Chang Xu

Mitigating Legal Hallucinations via Symbolic Constraints and Analogical Precedents ACL 2026 Explainable Oracle Bone Script Recognition via Multimodal Pictographic Reasoning AAAI 2026 Eliciting Chain-of-Thought in Base LLMs via Gradient-Based Representation Optimization AAAI 2026 Controllable Financial Market Generation with Diffusion Guided Meta Agent AAAI 2026 Anti-Exposure Bias in Diffusion Models ICLR 2025 Lumina-Image 2.0: A Unified and Efficient Image Generative Framework ICCV 2025 SMARTIES: Spectrum-Aware Multi-Sensor Auto-Encoder for Remote Sensing Images ICCV 2025 VSSD: Vision Mamba with Non-Causal State Space Duality ICCV 2025 Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation ICCV 2025 Adversarial Robustness via Deformable Convolution with Stochasticity ICML 2025 Beyond One-Hot Labels: Semantic Mixing for Model Calibration ICML 2025 BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modeling ICML 2025 Stable Fair Graph Representation Learning with Lipschitz Constraint ICML 2025 WaterDiffusion: Learning a Prior-involved Unrolling Diffusion for Joint Underwater Saliency Detection and Visual Restoration AAAI 2025 Efficient Image-to-Image Diffusion Classifier for Adversarial Robustness AAAI 2025 EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba AAAI 2025 TimeDP: Learning to Generate Multi-Domain Time Series with Domain Prompts AAAI 2025 Feature Clipping for Uncertainty Calibration AAAI 2025 Does Acceleration Cause Hidden Instability in Vision Language Models? Uncovering Instance-Level Divergence Through a Large-Scale Empirical Study EMNLP 2025 ThoughtProbe: Classifier-Guided LLM Thought Space Exploration via Probing Representations EMNLP 2025 Learning Mask Invariant Mutual Information for Masked Image Modeling ICLR 2025 CollagePrompt: A Benchmark for Budget-Friendly Visual Recognition with GPT-4V NAACL 2025 DentEval: Fine-tuning-Free Expert-Aligned Assessment in Dental Education via LLM Agents MICCAI 2025 Minimizing Labeled, Maximizing Unlabeled: An Image-Driven Approach for Video Instance Segmentation CVPR 2025 Position: AI Scaling: From Up to Down and Out ICML 2025 Uncertainty Weighted Gradients for Model Calibration CVPR 2025 UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping CVPR 2025 Enhancing Privacy-Utility Trade-offs to Mitigate Memorization in Diffusion Models CVPR 2025 Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Models ICLR 2025 MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model ICLR 2025 Representative Guidance: Diffusion Model Sampling with Coherence ICLR 2025 Exploring Local Memorization in Diffusion Models via Bright Ending Attention ICLR 2025 Understanding and Mitigating Hallucination in Large Vision-Language Models via Modular Attribution and Intervention ICLR 2025 A Benchmark Study on Calibration ICLR 2024 Locating and Extracting Relational Concepts in Large Language Models ACL 2024 Active Generation for Image Classification ECCV 2024 Visual Prompting via Partial Optimal Transport ECCV 2024 ConGeo: Robust Cross-view Geo-localization across Ground View Variations ECCV 2024 Hybrid Proposal Refiner: Revisiting DETR Series from the Faster R-CNN Perspective CVPR 2024 Random Entangled Tokens for Adversarially Robust Vision Transformer CVPR 2024 Residual Learning in Diffusion Models CVPR 2024 Towards Memorization-Free Diffusion Models CVPR 2024 Detecting Any instruction-to-answer interaction relationship:Universal Instruction-to-Answer Navigator for Med-VQA ICML 2024 Bridging Data Gaps in Diffusion Models with Adversarial Noise-Based Transfer Learning ICML 2024 Imitation Learning from Purified