Zihan Wang

ConfGuard: A Simple and Effective Backdoor Detection for Large Language Models AAAI 2026 MPMA: Preference Manipulation Attack Against Model Context Protocol AAAI 2026 MessToClean: Evidence-Grounded Structure-Preserving Reconstruction for Real-World Degraded Exam Paper Images ACL 2026 MTRouter: Cost-Aware Multi-Turn LLM Routing with History–Model Joint Embeddings ACL 2026 VPN: Visual Prompt Navigation AAAI 2026 CloserToMe: A Unified Framework for Accurate and Transferable Latency Prediction Across Heterogeneous Devices AAAI 2026 GitChameleon 2.0: Evaluating AI Code Generation Against Python Library Version Incompatibilities ACL 2026 CIRAG: Construction–Integration Retrieval and Adaptive Generation for Multi-hop Question Answering ACL 2026 MTAttack: Multi-Target Backdoor Attacks Against Large Vision-Language Models AAAI 2026 STELAR-VISION: Self-Topology-Aware Efficient Learning for Aligned Reasoning in Vision AAAI 2026 Is He Extroverted? Identifying Missing Relevant Personas for Faithful User Simulation EACL 2026 KeepKV: Achieving Periodic Lossless KV Cache Compression for Efficient LLM Inference AAAI 2026 ReportLogic: Evaluating Logical Quality in Deep Research Reports ACL 2026 MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion ICCV 2025 Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse ICLR 2025 MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization ICLR 2025 Reducing Tool Hallucination via Reliability Alignment ICML 2025 Commentary Generation from Multimodal Game Data for Esports Moments in Multiplayer Strategy Games IJCNLP 2025 FMM-Diff: A Feature Mapping and Merging Diffusion Model for MRI Generation with Missing Modality MICCAI 2025 Direct Prompt Optimization with Continuous Representations ACL 2025 InstructPart: Task-Oriented Part Segmentation with Instruction Reasoning ACL 2025 MUSE: A Multimodal Conversational Recommendation Dataset with Scenario-Grounded User Profiles ACL 2025 NavRAG: Generating User Demand Instructions for Embodied Navigation through Retrieval-Augmented LLM ACL 2025 LLMSR@XLLM25: A Language Model-Based Pipeline for Structured Reasoning Data Construction ACL 2025 Elastic Representation: Mitigating Spurious Correlations for Group Robustness AISTATS 2025 Data Reconstruction Attacks and Defenses: A Systematic Evaluation AISTATS 2025 g3D-LF: Generalizable 3D-Language Feature Fields for Embodied Tasks CVPR 2025 Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis CVPR 2025 Re-thinking Temporal Search for Long-Form Video Understanding CVPR 2025 Commentary Generation from Multimodal Game Data for Esports Moments in Multiplayer Strategy Games AACL 2025 InfoGain-RAG: Boosting Retrieval-Augmented Generation through Document Information Gain-based Reranking and Filtering EMNLP 2025 Alignment for Efficient Tool Calling of Large Language Models EMNLP 2025 CodeContests+: High-Quality Test Case Generation for Competitive Programming EMNLP 2025 Auxiliary Prompt Tuning of Vision-Language Models for Few-Shot Out-of-Distribution Detection ICCV 2025 Utilizing Local Hierarchy with Adversarial Training for Hierarchical Text Classification COLING 2024 Learn from Failure: Fine-tuning LLMs with Trial-and-Error Data for Intuitionistic Propositional Logic Proving ACL 2024 I Can Tell What I am Doing: Toward Real-World Natural Language Grounding of Robot Experiences CORL 2024 Commentary Generation from Data Records of Multiplayer Strategy Esports Game NAACL 2024 BPKD: Boundary Privileged Knowledge Distillation for Semantic Segmentation WACV 2024 Learning Fair Representations for Recommendation via Information Bottleneck Principle IJCAI 2024 TeleChat: An Open-source Billingual Large Language Model ACL 2024 MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback ICLR 2024 Implicit bias of SGD in $L_2$-regularized linear DNNs: One-way jumps from high to low rank ICLR 2024 Evoke: Evoking Critical Thinking Abilities in LLMs via Reviewer-Author Prompt Editing ICLR 2024 SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models NIPS 2024 Answer is All You Need: Instruction-following Text Embedding via Answering the Question ACL 2024 