Hang Su

Benchmarking Trustworthiness in Multimodal LLMs for Video Understanding AAAI 2026 Red Teaming Large Reasoning Models ACL 2026 FedCD: Towards Consolidated Distillation for Heterogeneous Federated Learning AAAI 2026 ReflexDiffusion: Reflection-Enhanced Trajectory Planning for High-lateral-acceleration Scenarios in Autonomous Driving AAAI 2026 H-RDT: Human Manipulation Enhanced Bimanual Robotic Manipulation AAAI 2026 Dual-Seed Evolutionary Algorithm for Noise Optimization in Diffusion Models AAAI 2026 The Subtle Art of Defection: Understanding Uncooperative Behaviors in LLM based Multi-Agent Systems EACL 2026 Active Generalized Category Discovery with Diverse LLM Feedback EACL 2026 Accelerating PDE-Constrained Optimization by the Derivative of Neural Operators ICML 2025 A Linear N-Point Solver for Structure and Motion from Asynchronous Tracks ICCV 2025 Self-Consistent Model-based Adaptation for Visual Reinforcement Learning IJCAI 2025 MDSEval: A Meta-Evaluation Benchmark for Multimodal Dialogue Summarization EMNLP 2025 Understanding and Improving Information Preservation in Prompt Compression for LLMs EMNLP 2025 HybridDepth: Robust Metric Depth Fusion by Leveraging Depth from Focus and Single-Image Priors WACV 2025 Zero-Shot Monocular Scene Flow Estimation in the Wild CVPR 2025 Visual Generation Without Guidance ICML 2025 Learning to Summarize from LLM-generated Feedback NAACL 2025 Towards Multi-dimensional Evaluation of LLM Summarization across Domains and Languages ACL 2025 Graph Diffusion for Robust Multi-Agent Coordination ICML 2025 AutoBreach: Universal and Adaptive Jailbreaking with Efficient Wordplay-Guided Optimization via Multi-LLMs NAACL 2025 Faithful, Unfaithful or Ambiguous? Multi-Agent Debate with Initial Stance for Summary Evaluation NAACL 2025 Exploring the Generalizability of Factual Hallucination Mitigation via Enhancing Precise Knowledge Utilization EMNLP 2025 Personalized Question Answering with User Profile Generation and Compression EMNLP 2025 RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation ICLR 2025 Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment ICLR 2025 AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations? ICCV 2025 Exploring the Transferability of Visual Prompting for Multimodal Large Language Models CVPR 2024 Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches ICLR 2024 Omniview-Tuning: Boosting Viewpoint Invariance of Vision-Language Pre-training Models ECCV 2024 Controllable Navigation Instruction Generation with Chain of Thought Prompting ECCV 2024 CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model ECCV 2024 Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection ECCV 2024 LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents ECCV 2024 Controllable Contextualized Image Captioning: Directing the Visual Narrative through User-Defined Highlights ECCV 2024 DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks ECCV 2024 TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization NAACL 2024 Score Regularized Policy Optimization through Diffusion Behavior ICLR 2024 UniSumEval: Towards Unified, Fine-grained, Multi-dimensional Summarization Evaluation for LLMs EMNLP 2024 CERET: Cost-Effective Extrinsic Refinement for Text Generation NAACL 2024 Semi-Supervised Dialogue Abstractive Summarization via High-Quality Pseudolabel Selection NAACL 2024 MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models NIPS 2024 Diffusion Models are Certifiably Robust Classifiers NIPS 2024 PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning NIPS 2024 Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy NIPS 2024 PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs NIPS 2024 Full-Distance Evasion of Pedestrian Detectors in the Physical World NIPS 2024 Noise Contrastive Alignment of Language Models with Explicit Rewards NIPS 2024 Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control NIPS 2024 Improved Operator Learning by Orthogonal Attention ICML 2024 Fourier Controller Networks for Real-Time Decision-Making in Embodied Learning ICML 2024 Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency ICML 2024 Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning ICML 2024 DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training ICML 2024 MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets NAACL 2024 Can Your Model Tell a Negation from an Implicature? Unravelling Challenges With Intent Encoders ACL 2024 FineSurE: Fine-grained Summarization Evaluation using LLMs ACL 2024 Reference Neural Operators: Learning the Smooth Dependence of Solutions of PDEs on Geometric Deformations ICML 2024 Robust Classification via a Single Diffusion Model ICML 2024 Rethinking Model Ensemble in Transfer-based Adversarial Attacks ICLR 2024 Speaker Change Detection with Weighted-sum Knowledge Distillation based on Self-supervised Pre-trained Models INTERSPEECH 2024 Towards Transferable Targeted 3D Adversarial Attack in the Physical World CVPR 2024 An N-Point Linear Solver for Line and Motion Estimation with Event Cameras CVPR 2024 Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement Learning ICML 2023 On the Reuse Bias in Off-Policy Reinforcement Learning IJCAI 2023 Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality NIPS 2023 DQ-DETR: Dual Query Detection Transformer for Phrase Extraction and Grounding AAAI 2023 Meta-Reinforcement Learning Based on Self-Supervised Task Representation Learning AAAI 2023 Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition CVPR 2023 All Are Worth Words: A ViT Backbone for Diffusion Models CVPR 2023 