Kun Wang

CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems ACL 2026 Backdoor Collapse: Eliminating Unknown Threats Via Known Backdoor Aggregation In Language Models ACL 2026 JARVIS or Ultron? A Survey on the Safety and Security Threats of Computer-Using Agents ACL 2026 SafeSieve: From Heuristics to Experience in Progressive Pruning for LLM-based Multi-Agent Communication AAAI 2026 Hidden in the Noise: Unveiling Backdoors in Audio LLMs Alignment Through Latent Acoustic Pattern Triggers AAAI 2026 NeuralOM: Neural Ocean Model for Subseasonal-to-Seasonal Simulation AAAI 2026 Drift-aware Collaborative Assistance Mixture of Experts for Heterogeneous Multistream Learning AAAI 2026 Calibrating Inference Time Alignment with Sequence-level Risk Accumulation ACL 2026 Scaling Law for Multimodal Large Language Model Supervised Fine-Tuning ACL 2026 DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent EMNLP 2025 OneForecast: A Universal Framework for Global and Regional Weather Forecasting ICML 2025 KGMark: A Diffusion Watermark for Knowledge Graphs ICML 2025 Depth-Centric Dehazing and Depth-Estimation from Real-World Hazy Driving Video AAAI 2025 UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction AAAI 2025 G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systems ACL 2025 ARise: Towards Knowledge-Augmented Reasoning via Risk-Adaptive Search ACL 2025 MasRouter: Learning to Route LLMs for Multi-Agent Systems ACL 2025 NetSafe: Exploring the Topological Safety of Multi-agent System ACL 2025 FiDeLiS: Faithful Reasoning in Large Language Models for Knowledge Graph Question Answering ACL 2025 A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges ACL 2025 iAgent: LLM Agent as a Shield between User and Recommender Systems ACL 2025 A Complete Characterization of Learnability for Stochastic Noisy Bandits ALT 2025 Multi-expert collaboration and knowledge enhancement network for multimodal emotion recognition MICCAI 2025 Deploying Multi-task Online Server with Large Language Model COLING 2025 Completion as Enhancement: A Degradation-Aware Selective Image Guided Network for Depth Completion CVPR 2025 Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis EMNLP 2025 DynamicNER: A Dynamic, Multilingual, and Fine-Grained Dataset for LLM-based Named Entity Recognition EMNLP 2025 Position: LLMs Can be Good Tutors in English Education EMNLP 2025 MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans? ICLR 2025 Knowledge Graph-Driven Memory Editing with Directional Interventions EMNLP 2025 G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks ICML 2025 Multi-agent Architecture Search via Agentic Supernet ICML 2025 Discovering Latent Causal Graphs from Spatiotemporal Data ICML 2025 PUMA: Empowering Unified MLLM with Multi-granular Visual Generation ICCV 2025 ViLLa: Video Reasoning Segmentation with Large Language Model ICCV 2025 Graph Sparsification via Mixture of Graphs ICLR 2025 AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models ICLR 2025 On the Role of Attention Heads in Large Language Model Safety ICLR 2025 Open-CK: A Large Multi-Physics Fields Coupling benchmarks in Combustion Kinetics ICLR 2025 Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality ICLR 2025 Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems ICLR 2025 Driving-Video Dehazing with Non-Aligned Regularization for Safety Assistance CVPR 2024 Learning Differentiable Tensegrity Dynamics using Graph Neural Networks CORL 2024 Gradient-based Visual Explanation for Transformer-based CLIP ICML 2024 Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness ICML 2024 Prometheus: Out-of-distribution Fluid Dynamics Modeling with Disentangled Graph ODE ICML 2024 Graph Lottery Ticket Automated ICLR 2024 Tri-Perspective View Decomposition for Geometry-Aware Depth Completion CVPR 2024 Kill Two Birds with One Stone: Rethinking Data Augmentation for Deep Long-tailed Learning ICLR 2024 AltNeRF: Learning Robust Neural Radiance Field via Alternating Depth-Pose Optimization AAAI 2024 