Demonstrations ICML 2024 GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer ICML 2024 Data-efficient Large Vision Models through Sequential Autoregression ICML 2024 Boosting Diffusion Models with an Adaptive Momentum Sampler IJCAI 2024 Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model NIPS 2024 A Large-Scale Human-Centric Benchmark for Referring Expression Comprehension in the LMM Era NIPS 2024 Enhancing Large Language Models through Adaptive Tokenizers NIPS 2024 Adapt without Forgetting: Distill Proximity from Dual Teachers in Vision-Language Models ECCV 2024 MG-TSD: Multi-Granularity Time Series Diffusion Models with Guided Learning Process ICLR 2024 Neural Architecture Retrieval ICLR 2024 AMD: Autoregressive Motion Diffusion AAAI 2024 Harnessing Edge Information for Improved Robustness in Vision Transformers AAAI 2024 Learning Visual Abstract Reasoning through Dual-Stream Networks AAAI 2024 Training-free Composite Scene Generation for Layout-to-Image Synthesis ECCV 2024 Beyond Pretrained Features: Noisy Image Modeling Provides Adversarial Defense NIPS 2023 Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundation Models NIPS 2023 Revisit the Power of Vanilla Knowledge Distillation: from Small Scale to Large Scale NIPS 2023 Adversarial Robustness through Random Weight Sampling NIPS 2023 Rethinking Conditional Diffusion Sampling with Progressive Guidance NIPS 2023 Stable Diffusion is Unstable NIPS 2023 Knowledge Diffusion for Distillation NIPS 2023 Contrastive Sampling Chains in Diffusion Models NIPS 2023 One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation NIPS 2023 Neural Architecture Search for Wide Spectrum Adversarial Robustness AAAI 2023 Boosting Semi-Supervised Semantic Segmentation with Probabilistic Representations AAAI 2023 Unlabeled Imperfect Demonstrations in Adversarial Imitation Learning AAAI 2023 ContraFeat: Contrasting Deep Features for Semantic Discovery AAAI 2023 Dynamic Coarse-To-Fine Learning for Oriented Tiny Object Detection CVPR 2023 PSVT: End-to-End Multi-Person 3D Pose and Shape Estimation With Progressive Video Transformers CVPR 2023 Trade-Off Between Robustness and Accuracy of Vision Transformers CVPR 2023 Private Image Generation With Dual-Purpose Auxiliary Classifier CVPR 2023 Adversarial Robustness via Random Projection Filters CVPR 2023 Personalized Image Generation for Color Vision Deficiency Population ICCV 2023 What Can Simple Arithmetic Operations Do for Temporal Modeling? ICCV 2023 Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detection ICCV 2023 Speech4Mesh: Speech-Assisted Monocular 3D Facial Reconstruction for Speech-Driven 3D Facial Animation ICCV 2023 SimMatchV2: Semi-Supervised Learning with Graph Consistency ICCV 2023 Diffusion Action Segmentation ICCV 2023 Masked Distillation with Receptive Tokens ICLR 2023 PixelAsParam: A Gradient View on Diffusion Sampling with Guidance ICML 2023 Dual Focal Loss for Calibration ICML 2023 Calibrating a Deep Neural Network with Its Predecessors IJCAI 2023 DSTrans: Dual-Stream Transformer for Hyperspectral Image Restoration WACV 2023 Searching for Better Spatio-temporal Alignment in Few-Shot Action Recognition NIPS 2022 RFLA: Gaussian Receptive Field Based Label Assignment for Tiny Object Detection ECCV 2022 ViTAS: Vision Transformer Architecture Search ECCV 2022 Random Normalization Aggregation for Adversarial Defense NIPS 2022 An Image Patch Is a Wave: Phase-Aware Vision MLP CVPR 2022 GreedyNASv2: Greedier Search With a Greedy Path Filter CVPR 2022 Patch Slimming for Efficient Vision Transformers CVPR 2022 DyRep: Bootstrapping Training With Dynamic Re-Parameterization