognition INTERSPEECH 2022 Can We Train a Language Model Inside an End-to-End ASR Model? - Investigating Effective Implicit Language Modeling COLING 2022 Patch Diffusion: A General Module for Face Manipulation Detection AAAI 2022 An End-to-End Dialect Identification System with Transfer Learning from a Multilingual Automatic Speech Recognition Model INTERSPEECH 2021 Correlative Channel-Aware Fusion for Multi-View Time Series Classification AAAI 2021 Exploiting Auxiliary Data for Offensive Language Detection with Bidirectional Transformers ACL 2021 Searching for Fast Model Families on Datacenter Accelerators CVPR 2021 Exploiting Auxiliary Data for Offensive Language Detection with Bidirectional Transformers IJCNLP 2021 End-to-End Speech Separation Using Orthogonal Representation in Complex and Real Time-Frequency Domain INTERSPEECH 2021 Edge: Enriching Knowledge Graph Embeddings with External Text NAACL 2021 Singing Voice Extraction with Attention-Based Spectrograms Fusion INTERSPEECH 2020 Global Co-occurrence Feature Learning and Active Coordinate System Conversion for Skeleton-based Action Recognition WACV 2020 A Survey on Representation Learning for User Modeling IJCAI 2020 Staged Knowledge Distillation for End-to-End Dysarthric Speech Recognition and Speech Attribute Transcription INTERSPEECH 2020 CensNet: Convolution with Edge-Node Switching in Graph Neural Networks IJCAI 2019 Self-attentive Biaffine Dependency Parsing IJCAI 2019 Scalable Block-Diagonal Locality-Constrained Projective Dictionary Learning IJCAI 2019 End-to-End Articulatory Attribute Modeling for Low-Resource Multilingual Speech Recognition INTERSPEECH 2019 Scene Graph Generation With External Knowledge and Image Reconstruction CVPR 2019 Investigating Radical-Based End-to-End Speech Recognition Systems for Chinese Dialects and Japanese INTERSPEECH 2019 Class-Wise Centroid Distance Metric Learning for Acoustic Event Detection INTERSPEECH 2019 On the Estimation of Treatment Effect with Text Covariates IJCAI 2019 SADIH: Semantic-Aware DIscrete Hashing AAAI 2019 Improving Transformer-Based Speech Recognition Systems with Compressed Structure and Speech Attributes Augmentation INTERSPEECH 2019 Fast Spatio-Temporal Residual Network for Video Super-Resolution CVPR 2019 MMFace: A Multi-Metric Regression Network for Unconstrained Face Reconstruction CVPR 2019 Improving CTC-based Acoustic Model with Very Deep Residual Time-delay Neural Networks INTERSPEECH 2018 Temporal Attentive Pooling for Acoustic Event Detection INTERSPEECH 2018 Graph Adaptive Knowledge Transfer for Unsupervised Domain Adaptation ECCV 2018 A Review on Deep Learning Techniques Applied to Answer Selection COLING 2018 Representation Learning for Treatment Effect Estimation from Observational Data NIPS 2018 A Simple End-to-End Question Answering Model for Product Information ACL 2018 Supervised Treebank Conversion: Data and Approaches ACL 2018 Feature Representation of Short Utterances Based on Knowledge Distillation for Spoken Language Identification INTERSPEECH 2018 Matching on Balanced Nonlinear Representations for Treatment Effects Estimation NIPS 2017 From Ensemble Clustering to Multi-View Clustering IJCAI 2017 Conditional Generative Adversarial Nets Classifier for Spoken Language Identification INTERSPEECH 2017 Matching via Dimensionality Reduction for Estimation of Treatment Effects in Digital Marketing Campaigns IJCAI 2016 SoNLP-DP System for ConLL-2016 English Shallow Discourse Parsing CONLL 2016 SoNLP-DP System for ConLL-2016 Chinese