Hongxu Yin

Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing CVPR 2026 Grounded 3D-Aware Spatial Vision-Language Modeling CVPR 2026 Scaling Parallel Sequence Models to Vision Foundation Models CVPR 2026 Advancing Weight and Channel Sparsification with Enhanced Saliency WACV 2025 Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders ICLR 2025 LLaMaFlex: Many-in-one LLMs via Generalized Pruning and Weight Sharing ICLR 2025 LongVILA: Scaling Long-Context Visual Language Models for Long Videos ICLR 2025 NaVILA: Legged Robot Vision-Language-Action Model for Navigation RSS 2025 NVILA: Efficient Frontier Visual Language Models CVPR 2025 RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models CVPR 2025 Scaling Vision Pre-Training to 4K Resolution CVPR 2025 Token-Efficient VLM: High-Resolution Image Understanding via Dynamic Region Proposal ICCV 2025 VILA-M3: Enhancing Vision-Language Models with Medical Expert Knowledge CVPR 2025 VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation ICLR 2025 Adaptive Sharpness-Aware Pruning for Robust Sparse Networks ICLR 2024 DoRA: Weight-Decomposed Low-Rank Adaptation ICML 2024 FasterViT: Fast Vision Transformers with Hierarchical Attention ICLR 2024 FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models ICML 2024 Flextron: Many-in-One Flexible Large Language Model ICML 2024 LITA: Language Instructed Temporal-Localization Assistant ECCV 2024 MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models NeurIPS 2024 RegionGPT: Towards Region Understanding Vision Language Model CVPR 2024 SpatialRGPT: Grounded Spatial Reasoning in Vision-Language Models NeurIPS 2024 VILA: On Pre-training for Visual Language Models CVPR 2024 Global Context Vision Transformers ICML 2023 Global Vision Transformer Pruning With Hessian-Aware Saliency CVPR 2023 Heterogeneous Continual Learning CVPR 2023 Loss-Guided Diffusion Models for Plug-and-Play Controllable Generation ICML 2023 Recurrence Without Recurrence: Stable Video Landmark Detection With Deep Equilibrium Models CVPR 2023 A-ViT: Adaptive Tokens for Efficient Vision Transformer CVPR 2022 GradViT: Gradient Inversion of Vision Transformers CVPR 2022 LANA: Latency Aware Network Acceleration ECCV 2022 Structural Pruning via Latency-Saliency Knapsack NeurIPS 2022 When To Prune? A Policy Towards Early Structural Pruning CVPR 2022 Data-Free Knowledge Distillation for Object Detection WACV 2021 Optimal Quantization Using Scaled Codebook CVPR 2021 See Through Gradients: Image Batch Recovery via GradInversion CVPR 2021 Dreaming to Distill: Data-Free Knowledge Transfer via DeepInversion CVPR 2020 ChamNet: Towards Efficient Network Design Through Platform-Aware Model Adaptation CVPR 2019