Yi Liu

LLM-VA: Resolving the Jailbreak-Overrefusal Trade-off via Vector Alignment ACL 2026 STEAMROLLER: A Multi-Agent System for Inclusive Automatic Speech Recognition for People Who Stutter AAAI 2026 Synergizing Multigrid Algorithms with Vision Transformer: A Novel Approach to Enhance the Seismic Foundation Model AAAI 2026 DynamicRTL: RTL Representation Learning for Dynamic Circuit Behavior AAAI 2026 ProtSAE: Disentangling and Interpreting Protein Language Models via Semantically-Guided Sparse Autoencoders AAAI 2026 AIM: Manifold-based Data Filtering for Representation Finetuning AAAI 2026 Answering the Unanswerable Is to Err Knowingly: Analyzing and Mitigating Abstention Failures in Large Reasoning Models AAAI 2026 Sortblock: Similarity-Aware Feature Reuse for Diffusion Model AAAI 2026 Libra-VLA: Achieving Learning Equilibrium via Asynchronous Coarse-to-Fine Dual-System ACL 2026 Finding Time Series Anomalies Using Granular-Ball Vector Data Description AAAI 2026 In-Token Rationality Optimization: Towards Accurate and Concise LLM Reasoning via Self-Feedback AAAI 2026 FineRef: Fine-Grained Error Reflection and Correction for Long-Form Generation with Citations AAAI 2026 Who Should I Trust? Explicit Confidence-Focused Multimodal Intent Recognition AAAI 2026 CoST: Efficient Collaborative Perception From Unified Spatiotemporal Perspective ICCV 2025 CycleVAR: Repurposing Autoregressive Model for Unsupervised One-Step Image Translation ICCV 2025 Avoiding Knowledge Edit Skipping in Multi-hop Question Answering with Guided Decomposition EMNLP 2025 Libra-Leaderboard: Towards Responsible AI through a Balanced Leaderboard of Safety and Capability NAACL 2025 Mitigating Biases in Language Models via Bias Unlearning EMNLP 2025 TombRaider: Entering the Vault of History to Jailbreak Large Language Models EMNLP 2025 VENUS: A VLLM-driven Video Content Discovery System for Real Application Scenarios EMNLP 2025 Knowledge Graph-Guided Retrieval Augmented Generation NAACL 2025 Anatomy-Guided Multimodal Graph Networks for Alzheimer’s Disease: Integrative Analysis of Cross-Modal Brain Connectivity Signatures MICCAI 2025 D3: Diversity, Difficulty, and Dependability-Aware Data Selection for Sample-Efficient LLM Instruction Tuning IJCAI 2025 PunchBench: Benchmarking MLLMs in Multimodal Punchline Comprehension ACL 2025 ATLANTIS: Weak-to-Strong Learning via Importance Sampling ACL 2025 Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models ACL 2025 DeepRTL2: A Versatile Model for RTL-Related Tasks ACL 2025 Fine-grained Knowledge Enhancement for Retrieval-Augmented Generation ACL 2025 RL-Guider: Leveraging Historical Decisions and Feedback for Drug Editing with Large Language Models ACL 2025 Template3D-AD: Point Cloud Template Matching Method Based on Center Points for 3D Anomaly Detection IJCAI 2025 SAP: Privacy-Preserving Fine-Tuning on Language Models with Split-and-Privatize Framework IJCAI 2025 Perturbation-driven Dual Auxiliary Contrastive Learning for Collaborative Filtering Recommendation COLING 2025 Controllable Protein Sequence Generation with LLM Preference Optimization AAAI 2025 Modeling Interactions Between Stocks Using LLM-Enhanced Graphs for Volume Prediction COLING 2025 Proxy Tuning for Financial Sentiment Analysis: Overcoming Data Scarcity and Computational Barriers COLING 2025 RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph Explanation ICML 2025 On-the-fly Preference Alignment via Principle-Guided Decoding ICLR 2025 DeepRTL: Bridging Verilog Understanding and Generation with a Unified Representation Model ICLR 2025 Discretization-invariance? On the Discretization Mismatch Errors in Neural Operators ICLR 2025 SUTrack: Towards Simple and Unified Single Object Tracking AAAI 2025 Exploring Enhanced Contextual Information for Video-Level Object Tracking AAAI 2025 VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis AAAI 2025 CALM: Curiosity-Driven Auditing for Large Language Models AAAI 2025 Erase Diffusion: Empowering Object Removal Through Calibrating Diffusion Pathways CVPR 2025 Effective Cloud Removal for Remote Sensing Images by an Improved Mean-Reverting Denoising Model with Elucidated Design Space CVPR 2025 LIRE: listwise reward enhancement for preference alignment ACL 2024 Empowering Active Learning for 3D Molecular Graphs with Geometric Graph Isomorphism NIPS 2024 Gradual Residuals Alignment: A Dual-Stream Framework for GAN Inversion and Image Attribute Editing AAAI 2024 Towards Efficient and Effective Text-to-Video Retrieval with Coarse-to-Fine Visual Representation Learning AAAI 2024 Benchmarking Large Language Models on Controllable Generation under Diversified Instructions AAAI 2024 Analysis of Differentially Private Synthetic Data: A Measurement Error Approach AAAI 2024 Multi-Aspect Controllable Text Generation with Disentangled Counterfactual Augmentation ACL 2024 Chain-of-Question: A Progressive Question Decomposition Approach for Complex Knowledge Base Question Answering ACL 2024 Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues ACL 2024 A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models ACL 2024 Knowledge Context Modeling with Pre-trained Language Models for Contrastive Knowledge Graph Completion ACL 2024 TempCompass: Do Video LLMs Really Understand Videos? ACL 2024 Enhancing Emotion Prediction