Yu Li

AgentSwift: Efficient LLM Agent Design via Value-Guided Hierarchical Search AAAI 2026 C³TG: Conflict-aware, Composite, and Collaborative Controlled Text Generation AAAI 2026 Calibrating and Rotating: A Unified Framework for Weight Conditioning in PEFT AAAI 2026 MultiKD: Backdoor Defense in Federated Graph Learning via Attention-Guided Multi-Teacher Distillation AAAI 2026 LinProVSR: Linguistics-Knowledge Guided Progressive Disambiguation Network for Visual Speech Recognition AAAI 2026 Investigating Data Pruning for Pretraining Biological Foundation Models at Scale AAAI 2026 DS-ProGen: A Dual-Structure Deep Language Model for Functional Protein Design AAAI 2026 REST: Stress Testing Large Reasoning Models by Asking Multiple Problems at Once ACL 2026 Don’t Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Termination ACL 2026 Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs ACL 2026 ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch ACL 2026 Beyond Semantic Features: Pixel-level Mapping for Generalized AI-Generated Image Detection AAAI 2026 RMSAGen: Integrating Multiple Sequence Alignment for Function RNA Design AAAI 2026 CuMA: Aligning LLMs with Sparse Cultural Values via Demographic-Aware Mixture of Adapters ACL 2026 Dynamic Guided and Domain Applicable Safeguards for Enhanced Security in Large Language Models NAACL 2025 CAPE: A Chinese Dataset for Appraisal-based Emotional Generation in Large Language Models NAACL 2025 How Well Do LLMs Handle Cantonese? Benchmarking Cantonese Capabilities of Large Language Models NAACL 2025 Function-to-Style Guidance of LLMs for Code Translation ICML 2025 MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusion ACL 2025 DAPE V2: Process Attention Score as Feature Map for Length Extrapolation ACL 2025 A Strategic Coordination Framework of Small LMs Matches Large LMs in Data Synthesis ACL 2025 Safety Alignment via Constrained Knowledge Unlearning ACL 2025 MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming ACL 2025 Parameter-Efficient Fine-Tuning via Circular Convolution ACL 2025 Large Language Models in Bioinformatics: A Survey ACL 2025 CipherBank: Exploring the Boundary of LLM Reasoning Capabilities through Cryptography Challenge ACL 2025 LEMMA: Learning from Errors for MatheMatical Advancement in LLMs ACL 2025 DeTAM: Defending LLMs Against Jailbreak Attacks via Targeted Attention Modification ACL 2025 Enhanced Data Synthesis for LLM through Reasoning Structures Generated by Hierarchical GFlowNet ACL 2025 Learning Cascade Ranking as One Network ICML 2025 InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery COLING 2025 Non-Stationary Predictions May Be More Informative: Exploring Pseudo-Labels with a Two-Phase Pattern of Training Dynamics ICML 2025 TEASER: Token Enhanced Spatial Modeling for Expressions Reconstruction ICLR 2025 AdaManip: Adaptive Articulated Object Manipulation Environments and Policy Learning ICLR 2025 AgentSquare: Automatic LLM Agent Search in Modular Design Space ICLR 2025 One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMs ICLR 2025 MVQA: Mamba with Unified Sampling for Efficient Video Quality Assessment ICCV 2025 CanonSwap: High-Fidelity and Consistent Video Face Swapping via Canonical Space Modulation ICCV 2025 GUAVA: Generalizable Upper Body 3D Gaussian Avatar ICCV 2025 Adaptive Articulated Object Manipulation On The Fly with Foundation Model Reasoning and Part Grounding ICCV 2025 Semantic Contribution-Aware Adaptive Retrieval for Black-Box Models EMNLP 2025 MetaLadder: Ascending Mathematical Solution Quality via Analogical-Problem Reasoning Transfer EMNLP 2025 ProReflow: Progressive Reflow with Decomposed Velocity CVPR 2025 HRAvatar: High-Quality and Relightable Gaussian Head Avatar CVPR 2025 CDT: A Comprehensive Capability Framework for Large Language Models Across Cognition, Domain, and Task EMNLP 2025 Developing and Utilizing a Large-Scale Cantonese Dataset for Multi-Tasking in Large Language Models EMNLP 2025 AIR: Complex Instruction Generation via Automatic Iterative Refinement EMNLP 2025 Rethinking Text-based Protein Understanding: Retrieval or LLM? EMNLP 2025 Self-Adjust Softmax EMNLP 2025 