Benchmarking Robustness of 3D Object Detection to Common Corruptions CVPR 2023 ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation NIPS 2023 Enhancing Abstractiveness of Summarization Models through Calibrated Distillation EMNLP 2023 A 5-Point Minimal Solver for Event Camera Relative Motion Estimation ICCV 2023 Towards Viewpoint-Invariant Visual Recognition via Adversarial Training ICCV 2023 COCO-O: A Benchmark for Object Detectors under Natural Distribution Shifts ICCV 2023 Detection Transformer with Stable Matching ICCV 2023 Overcoming Recency Bias of Normalization Statistics in Continual Learning: Balance and Adaptation NIPS 2023 Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling ICLR 2023 DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection ICLR 2023 Bi-level Physics-Informed Neural Networks for PDE Constrained Optimization using Broyden's Hypergradients ICLR 2023 One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale ICML 2023 GNOT: A General Neural Operator Transformer for Operator Learning ICML 2023 NUNO: A General Framework for Learning Parametric PDEs with Non-Uniform Data ICML 2023 MultiAdam: Parameter-wise Scale-invariant Optimizer for Multiscale Training of Physics-informed Neural Networks ICML 2023 ViewFool: Evaluating the Robustness of Visual Recognition to Adversarial Viewpoints NIPS 2022 Policy Learning for Robust Markov Decision Process with a Mismatched Generative Model AAAI 2022 Towards Safe Reinforcement Learning via Constraining Conditional Value-at-Risk IJCAI 2022 Cluster Attack: Query-based Adversarial Attacks on Graph with Graph-Dependent Priors IJCAI 2022 Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks ECCV 2022 Tianshou: A Highly Modularized Deep Reinforcement Learning Library JMLR 2022 Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart CVPR 2022 Exploring Memorization in Adversarial Training ICLR 2022 DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR ICLR 2022 A Unified Hard-Constraint Framework for Solving Geometrically Complex PDEs NIPS 2022 GSmooth: Certified Robustness against Semantic Transformations via Generalized Randomized Smoothing ICML 2022 Bag of Tricks for Adversarial Training ICLR 2021 Flexi-Transducer: Optimizing Latency, Accuracy and Compute for Multi-Domain On-Device Scenarios INTERSPEECH 2021 Accumulative Poisoning Attacks on Real-time Data NIPS 2021 Beta Distribution Guided Aspect-aware Graph for Aspect Category Sentiment Analysis with Affective Knowledge EMNLP 2021 Unsupervised Part Segmentation Through Disentangling Appearance and Shape CVPR 2021 QAIR: Practical Query-Efficient Black-Box Attacks for Image Retrieval CVPR 2021 Combining Tree Search and Action Prediction for State-of-the-Art Performance in DouDiZhu IJCAI 2021 Dissecting User-Perceived Latency of On-Device E2E Speech Recognition INTERSPEECH 2021 LiBRe: A Practical Bayesian Approach to Adversarial Detection CVPR 2021 Learning Task-Distribution Reward Shaping with Meta-Learning AAAI 2021 Towards Face Encryption by Generating Adversarial Identity Masks ICCV 2021 Black-Box Detection of Backdoor Attacks With Limited Information and Data ICCV 2021 Composite Adversarial Attacks AAAI 2021 Defense Against Adversarial Attacks via Controlling Gradient Leaking on Embedded Manifolds ECCV 2020 Boosting Adversarial Training with Hypersphere Embedding NIPS 2020 Adversarial Distributional Training for Robust Deep Learning NIPS 2020 Bi-level Score Matching for Learning Energy-based Latent Variable Models NIPS 2020 Dynamic Network Pruning with Interpretable Layerwise Channel Selection AAAI 2020 Pruning from Scratch AAAI 2020 Benchmarking Adversarial Robustness on Image Classification CVPR 2020 Training Interpretable Convolutional Neural Networks by Differentiating Class-specific Filters ECCV 2020 SVQN: Sequential Variational Soft Q-Learning Networks ICLR 2020 Combo-Action: Training Agent For FPS Game with Auxiliary Tasks AAAI 2019 Unsupervised Methods for Audio Classification from Lecture Discussion Recordings INTERSPEECH 2019 Playing FPS Games With Environment-Aware Hierarchical Reinforcement Learning IJCAI 2019 Improving Black-box Adversarial Attacks with a Transfer-based Prior NIPS 2019 Pixel-Adaptive Convolutional Neural Networks CVPR 2019 Efficient Decision-Based Black-Box Adversarial Attacks on Face Recognition CVPR 2019 Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks CVPR 2019 Sparse Adversarial Perturbations for Videos AAAI 2019 Interpret Neural Networks by Identifying Critical Data Routing Paths CVPR 2018 Boosting Adversarial Attacks With Momentum CVPR 2018 SPLATNet: Sparse Lattice Networks for Point Cloud Processing CVPR 2018 Learning to Write Stylized Chinese Characters by Reading a Handful of Examples IJCAI 2018 Textbook Question Answering Under Instructor Guidance With Memory Networks CVPR 2018 End-To-End Face Detection and Cast Grouping in Movies Using Erdos-Renyi Clustering ICCV 2017 Improving Interpretability of Deep Neural Networks With Semantic Information CVPR 2017 Forecast the Plausible Paths in Crowd Scenes IJCAI 2017 Semi-supervised Max-margin Topic Model with Manifold Posterior Regularization IJCAI 2017 Crowd Scene Understanding with Coherent Recurrent Neural Networks IJCAI 2016 Factor Analysis Based Speaker Verification Using ASR INTERSPEECH 2016 Semi-Supervised and Cross-Lingual Knowledge Transfer Learnings for DNN Hybrid Acoustic Models Under Low-Resource Conditions INTERSPEECH 2016 Active Sample Selection and Correction Propagation on a Gradually-Augmented Graph CVPR 2015 Multi-View Convolutional Neural Networks for 3D Shape Recognition ICCV 2015