Evaluating the Smooth Control of Attribute Intensity in Text Generation with LLMs ACL 2024 Let the Expert Stick to His Last: Expert-Specialized Fine-Tuning for Sparse Architectural Large Language Models EMNLP 2024 Text Grafting: Near-Distribution Weak Supervision for Minority Classes in Text Classification EMNLP 2024 Sim-to-Real Transfer via 3D Feature Fields for Vision-and-Language Navigation CORL 2024 SciCode: A Research Coding Benchmark Curated by Scientists NIPS 2024 Multi-scale Dynamic and Hierarchical Relationship Modeling for Facial Action Units Recognition CVPR 2024 Lookahead Exploration with Neural Radiance Representation for Continuous Vision-Language Navigation CVPR 2024 CogAgent: A Visual Language Model for GUI Agents CVPR 2024 Self-Renewal Prompt Optimizing with Implicit Reasoning EMNLP 2024 Multi-step Problem Solving Through a Verifier: An Empirical Analysis on Model-induced Process Supervision EMNLP 2024 ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline EMNLP 2024 Less than One-shot: Named Entity Recognition via Extremely Weak Supervision EMNLP 2023 Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback NIPS 2023 Autonomous Robotic Reinforcement Learning with Asynchronous Human Feedback CORL 2023 Learning to Imagine: Distillation-Based Interactive Context Exploitation for Dialogue State Tracking AAAI 2023 A Benchmark on Extremely Weakly Supervised Text Classification: Reconcile Seed Matching and Prompting Approaches ACL 2023 Reconstructing Training Data from Model Gradient, Provably AISTATS 2023 KERM: Knowledge Enhanced Reasoning for Vision-and-Language Navigation CVPR 2023 PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection CVPR 2023 Debiasing Made State-of-the-art: Revisiting the Simple Seed-based Weak Supervision for Text Classification EMNLP 2023 Goal-Driven Explainable Clustering via Language Descriptions EMNLP 2023 ClusterLLM: Large Language Models as a Guide for Text Clustering EMNLP 2023 Multi-Defendant Legal Judgment Prediction via Hierarchical Reasoning EMNLP 2023 Generalizing Few-Shot Named Entity Recognizers to Unseen Domains with Type-Related Features EMNLP 2023 ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation EMNLP 2023 GridMM: Grid Memory Map for Vision-and-Language Navigation ICCV 2023 GLM-130B: An Open Bilingual Pre-trained Model ICLR 2023 Guiding Pretraining in Reinforcement Learning with Large Language Models ICML 2023 A System for Generating Voice Source Signals that Implements the Transformed LF-model Parameter Control INTERSPEECH 2023 Contribution of the glottal flow residual in affect-related voice transformation INTERSPEECH 2022 Rethinking the Setting of Semi-supervised Learning on Graphs IJCAI 2022 M$^4$I: Multi-modal Models Membership Inference NIPS 2022 Formulating Few-shot Fine-tuning Towards Language Model Pre-training: A Pilot Study on Named Entity Recognition EMNLP 2022 WeDef: Weakly Supervised Backdoor Defense for Text Classification EMNLP 2022 HPT: Hierarchy-aware Prompt Tuning for Hierarchical Text Classification EMNLP 2022 Learning Adaptive Axis Attentions in Fine-tuning: Beyond Fixed Sparse Attention Patterns ACL 2022 Incorporating Hierarchy into Text Encoder: a Contrastive Learning Approach for Hierarchical Text Classification ACL 2022 Beyond the Granularity: Multi-Perspective Dialogue Collaborative Selection for Dialogue State Tracking ACL 2022 Dual Slot Selector via Local Reliability Verification for Dialogue State Tracking ACL 2021 X-Class: Text Classification with Extremely Weak Supervision NAACL 2021 Dual Slot Selector via Local Reliability Verification for Dialogue State Tracking IJCNLP 2021 “Average” Approximates “First Principal Component”? An Empirical Analysis on Representations from Neural Language Models EMNLP 2021 Extending Multilingual BERT to Low-Resource Languages EMNLP 2020 Cross-Lingual Ability of Multilingual BERT: An Empirical Study ICLR 2020 CrossWeigh: Training Named Entity Tagger from Imperfect Annotations EMNLP 2019 CrossWeigh: Training Named Entity Tagger from Imperfect Annotations IJCNLP 2019 Robust Embedding with Multi-Level Structures for Link Prediction IJCAI 2019