RBPtool: A Deep Language Model Framework for Multi-Resolution RBP-RNA Binding Prediction and RNA Molecule Design EMNLP 2025 DF-MIA: A Distribution-Free Membership Inference Attack on Fine-Tuned Large Language Models AAAI 2025 AnyTalk: Multi-modal Driven Multi-domain Talking Head Generation AAAI 2025 TAMER: Tree-Aware Transformer for Handwritten Mathematical Expression Recognition AAAI 2025 HeGTa: Leveraging Heterogeneous Graph-enhanced Large Language Models for Few-shot Complex Table Understanding AAAI 2025 A Video is Worth 256 Bases: Spatial-Temporal Expectation-Maximization Inversion for Zero-Shot Video Editing CVPR 2024 HORSE: Hierarchical Representation for Large-Scale Neural Subset Selection NIPS 2024 DAPE: Data-Adaptive Positional Encoding for Length Extrapolation NIPS 2024 SubgDiff: A Subgraph Diffusion Model to Improve Molecular Representation Learning NIPS 2024 Vector Quantization Prompting for Continual Learning NIPS 2024 MSA Generation with Seqs2Seqs Pretraining: Advancing Protein Structure Predictions NIPS 2024 Towards Stable Representations for Protein Interface Prediction NIPS 2024 CNCA: Toward Customizable and Natural Generation of Adversarial Camouflage for Vehicle Detectors NIPS 2024 Blind Face Restoration under Extreme Conditions: Leveraging 3D-2D Prior Fusion for Superior Structural and Texture Recovery AAAI 2024 Atlantis: Enabling Underwater Depth Estimation with Stable Diffusion CVPR 2024 DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation CVPR 2024 Compress3D: a Compressed Latent Space for 3D Generation from a Single Image ECCV 2024 AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting ECCV 2024 AddMe: Zero-shot Group-photo Synthesis by Inserting People into Scenes ECCV 2024 LIONs: An Empirically Optimized Approach to Align Language Models EMNLP 2024 SeRTS: Self-Rewarding Tree Search for Biomedical Retrieval-Augmented Generation EMNLP 2024 MoleculeQA: A Dataset to Evaluate Factual Accuracy in Molecular Comprehension EMNLP 2024 From Pixels to Personas: Investigating and Modeling Self-Anthropomorphism in Human-Robot Dialogues EMNLP 2024 PRESTO: Progressive Pretraining Enhances Synthetic Chemistry Outcomes EMNLP 2024 Protein Multimer Structure Prediction via Prompt Learning ICLR 2024 Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts ICLR 2024 GPAvatar: Generalizable and Precise Head Avatar from Image(s) ICLR 2024 Multi-Track Message Passing: Tackling Oversmoothing and Oversquashing in Graph Learning via Preventing Heterophily Mixing ICML 2024 Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models ICML 2024 RAUCA: A Novel Physical Adversarial Attack on Vehicle Detectors via Robust and Accurate Camouflage Generation ICML 2024 Protecting Object Detection Models from Model Extraction Attack via Feature Space Coverage IJCAI 2024 Exploring the Impact of Table-to-Text Methods on Augmenting LLM-based Question Answering with Domain Hybrid Data NAACL 2024 Microkernel Goes General: Performance and Compatibility in the HongMeng Production Microkernel OSDI 2024 Signed Laplacian Graph Neural Networks AAAI 2023 Large-Scale and Multi-Perspective Opinion Summarization with Diverse Review Subsets EMNLP 2023 DIONYSUS: A Pre-trained Model for Low-Resource Dialogue Summarization ACL 2023 HiBug: On Human-Interpretable Model Debug NIPS 2023 L-CAD: Language-based Colorization with Any-level Descriptions using Diffusion Priors NIPS 2023 A Multi-modal Debiasing Model with Dynamical Constraint for Robust Visual Question Answering ACL 2023 MODA: Mapping-Once Audio-driven Portrait Animation with Dual Attentions ICCV 2023 Make Encoder Great Again in 3D GAN Inversion through Geometry and Occlusion-Aware Encoding ICCV 2023 Learning Rain Location Prior for Nighttime Deraining ICCV 2023 From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels ICCV 2023 Accurate 3D Face Reconstruction with Facial Component Tokens ICCV 2023 One-Stage 3D Whole-Body Mesh Recovery With Component Aware Transformer CVPR 2023 Learning Single Image Defocus Deblurring with Misaligned Training Pairs AAAI 2023 L-CoIns: Language-Based Colorization With Instance Awareness CVPR 2023 CT2: Colorization Transformer via