Earthfarsser: Versatile Spatio-Temporal Dynamical Systems Modeling in One Model AAAI 2024 M2Fusion: Multi-time Multimodal Fusion for Prediction of Pathological Complete Response in Breast Cancer MICCAI 2024 Predicting Carpark Availability in Singapore with Cross-Domain Data: A New Dataset and A Data-Driven Approach IJCAI 2024 Towards Neuron Attributions in Multi-Modal Large Language Models NIPS 2024 Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model NIPS 2024 MolTC: Towards Molecular Relational Modeling In Language Models ACL 2024 MotionTTT: 2D Test-Time-Training Motion Estimation for 3D Motion Corrected MRI NIPS 2024 SyncVIS: Synchronized Video Instance Segmentation NIPS 2024 GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning NIPS 2024 Multi-scale Cross Distillation for Object Detection in Aerial Images ECCV 2024 Towards Robust Trajectory Representations: Isolating Environmental Confounders with Causal Learning IJCAI 2024 DCDepth: Progressive Monocular Depth Estimation in Discrete Cosine Domain NIPS 2024 CLEAR: Can Language Models Really Understand Causal Graphs? EMNLP 2024 Dueling over Dessert, Mastering the Art of Repeated Cake Cutting NIPS 2024 NuwaDynamics: Discovering and Updating in Causal Spatio-Temporal Modeling ICLR 2024 DesNet: Decomposed Scale-Consistent Network for Unsupervised Depth Completion AAAI 2023 Siamese DETR CVPR 2023 Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatment NIPS 2023 TMT-VIS: Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation NIPS 2023 Searching Lottery Tickets in Graph Neural Networks: A Dual Perspective ICLR 2023 Distortion and Uncertainty Aware Loss for Panoramic Depth Completion ICML 2023 ERGO: Event Relational Graph Transformer for Document-level Event Causality Identification COLING 2022 Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction ACL 2022 MMEKG: Multi-modal Event Knowledge Graph towards Universal Representation across Modalities ACL 2022 Multi-modal Masked Pre-training for Monocular Panoramic Depth Completion ECCV 2022 X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation ECCV 2022 RigNet: Repetitive Image Guided Network for Depth Completion ECCV 2022 R2F: A General Retrieval, Reading and Fusion Framework for Document-level Natural Language Inference EMNLP 2022 A Comparison between Pre-training and Large-scale Back-translation for Neural Machine Translation IJCNLP 2021 Regularizing Nighttime Weirdness: Efficient Self-Supervised Monocular Depth Estimation in the Dark ICCV 2021 Oral-3D: Reconstructing the 3D Structure of Oral Cavity from Panoramic X-ray AAAI 2021 Exploring Forensic Dental Identification with Deep Learning NIPS 2021 A Comparison between Pre-training and Large-scale Back-translation for Neural Machine Translation ACL 2021 Alignment-Enhanced Transformer for Constraining NMT with Pre-Specified Translations AAAI 2020 What Have We Achieved on Text Summarization? EMNLP 2020 Adapting Object Detectors with Conditional Domain Normalization ECCV 2020 A First Principles Approach for Data-Efficient System Identification of Spring-Rod Systems via Differentiable Physics Engines L4DC 2020 LST-Net: Learning a Convolutional Neural Network with a Learnable Sparse Transform ECCV 2020 Atlas-aware ConvNet for Accurate yet Robust Anatomical Segmentation ACML 2020 Code-Switching for Enhancing NMT with Pre-Specified Translation NAACL 2019 Chained Cascade Network for Object Detection ICCV 2017 Scene Graph Generation From Objects, Phrases and Region Captions ICCV 2017 Knowledge Sharing via Social Login: Exploiting Microblogging Service for Warming up Social Question Answering Websites COLING 2014 Dynamically Integrating Cross-Domain Translation Memory into Phrase-Based Machine Translation during Decoding COLING 2014 Integrating Translation Memory into Phrase-Based Machine Translation during Decoding ACL 2013 Integrating Surface and Abstract Features for Robust Cross-Domain Chinese Word Segmentation COLING 2012 A Character-Based Joint Model for Chinese Word Segmentation COLING 2010