Cihang Xie

LVM-Lite: Training Large Vision Models with Efficient Sequential Modeling WACV 2026 STAR-1: Safer Alignment of Reasoning LLMs with 1K Data AAAI 2026 Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency CVPR 2025 Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More ICML 2025 What If We Recaption Billions of Web Images with LLaMA-3? ICML 2025 MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine ICLR 2025 Autoregressive Pretraining with Mamba in Vision ICLR 2025 HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing ICLR 2025 OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning ICCV 2025 VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges ICCV 2025 ViLBench: A Suite for Vision-Language Process Reward Modeling EMNLP 2025 Mamba-Reg: Vision Mamba Also Needs Registers CVPR 2025 Generative Image Layer Decomposition with Visual Effects CVPR 2025 Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training CVPR 2024 Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning ICLR 2024 A Semantic Space is Worth 256 Language Descriptions: Make Stronger Segmentation Models with Descriptive Properties ECCV 2024 Scaling White-Box Transformers for Vision NIPS 2024 VHELM: A Holistic Evaluation of Vision Language Models NIPS 2024 Navigation as Attackers Wish? Towards Building Robust Embodied Agents under Federated Learning NAACL 2024 How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs ECCV 2024 Revisiting Adversarial Training at Scale CVPR 2024 L2B: Learning to Bootstrap Robust Models for Combating Label Noise CVPR 2024 Rejuvenating image-GPT as Strong Visual Representation Learners ICML 2024 Localization vs. Semantics: Visual Representations in Unimodal and Multimodal Models EACL 2024 From Pixels to Objects: A Hierarchical Approach for Part and Object Segmentation Using Local and Global Aggregation ECCV 2024 Diffusion Models as Masked Autoencoders ICCV 2023 An Inverse Scaling Law for CLIP Training NIPS 2023 Practical Disruption of Image Translation Deepfake Networks AAAI 2023 Masked Autoencoders Enable Efficient Knowledge Distillers CVPR 2023 SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-Training ICCV 2023 DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillation ICCV 2023 Can CNNs Be More Robust Than Transformers? ICLR 2023 One-Pixel Shortcut: On the Learning Preference of Deep Neural Networks ICLR 2023 Simulated Adversarial Testing of Face Recognition Models CVPR 2022 A Simple Data Mixing Prior for Improving Self-Supervised Learning CVPR 2022 Fast AdvProp ICLR 2022 Image BERT Pre-training with Online Tokenizer ICLR 2022 Adversarial Attack on Attackers: Post-Process to Mitigate Black-Box Score-Based Query Attacks NIPS 2022 Finding Differences Between Transformers and ConvNets Using Counterfactual Simulation Testing NIPS 2022 In Defense of Image Pre-training for Spatiotemporal Recognition ECCV 2022 VIP: Unified Certified Detection and Recovery for Patch Attack with Vision Transformers ECCV 2022 Robust and Accurate Object Detection via Adversarial Learning CVPR 2021 Are Transformers more robust than CNNs? NIPS 2021 Calibrating Concepts and Operations: Towards Symbolic Reasoning on Real Images ICCV 2021 Shape-Texture Debiased Neural Network Training ICLR 2021 Neural Architecture Search for Lightweight Non-Local Networks CVPR 2020 Adversarial Examples Improve Image Recognition CVPR 2020 Universal Physical Camouflage Attacks on Object Detectors CVPR 2020 Intriguing Properties of Adversarial Training at Scale ICLR 2020 PatchAttack: A Black-box Texture-based Attack with Reinforcement Learning ECCV 2020 Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses ECCV 2020 Learning Transferable Adversarial Examples via Ghost Networks AAAI 2020 Feature Denoising for Improving Adversarial Robustness CVPR 2019 Improving Transferability of Adversarial Examples With Input Diversity CVPR 2019 Mitigating Adversarial Effects Through Randomization ICLR 2018 Single-Shot Object Detection With Enriched Semantics CVPR 2018 DeepVoting: A Robust and Explainable Deep Network for Semantic Part Detection Under Partial Occlusion CVPR 2018 Adversarial Examples for Semantic Segmentation and Object Detection ICCV 2017