in News Headlines: Insights from ChatGPT and Seq2Seq Models for Free-Text Generation COLING 2024 Visual-Linguistic Dependency Encoding for Image-Text Retrieval COLING 2024 Modal-adaptive Knowledge-enhanced Graph-based Financial Prediction from Monetary Policy Conference Calls with LLM COLING 2024 MVBench: A Comprehensive Multi-modal Video Understanding Benchmark CVPR 2024 Tactile-Augmented Radiance Fields CVPR 2024 DETRs Beat YOLOs on Real-time Object Detection CVPR 2024 CAMixerSR: Only Details Need More "Attention" CVPR 2024 VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models ECCV 2024 Alignment-Enhanced Decoding: Defending Jailbreaks via Token-Level Adaptive Refining of Probability Distributions EMNLP 2024 FlipGuard: Defending Preference Alignment against Update Regression with Constrained Optimization EMNLP 2024 Task Oriented In-Domain Data Augmentation EMNLP 2024 Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs EMNLP 2024 Repairing Catastrophic-Neglect in Text-to-Image Diffusion Models via Attention-Guided Feature Enhancement EMNLP 2024 Neural Field Classifiers via Target Encoding and Classification Loss ICLR 2024 Tuning-free Estimation and Inference of Cumulative Distribution Function under Local Differential Privacy ICML 2024 Multi-Source Conformal Inference Under Distribution Shift ICML 2024 A Small and Fast BERT for Chinese Medical Punctuation Restoration INTERSPEECH 2024 TISE: A Tripartite In-context Selection Method for Event Argument Extraction NAACL 2024 Semi-Offline Reinforcement Learning for Optimized Text Generation ICML 2023 Lightweight Image Super-Resolution with Superpixel Token Interaction ICCV 2023 Random Entity Quantization for Parameter-Efficient Compositional Knowledge Graph Representation EMNLP 2023 Efficient Approximations of Complete Interatomic Potentials for Crystal Property Prediction ICML 2023 Gaussian Differential Privacy on Riemannian Manifolds NIPS 2023 Learning Hierarchical Protein Representations via Complete 3D Graph Networks ICLR 2023 Online Local Differential Private Quantile Inference via Self-normalization ICML 2023 Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection CVPR 2023 Towards Better Entity Linking with Multi-View Enhanced Distillation ACL 2023 Communication Efficient Federated Learning for Multilingual Neural Machine Translation with Adapter ACL 2023 Multimodal Sarcasm Target Identification in Tweets ACL 2022 ComENet: Towards Complete and Efficient Message Passing for 3D Molecular Graphs NIPS 2022 Hierarchical Channel-spatial Encoding for Communication-efficient Collaborative Learning NIPS 2022 Token-level Speaker Change Detection Using Speaker Difference and Speech Content via Continuous Integrate-and-fire INTERSPEECH 2022 Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation NIPS 2022 Spherical Message Passing for 3D Molecular Graphs ICLR 2022 DeepGen: Diverse Search Ad Generation and Real-Time Customization EMNLP 2022 Periodic Graph Transformers for Crystal Material Property Prediction NIPS 2022 Identification, Amplification and Measurement: A bridge to Gaussian Differential Privacy NIPS 2022 CLIO: Role-interactive Multi-event Head Attention Network for Document-level Event Extraction COLING 2022 How Does Knowledge Graph Embedding Extrapolate to Unseen Data: A Semantic Evidence View AAAI 2022 Mask-Embedded Discriminator With Region-Based Semantic Regularization for Semi-Supervised Class-Conditional Image Synthesis CVPR 2021 BioCopy: A Plug-And-Play Span Copy Mechanism in Seq2Seq Models EMNLP 2021 Damped Anderson Mixing for Deep Reinforcement Learning: Acceleration, Convergence, and Stabilization NIPS 2021 DIG: A Turnkey Library for Diving into Graph Deep Learning Research JMLR 2021 Semi-Supervised Single-Stage Controllable GANs for Conditional Fine-Grained Image Generation ICCV 2021 The Effect of Language Dominance on the Selective Attention of Segments and Tones in Urdu-Cantonese Speakers INTERSPEECH 2020 Regularizing Discriminative Capability of CGANs for Semi-Supervised Generative Learning CVPR 2020 THUEE System for NIST SRE19 CTS Challenge INTERSPEECH 2020 Internal and Contextual Attention Network for Cold-start Multi-channel Matching in Recommendation IJCAI 2020 A Human-Like Semantic Cognition Network for Aspect-Level Sentiment Classification AAAI 2019 Large Margin Softmax Loss for Speaker Verification INTERSPEECH 2019 Employing Deep Part-Object Relationships for Salient Object Detection ICCV 2019 Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network ACL 2018 Multi-glance Reading Model for Text Understanding ACL 2018 Speaker Embedding Extraction with Phonetic Information INTERSPEECH 2018 A Multi-sentiment-resource Enhanced Attention Network for Sentiment Classification ACL 2018 Teaching Compositionality to CNNs CVPR 2017 Investigating Various Diarization Algorithms for Speaker in the Wild (SITW) Speaker Recognition Challenge INTERSPEECH 2016 THU-EE System Description for NIST LRE 2015 INTERSPEECH 2016 Clustering Sentences with Density Peaks for Multi-document Summarization NAACL 2015 Translating Queries into Snippets for Improved Query Expansion COLING 2008 Automated Vocabulary Acquisition and Interpretation in Multimodal Conversational Systems ACL 2007 Statistical Machine Translation for Query Expansion in Answer Retrieval ACL 2007