Xinmei Tian

Bridging the Language Gap: Uncovering and Aligning Shared Circuits for Multi-Hop Reasoning in Multilingual LLMs AAAI 2026 Cross-Modal Masked Compositional Concept Modeling for Enhancing Visio-Linguistic Compositionality ACL 2026 Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models CVPR 2026 A Similarity Paradigm Through Textual Regularization Without Forgetting AAAI 2025 A Theoretical Perspective: How to Prevent Model Collapse in Self-consuming Training Loops ICLR 2025 Enhancing Target-unspecific Tasks through a Features Matrix ICML 2025 Interpret and Improve In-Context Learning via the Lens of Input-Label Mappings ACL 2025 Leveraging Submodule Linearity Enhances Task Arithmetic Performance in LLMs ICLR 2025 Visual Evidence Prompting Mitigates Hallucinations in Large Vision-Language Models ACL 2025 Adaptive Time-Stepping Schedules for Diffusion Models UAI 2024 Convergence of Bayesian Bilevel Optimization ICLR 2024 Enhanced Motion-Text Alignment for Image-to-Video Transfer Learning CVPR 2024 FedImpro: Measuring and Improving Client Update in Federated Learning ICLR 2024 From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning ICML 2024 Interpretable Composition Attribution Enhancement for Visio-linguistic Compositional Understanding EMNLP 2024 Interpreting and Improving Large Language Models in Arithmetic Calculation ICML 2024 Out-of-Distribution Detection with Negative Prompts ICLR 2024 Robust Training of Federated Models with Extremely Label Deficiency ICLR 2024 Sheared Backpropagation for Fine-tuning Foundation Models CVPR 2024 Towards Theoretical Understandings of Self-Consuming Generative Models ICML 2024 FedFed: Feature Distillation against Data Heterogeneity in Federated Learning NeurIPS 2023 Moderately Distributional Exploration for Domain Generalization ICML 2023 Sharper Bounds for Uniformly Stable Algorithms with Stationary Mixing Process ICLR 2023 Structured Cooperative Learning with Graphical Model Priors ICML 2023 Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach NeurIPS 2022 Adversarial Robustness Through the Lens of Causality ICLR 2022 DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training ICML 2022 Identity-Disentangled Adversarial Augmentation for Self-supervised Learning ICML 2022 Learning To Collaborate in Decentralized Learning of Personalized Models CVPR 2022 Meta Convolutional Neural Networks for Single Domain Generalization CVPR 2022 Prompt Distribution Learning CVPR 2022 Self-Supervision Can Be a Good Few-Shot Learner ECCV 2022 Towards Lightweight Black-Box Attack Against Deep Neural Networks NeurIPS 2022 3D Local Convolutional Neural Networks for Gait Recognition ICCV 2021 A Style and Semantic Memory Mechanism for Domain Generalization ICCV 2021 Class-Disentanglement and Applications in Adversarial Detection and Defense NeurIPS 2021 Revisiting Knowledge Distillation: An Inheritance and Exploration Framework CVPR 2021 Dual-Path Distillation: A Unified Framework to Improve Black-Box Attacks ICML 2020 Learning to Localize Actions from Moments ECCV 2020 Camera Lens Super-Resolution CVPR 2019 Compact Feature Learning for Multi-Domain Image Classification CVPR 2019 Exploring Object Relation in Mean Teacher for Cross-Domain Detection CVPR 2019 Gaussian Temporal Awareness Networks for Action Localization CVPR 2019 KCNN: Kernel-wise Quantization to Remarkably Decrease Multiplications in Convolutional Neural Network IJCAI 2019 Learning Spatio-Temporal Representation With Local and Global Diffusion CVPR 2019 Quantization Networks CVPR 2019 A Twofold Siamese Network for Real-Time Object Tracking CVPR 2018 Deep Boosting for Image Denoising ECCV 2018 Deep Domain Generalization via Conditional Invariant Adversarial Networks ECCV 2018 Classification and Representation Joint Learning via Deep Networks IJCAI 2017 Multi-Task Model and Feature Joint Learning IJCAI 2015