Color Tokens ECCV 2022 GHAN: Graph-Based Hierarchical Aggregation Network for Text-Video Retrieval EMNLP 2022 Robots-Dont-Cry: Understanding Falsely Anthropomorphic Utterances in Dialog Systems EMNLP 2022 Hot-Refresh Model Upgrades with Regression-Free Compatible Training in Image Retrieval ICLR 2022 Orthogonal Graph Neural Networks AAAI 2022 Improving Conversational Recommendation Systems’ Quality with Context-Aware Item Meta-Information NAACL 2022 Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representation NAACL 2022 Temporally Efficient Vision Transformer for Video Instance Segmentation CVPR 2022 “Think Before You Speak”: Improving Multi-Action Dialog Policy by Planning Single-Action Dialogs IJCAI 2022 Active Learning for Open-Set Annotation CVPR 2022 Contact-Distil: Boosting Low Homologous Protein Contact Map Prediction by Self-Supervised Distillation AAAI 2022 L-CoDer: Language-Based Colorization with Color-Object Decoupling Transformer ECCV 2022 SMINet: State-Aware Multi-Aspect Interests Representation Network for Cold-Start Users Recommendation AAAI 2022 LEGOEval: An Open-Source Toolkit for Dialogue System Evaluation via Crowdsourcing ACL 2021 CLiMP: A Benchmark for Chinese Language Model Evaluation EACL 2021 Alternating Recurrent Dialog Model with Large-scale Pre-trained Language Models EACL 2021 Instances As Queries ICCV 2021 Crossover Learning for Fast Online Video Instance Segmentation ICCV 2021 Towards Vivid and Diverse Image Colorization With Generative Color Prior ICCV 2021 Learning Temporal Consistency for Low Light Video Enhancement From Single Images CVPR 2021 Beyond Categorical Label Representations for Image Classification ICLR 2021 Exploring Balanced Feature Spaces for Representation Learning ICLR 2021 RevMan: Revenue-aware Multi-task Online Insurance Recommendation AAAI 2021 Towards Real-World Blind Face Restoration With Generative Facial Prior CVPR 2021 Information Bottleneck Approach to Spatial Attention Learning IJCAI 2021 Towards Emotional Support Dialog Systems IJCNLP 2021 The R-U-A-Robot Dataset: Helping Avoid Chatbot Deception by Detecting User Questions About Human or Non-Human Identity IJCNLP 2021 LEGOEval: An Open-Source Toolkit for Dialogue System Evaluation via Crowdsourcing IJCNLP 2021 The R-U-A-Robot Dataset: Helping Avoid Chatbot Deception by Detecting User Questions About Human or Non-Human Identity ACL 2021 TestRank: Bringing Order into Unlabeled Test Instances for Deep Learning Tasks NIPS 2021 FLiText: A Faster and Lighter Semi-Supervised Text Classification with Convolution Networks EMNLP 2021 Refine and Imitate: Reducing Repetition and Inconsistency in Persuasion Dialogues via Reinforcement Learning and Human Demonstration EMNLP 2021 Towards Emotional Support Dialog Systems ACL 2021 Learning Signed Network Embedding via Graph Attention AAAI 2020 Learning To Stop While Learning To Predict ICML 2020 Fast Video Object Segmentation using the Global Context Module ECCV 2020 A Multi-Persona Chatbot for Hotline Counselor Training EMNLP 2020 Unsupervised Learning for Intrinsic Image Decomposition From a Single Image CVPR 2020 Overcoming Classifier Imbalance for Long-Tail Object Detection With Balanced Group Softmax CVPR 2020 Interactive Key-Value Memory-augmented Attention for Image Paragraph Captioning COLING 2020 The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation ECCV 2020 End-to-End Trainable Non-Collaborative Dialog System AAAI 2020 RNA Secondary Structure Prediction By Learning Unrolled Algorithms ICLR 2020 Learning Network Embedding with Community Structural Information IJCAI 2019 Approximate Kernel Selection with Strong Approximate Consistency AAAI 2019 Linear Kernel Tests via Empirical Likelihood for High-Dimensional Data AAAI 2019 Two Generator Game: Learning to Sample via Linear Goodness-of-Fit Test NIPS 2019 Rain Streak Removal Using Layer Priors CVPR 2016 SPM-BP: Sped-up PatchMatch Belief Propagation for Continuous MRFs ICCV 2015 Nighttime Haze Removal With Glow and Multiple Light Colors ICCV 2015 Single Image Layer Separation using Relative Smoothness CVPR 2014 Exploiting Reflection Change for Automatic Reflection Removal ICCV 2013