Chao Ma

Grounding Everything in Tokens for Multimodal Large Language Models CVPR 2026 Guiding a Diffusion Model by Swapping Its Tokens CVPR 2026 Latent Knowledge-Guided Video Diffusion for Scientific Phenomena Generation from a Single Initial Frame AAAI 2026 Octopus: History-Free Gradient Orthogonalization for Continual Learning in Multimodal Large Language Models CVPR 2026 Parameter-Free Fine-tuning via Redundancy Elimination for Vision Foundation Models AAAI 2026 Thermally Activated Dual-Modal Adversarial Clothing against AI Surveillance Systems CVPR 2026 A Simple Approach to Unifying Diffusion-based Conditional Generation ICLR 2025 Corvid: Improving Multimodal Large Language Models Towards Chain-of-Thought Reasoning ICCV 2025 Cross-Architecture Distillation Made Simple with Redundancy Suppression ICCV 2025 Deploying Multi-task Online Server with Large Language Model COLING 2025 Domain Prompt Learning with Quaternion Networks (Extended Abstract) IJCAI 2025 HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos CVPR 2025 PVMamba: Parallelizing Vision Mamba via Dynamic State Aggregation ICCV 2025 Robust SAM: On the Adversarial Robustness of Vision Foundation Models AAAI 2025 S^3-Face: SSS-Compliant Facial Reflectance Estimation via Diffusion Priors CVPR 2025 SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training ICML 2025 Towards Generalized Face Anti-Spoofing from a Frequency Shortcut View WACV 2025 VRM: Knowledge Distillation via Virtual Relation Matching ICCV 2025 VTimeCoT: Thinking by Drawing for Video Temporal Grounding and Reasoning ICCV 2025 What You Have is What You Track: Adaptive and Robust Multimodal Tracking ICCV 2025 XTrack: Multimodal Training Boosts RGB-X Video Object Trackers ICCV 2025 A Fixed-Point Approach for Causal Generative Modeling ICML 2024 Alleviating Foreground Sparsity for Semi-Supervised Monocular 3D Object Detection WACV 2024 DiffusionTrack: Point Set Diffusion Model for Visual Object Tracking CVPR 2024 Domain-Controlled Prompt Learning AAAI 2024 Domain Prompt Learning with Quaternion Networks CVPR 2024 LERE: Learning-Based Low-Rank Matrix Recovery with Rank Estimation AAAI 2024 Monocular Identity-Conditioned Facial Reflectance Reconstruction CVPR 2024 NeuMA: Neural Material Adaptor for Visual Grounding of Intrinsic Dynamics NeurIPS 2024 OccGen: Generative Multi-modal 3D Occupancy Prediction for Autonomous Driving ECCV 2024 PapMOT: Exploring Adversarial Patch Attack against Multiple Object Tracking ECCV 2024 Prompt Learning with Quaternion Networks ICLR 2024 QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Model NeurIPS 2024 Single-Model and Any-Modality for Video Object Tracking CVPR 2024 SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction CVPR 2024 Towards Causal Foundation Model: on Duality between Optimal Balancing and Attention ICML 2024 Understanding the Generalization Benefits of Late Learning Rate Decay AISTATS 2024 VEON: Vocabulary-Enhanced Occupancy Prediction ECCV 2024 VidToMe: Video Token Merging for Zero-Shot Video Editing CVPR 2024 3D-Aware Face Swapping CVPR 2023 Causal Reasoning in the Presence of Latent Confounders via Neural ADMG Learning ICLR 2023 High Precision Causal Model Evaluation with Conditional Randomization NeurIPS 2023 Improving Fairness in Facial Albedo Estimation via Visual-Textual Cues CVPR 2023 PlenVDB: Memory Efficient VDB-Based Radiance Fields for Fast Training and Rendering CVPR 2023 ProtoTransfer: Cross-Modal Prototype Transfer for Point Cloud Segmentation ICCV 2023 SmartAssign: Learning a Smart Knowledge Assignment Strategy for Deraining and Desnowing CVPR 2023 T-distributed Spherical Feature Representation for Imbalanced Classification AAAI 2023 The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks ICLR 2023 Understanding Multi-phase Optimization Dynamics and Rich Nonlinear Behaviors of ReLU Networks NeurIPS 2023 UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye View CVPR 2023 VideoTrack: Learning To Track Objects via Video Transformer CVPR 2023 Adv-Attribute: Inconspicuous and Transferable Adversarial Attack on Face Recognition NeurIPS 2022 AiATrack: Attention in Attention for Transformer Visual Tracking ECCV 2022 Early Stage Convergence and Global Convergence of Training Mildly Parameterized Neural Networks NeurIPS 2022 End-to-End Reconstruction-Classification Learning for Face Forgery Detection CVPR 2022 Exploring Frequency Adversarial Attacks for Face Forgery Detection CVPR 2022 LIFT: Learning 4D LiDAR Image Fusion Transformer for 3D Object Detection CVPR 2022 Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlo NeurIPS 2022 PillarNet: Real-Time and High-Performance Pillar-Based 3D Object Detection ECCV 2022 Provably convergent quasistatic dynamics for mean-field two-player zero-sum games ICLR 2022 Unsupervised Sounding Object Localization With Bottom-Up and Top-Down Attention WACV 2022 Cross-Modality 3D Object Detection WACV 2021 Functional Variational Inference based on Stochastic Process Generators NeurIPS 2021 Identifiable Generative models for Missing Not at Random Data Imputation NeurIPS 2021 IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking CVPR 2021 Learning To Track Objects From Unlabeled Videos ICCV 2021 Learning Transferable Features for Point Cloud Detection via 3D Contrastive Co-training NeurIPS 2021 Multi-Decoding Deraining Network and Quasi-Sparsity Based Training CVPR 2021 On Linear Stability of SGD and Input-Smoothness of Neural Networks NeurIPS 2021 On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Framework ICML 2021 Partial Feature Selection and Alignment for Multi-Source Domain Adaptation CVPR 2021 PointAugmenting: Cross-Modal Augmentation for 3D Object Detection CVPR 2021 A Mean Field Analysis Of Deep ResNet And Beyond: Towards Provably Optimization Via Overparameterization From Depth ICML 2020 Rethinking Image Deraining via Rain Streaks and Vapors ECCV 2020 Robust Tracking against Adversarial Attacks ECCV 2020 Semantic Equivalent Adversarial Data Augmentation for Visual Question Answering ECCV 2020 Towards Theoretically Understanding Why Sgd Generalizes Better Than Adam in Deep Learning NeurIPS 2020 VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data NeurIPS 2020 Depth-Aware Video Frame Interpolation CVPR 2019 EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE ICML 2019 Global Convergence of Gradient Descent for Deep Linear Residual Networks NeurIPS 2019 Randomized Greedy Search for Structured Prediction: Amortized Inference and Learning IJCAI 2019 See More, Know More: Unsupervised Video Object Segmentation With Co-Attention Siamese Networks CVPR 2019 Target-Aware Deep Tracking CVPR 2019 Unsupervised Deep Tracking CVPR 2019 Variational Implicit Processes ICML 2019 A Joint Learning Approach to Intelligent Job Interview Assessment IJCAI 2018 Deep Attentive Tracking via Reciprocative Learning NeurIPS 2018 Deep Regression Tracking with Shrinkage Loss ECCV 2018 How SGD Selects the Global Minima in Over-parameterized Learning: A Dynamical Stability Perspective NeurIPS 2018 Joint Neural Entity Disambiguation with Output Space Search COLING 2018 Visual Question Answering With Memory-Augmented Networks CVPR 2018 VITAL: VIsual Tracking via Adversarial Learning CVPR 2018 CREST: Convolutional Residual Learning for Visual Tracking ICCV 2017 Multi-Task Structured Prediction for Entity Analysis: Search-Based Learning Algorithms ACML 2017 Select-and-Evaluate: A Learning Framework for Large-Scale Knowledge Graph Search ACML 2017 Video Segmentation via Multiple Granularity Analysis CVPR 2017 Improving Users’ Demographic Prediction via the Videos They Talk about EMNLP 2016 Hierarchical Convolutional Features for Visual Tracking ICCV 2015 Long-Term Correlation Tracking CVPR 2015 Prune-and-Score: Learning for Greedy Coreference Resolution EMNLP 2014