Yiming Li

Learning Better UAV-Based Cross-View Object Geo-Localization from Multi-Modal Prompts: MoP-UAV Benchmark and MoPT Framework AAAI 2026 Listening Between the Frames: Bridging Temporal Gaps in Large Audio-Language Models AAAI 2026 DQA: Diagnostic Question Answering for IT Support ACL 2026 Probing Semantic Insensitivity for Inference-Time Backdoor Defense in Multimodal Large Language Model AAAI 2026 KVTuner: Sensitivity-Aware Layer-Wise Mixed-Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference ICML 2025 Tree-of-Quote Prompting Improves Factuality and Attribution in Multi-Hop and Medical Reasoning EMNLP 2025 Graph Prompts: Adapting Video Graph for Video Question Answering IJCAI 2025 Recovering Parametric Scenes from Very Few Time-of-Flight Pixels ICCV 2025 When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations ACL 2025 Unraveling the Effects of Synthetic Data on End-to-End Autonomous Driving ICCV 2025 Adversarial Exploitation of Data Diversity Improves Visual Localization ICCV 2025 Understanding the Dark Side of LLMs’ Intrinsic Self-Correction ACL 2025 Leveraging Large Language Models for Conversational Multi-Doc Question Answering: The First Place of WSDM Cup 2024 ACL 2025 Exposing Numeracy Gaps: A Benchmark to Evaluate Fundamental Numerical Abilities in Large Language Models ACL 2025 Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models ICLR 2025 Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems ICML 2025 Coronary Artery Calcification segmentation by using cross-frequency conditioner and geometric priors Learning MICCAI 2025 VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking ICLR 2025 Extrapolated Urban View Synthesis Benchmark ICCV 2025 REFINE: Inversion-Free Backdoor Defense via Model Reprogramming ICLR 2025 SleeperMark: Towards Robust Watermark against Fine-Tuning Text-to-image Diffusion Models CVPR 2025 A Benchmark for Semantic Sensitive Information in LLMs Outputs ICLR 2025 LLM-Driven Knowledge Injection Advances Zero-Shot and Cross-Target Stance Detection NAACL 2024 Purifying Quantization-conditioned Backdoors via Layer-wise Activation Correction with Distribution Approximation ICML 2024 Defending Against Backdoor Attacks by Layer-wise Feature Analysis (Extended Abstract) IJCAI 2024 IarCAC: Instance-aware Representation for Coronary Artery Calcification Segmentation in Cardiac CT angiography MICCAI 2024 Multi-Region Text-Driven Manipulation of Diffusion Imagery AAAI 2024 BadActs: A Universal Backdoor Defense in the Activation Space ACL 2024 RadarOcc: Robust 3D Occupancy Prediction with 4D Imaging Radar NIPS 2024 Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks CVPR 2024 Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset CVPR 2024 Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers CVPR 2024 Which Model Generated This Image? A Model-Agnostic Approach for Origin Attribution ECCV 2024 CVT-Occ: Cost Volume Temporal Fusion for 3D Occupancy Prediction ECCV 2024 Configuration Space Distance Fields for Manipulation Planning RSS 2024 IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency ICML 2024 Memorize What Matters: Emergent Scene Decomposition from Multitraverse NIPS 2024 ZeroMark: Towards Dataset Ownership Verification without Disclosing Watermark NIPS 2024 BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection ICLR 2024 Towards Faithful XAI Evaluation via Generalization-Limited Backdoor Watermark ICLR 2024 Towards Reliable and Efficient Backdoor Trigger Inversion via Decoupling Benign Features ICLR 2024 VoxFormer: Sparse Voxel Transformer for Camera-Based 3D Semantic Scene Completion CVPR 2023 DeepMapping2: Self-Supervised Large-Scale LiDAR Map Optimization CVPR 2023 Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand NIPS 2023 Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots NIPS 2023 Revisiting the Assumption of Latent Separability for Backdoor Defenses ICLR 2023 SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency ICLR 2023 Poisoning-Based Backdoor Attacks in Computer Vision AAAI 2023 Generating Transferable 3D Adversarial Point Cloud via Random Perturbation Factorization AAAI 2023 One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training ICCV 2023 Among Us: Adversarially Robust Collaborative Perception by Consensus ICCV 2023 Towards Robust Model Watermark via Reducing Parametric Vulnerability ICCV 2023 PVT++: A Simple End-to-End Latency-Aware Visual Tracking Framework ICCV 2023 Metric-Free Exploration for Topological Mapping by Task and Motion Imitation in Feature Space RSS 2023 Defending against Model Stealing via Verifying Embedded External Features AAAI 2022 Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection NIPS 2022 Multi-Robot Scene Completion: Towards Task-Agnostic Collaborative Perception CORL 2022 Egocentric Prediction of Action Target in 3D CVPR 2022 Dynamic Scene Graph Generation via Anticipatory Pre-Training CVPR 2022 Few-Shot Backdoor Attacks on Visual Object Tracking ICLR 2022 Backdoor Defense via Decoupling the Training Process ICLR 2022 Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits ICLR 2021 Fooling LiDAR Perception via Adversarial Trajectory Perturbation ICCV 2021 Invisible Backdoor Attack With Sample-Specific Triggers ICCV 2021 HiFT: Hierarchical Feature Transformer for Aerial Tracking ICCV 2021 Learning Distilled Collaboration Graph for Multi-Agent Perception NIPS 2021 Targeted Attack for Deep Hashing based Retrieval ECCV 2020 AutoTrack: Towards High-Performance Visual Tracking for UAV With Automatic Spatio-Temporal Regularization CVPR 2020 Learning Aberrance Repressed Correlation Filters for Real-Time UAV Tracking ICCV 2019