CVPR 2022 Knowledge Distillation from A Stronger Teacher NIPS 2022 CMT: Convolutional Neural Networks Meet Vision Transformers CVPR 2022 Hire-MLP: Vision MLP via Hierarchical Rearrangement CVPR 2022 SimMatch: Semi-Supervised Learning With Similarity Matching CVPR 2022 GhostNetV2: Enhance Cheap Operation with Long-Range Attention NIPS 2022 Spatial-Channel Token Distillation for Vision MLPs ICML 2022 One Size Does NOT Fit All: Data-Adaptive Adversarial Training ECCV 2022 DeepFake Disrupter: The Detector of DeepFake Is My Friend CVPR 2022 Relational Surrogate Loss Learning ICLR 2022 As Easy as 1, 2, 3: Behavioural Testing of NMT Systems for Numerical Translation ACL 2021 Putting words into the system’s mouth: A targeted attack on neural machine translation using monolingual data poisoning ACL 2021 Mitigating Data Poisoning in Text Classification with Differential Privacy EMNLP 2021 Positive-Unlabeled Data Purification in the Wild for Object Detection CVPR 2021 Distilling Object Detectors via Decoupled Features CVPR 2021 Pre-Trained Image Processing Transformer CVPR 2021 AdderSR: Towards Energy Efficient Image Super-Resolution CVPR 2021 Learning Student Networks in the Wild CVPR 2021 ReNAS: Relativistic Evaluation of Neural Architecture Search CVPR 2021 Learning Frequency-Aware Dynamic Network for Efficient Super-Resolution ICCV 2021 Weakly Supervised Contrastive Learning ICCV 2021 Putting words into the system’s mouth: A targeted attack on neural machine translation using monolingual data poisoning IJCNLP 2021 As Easy as 1, 2, 3: Behavioural Testing of NMT Systems for Numerical Translation IJCNLP 2021 One-shot Graph Neural Architecture Search with Dynamic Search Space AAAI 2021 Adversarial Robustness through Disentangled Representations AAAI 2021 PTN: A Poisson Transfer Network for Semi-supervised Few-shot Learning AAAI 2021 Locally Free Weight Sharing for Network Width Search ICLR 2021 ReSSL: Relational Self-Supervised Learning with Weak Augmentation NIPS 2021 Manifold Regularized Dynamic Network Pruning CVPR 2021 Where and What? Examining Interpretable Disentangled Representations CVPR 2021 Robust Adversarial Imitation Learning via Adaptively-Selected Demonstrations IJCAI 2021 An Empirical Study of Adder Neural Networks for Object Detection NIPS 2021 Towards Stable and Robust AdderNets NIPS 2021 Augmented Shortcuts for Vision Transformers NIPS 2021 Handling Long-tailed Feature Distribution in AdderNets NIPS 2021 Learning Frequency Domain Approximation for Binary Neural Networks NIPS 2021 Neural Architecture Dilation for Adversarial Robustness NIPS 2021 BCNet: Searching for Network Width With Bilaterally Coupled Network CVPR 2021 K-shot NAS: Learnable Weight-Sharing for NAS with K-shot Supernets ICML 2021 Learning to Weight Imperfect Demonstrations ICML 2021 Commutative Lie Group VAE for Disentanglement Learning ICML 2021 Prioritized Architecture Sampling With Monto-Carlo Tree Search CVPR 2021 HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens CVPR 2021 Distilling Portable Generative Adversarial Networks for Image Translation AAAI 2020 On Positive-Unlabeled Classification in GAN CVPR 2020 AdderNet: Do We Really Need Multiplications in Deep Learning? CVPR 2020 CARS: Continuous Evolution for Efficient Neural Architecture Search CVPR 2020 A Semi-Supervised Assessor of Neural Architectures CVPR 2020 Neuromorphic Camera Guided High Dynamic Range Imaging CVPR 2020 Frequency Domain Compact 3D Convolutional Neural Networks CVPR 2020 GhostNet: More Features From Cheap Operations CVPR 2020 Optical Flow Distillation: Towards Efficient and Stable Video Style Transfer