Shallow Discourse Parsing CONLL 2016 Learning Robust Representations for Data Analytics IJCAI 2016 Deep Linear Coding for Fast Graph Clustering IJCAI 2015 Temporal Subspace Clustering for Human Motion Segmentation ICCV 2015 Hierarchical Recurrent Neural Network for Document Modeling EMNLP 2015 The SoNLP-DP System in the CoNLL-2015 shared Task CONLL 2015 Cross-View Projective Dictionary Learning for Person Re-Identification IJCAI 2015 Microblog Entity Linking by Leveraging Extra Posts EMNLP 2013 Low-Rank Coding with b-Matching Constraint for Semi-Supervised Classification IJCAI 2013 Fusion of Word and Letter Based Metrics for Automatic MT Evaluation IJCAI 2013 A Hierarchical Semantics-Aware Distributional Similarity Scheme IJCNLP 2013 Repairing Incorrect Translation with Examples IJCNLP 2013 A Graph-based Method for Entity Linking IJCNLP 2011 Reordering with Source Language Collocations ACL 2011 Harvesting Related Entities with a Search Engine IJCNLP 2011 Bridging Topic Modeling and Personalized Search COLING 2010 Utilizing Variability of Time and Term Content, within and across Users in Session Detection COLING 2010 HIT-CIR: An Unsupervised WSD System Based on Domain Most Frequent Sense Estimation SEMEVAL 2010 All in Strings: a Powerful String-based Automatic MT Evaluation Metric with Multiple Granularities COLING 2010 Improving Statistical Machine Translation with Monolingual Collocation ACL 2010 Reexamination on Potential for Personalization in Web Search COLING 2010 Head-modifier Relation based Non-lexical Reordering Model for Phrase-Based Translation COLING 2010 A Statistical Machine Translation Model Based on a Synthetic Synchronous Grammar IJCNLP 2009 Collocation Extraction Using Monolingual Word Alignment Method EMNLP 2009 A Statistical Machine Translation Model Based on a Synthetic Synchronous Grammar ACL 2009 Application-driven Statistical Paraphrase Generation IJCNLP 2009 Application-driven Statistical Paraphrase Generation ACL 2009 A Cascaded Syntactic and Semantic Dependency Parsing System CONLL 2008 Fast Computing Grammar-driven Convolution Tree Kernel for Semantic Role Labeling IJCNLP 2008 Grammar Comparison Study for Translational Equivalence Modeling and Statistical Machine Translation COLING 2008 Combining Multiple Resources to Improve SMT-based Paraphrasing Model ACL 2008 An Entity-Mention Model for Coreference Resolution with Inductive Logic Programming ACL 2008 Pivot Approach for Extracting Paraphrase Patterns from Bilingual Corpora ACL 2008 A Tree Sequence Alignment-based Tree-to-Tree Translation Model ACL 2008 HIT: Web based Scoring Method for English Lexical Substitution SEMEVAL 2007 A Grammar-driven Convolution Tree Kernel for Semantic Role Classification ACL 2007 Dependency Parsing Based on Dynamic Local Optimization CONLL 2006 An Equivalent Pseudoword Solution to Chinese Word Sense Disambiguation ACL 2006 A Hybrid Convolution Tree Kernel for Semantic Role Labeling COLING 2006 An Equivalent Pseudoword Solution to Chinese Word Sense Disambiguation COLING 2006 A Hybrid Convolution Tree Kernel for Semantic Role Labeling ACL 2006 Semantic Role Labeling System Using Maximum Entropy Classifier CONLL 2005 Automated Generalization of Phrasal Paraphrases from the Web IJCNLP 2005 A Hybrid Chinese Language Model based on a Combination of Ontology with Statistical Method IJCNLP 2005 An Automatic Evaluation Method for Localization Oriented Lexicalised EBMT System COLING 2002 Learning Chinese Bracketing Knowledge Based on a Bilingual Language Model COLING 2002