ECCV 2020 Learning Disentangled Representations with Latent Variation Predictability ECCV 2020 On Dropping Clusters to Regularize Graph Convolutional Neural Networks ECCV 2020 Assessing Social License to Operate from the Public Discourse on Social Media COLING 2020 SCOP: Scientific Control for Reliable Neural Network Pruning NIPS 2020 Speaker-Aware Monaural Speech Separation INTERSPEECH 2020 Searching for Low-Bit Weights in Quantized Neural Networks NIPS 2020 UnModNet: Learning to Unwrap a Modulo Image for High Dynamic Range Imaging NIPS 2020 Efficient Residual Dense Block Search for Image Super-Resolution AAAI 2020 Reborn Filters: Pruning Convolutional Neural Networks with Limited Data AAAI 2020 Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks AAAI 2020 Learning Student Networks with Few Data AAAI 2020 Training Binary Neural Networks through Learning with Noisy Supervision ICML 2020 Neural Architecture Search in A Proxy Validation Loss Landscape ICML 2020 Adapting Neural Architectures Between Domains NIPS 2020 Kernel Based Progressive Distillation for Adder Neural Networks NIPS 2020 Context Aware Graph Convolution for Skeleton-Based Action Recognition CVPR 2020 Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection CVPR 2020 Approximated Bilinear Modules for Temporal Modeling ICCV 2019 Co-Evolutionary Compression for Unpaired Image Translation ICCV 2019 Learning Instance-wise Sparsity for Accelerating Deep Models IJCAI 2019 Attribute Aware Pooling for Pedestrian Attribute Recognition IJCAI 2019 Data-Free Learning of Student Networks ICCV 2019 Self-Supervised Representation Learning From Multi-Domain Data ICCV 2019 Recognising Agreement and Disagreement between Stances with Reason Comparing Networks ACL 2019 Learning from Bad Data via Generation NIPS 2019 Self-Supervised Representation Learning by Rotation Feature Decoupling CVPR 2019 Image-Question-Answer Synergistic Network for Visual Dialog CVPR 2019 LegoNet: Efficient Convolutional Neural Networks with Lego Filters ICML 2019 Deep Hierarchical Graph Convolution for Election Prediction from Geospatial Census Data AAAI 2019 Smooth Deep Image Generator from Noises AAAI 2019 Modeling Local Dependence in Natural Language with Multi-Channel Recurrent Neural Networks AAAI 2019 Polygon-Net: A General Framework for Jointly Boosting Multiple Unsupervised Neural Machine Translation Models IJCAI 2019 Positive-Unlabeled Compression on the Cloud NIPS 2019 On Retrospecting Human Dynamics with Attention IJCAI 2019 Crafting Efficient Neural Graph of Large Entropy IJCAI 2019 Cross-Target Stance Classification with Self-Attention Networks ACL 2018 Attention-GAN for Object Transfiguration in Wild Images ECCV 2018 R-SVM+: Robust Learning with Privileged Information IJCAI 2018 Learning Versatile Filters for Efficient Convolutional Neural Networks NIPS 2018 Beyond Filters: Compact Feature Map for Portable Deep Model ICML 2017 Privileged Matrix Factorization for Collaborative Filtering IJCAI 2017 Collaborative Rating Allocation IJCAI 2017 Fast SVM Trained by Divide-and-Conquer Anchors IJCAI 2017 Tag Disentangled Generative Adversarial Network for Object Image Re-rendering IJCAI 2017 Multi-Positive and Unlabeled Learning IJCAI 2017 Privileged Multi-label Learning IJCAI 2017 Online Reputation Fraud Campaign Detection in User Ratings IJCAI 2017 CNNpack: Packing Convolutional Neural Networks in the Frequency Domain NIPS 2016 Improving Sybil Detection via Graph Pruning and Regularization Techniques ACML 2015 Multi-view Self-Paced Learning for Clustering IJCAI 2015 Large-margin Weakly Supervised Dimensionality Reduction ICML 2014