Pavlo Molchanov

NVILA: Efficient Frontier Visual Language Models CVPR 2025 RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models CVPR 2025 FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting CVPR 2025 Advancing Weight and Channel Sparsification with Enhanced Saliency WACV 2025 LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models ICML 2025 FeatSharp: Your Vision Model Features, Sharper ICML 2025 Puzzle: Distillation-Based NAS for Inference-Optimized LLMs ICML 2025 LLaMaFlex: Many-in-one LLMs via Generalized Pruning and Weight Sharing ICLR 2025 Hymba: A Hybrid-head Architecture for Small Language Models ICLR 2025 LongVILA: Scaling Long-Context Visual Language Models for Long Videos ICLR 2025 LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement ICLR 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 Scaling Vision Pre-Training to 4K Resolution CVPR 2025 Flextron: Many-in-One Flexible Large Language Model ICML 2024 MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models NIPS 2024 Compact Language Models via Pruning and Knowledge Distillation NIPS 2024 AM-RADIO: Agglomerative Vision Foundation Model Reduce All Domains Into One CVPR 2024 VILA: On Pre-training for Visual Language Models CVPR 2024 COIN: Control-Inpainting Diffusion Prior for Human and Camera Motion Estimation ECCV 2024 LITA: Language Instructed Temporal-Localization Assistant ECCV 2024 Adaptive Sharpness-Aware Pruning for Robust Sparse Networks ICLR 2024 FasterViT: Fast Vision Transformers with Hierarchical Attention ICLR 2024 DoRA: Weight-Decomposed Low-Rank Adaptation ICML 2024 Global Context Vision Transformers ICML 2023 RANA: Relightable Articulated Neural Avatars ICCV 2023 Heterogeneous Continual Learning CVPR 2023 Recurrence Without Recurrence: Stable Video Landmark Detection With Deep Equilibrium Models CVPR 2023 Global Vision Transformer Pruning With Hessian-Aware Saliency CVPR 2023 GLAMR: Global Occlusion-Aware Human Mesh Recovery With Dynamic Cameras CVPR 2022 GradViT: Gradient Inversion of Vision Transformers CVPR 2022 LANA: Latency Aware Network Acceleration ECCV 2022 A-ViT: Adaptive Tokens for Efficient Vision Transformer CVPR 2022 Structural Pruning via Latency-Saliency Knapsack NIPS 2022 When To Prune? A Policy Towards Early Structural Pruning CVPR 2022 Optimal Quantization Using Scaled Codebook CVPR 2021 See Through Gradients: Image Batch Recovery via GradInversion CVPR 2021 DexYCB: A Benchmark for Capturing Hand Grasping of Objects CVPR 2021 Data-Free Knowledge Distillation for Object Detection WACV 2021 Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction ECCV 2020 Weakly Supervised 3D Hand Pose Estimation via Biomechanical Constraints ECCV 2020 Dreaming to Distill: Data-Free Knowledge Transfer via DeepInversion CVPR 2020 Weakly-Supervised 3D Human Pose Learning via Multi-View Images in the Wild CVPR 2020 Few-Shot Adaptive Gaze Estimation ICCV 2019 Importance Estimation for Neural Network Pruning CVPR 2019 SCOPS: Self-Supervised Co-Part Segmentation CVPR 2019 Hand Pose Estimation via Latent 2.5D Heatmap Regression ECCV 2018 Improving Landmark Localization With Semi-Supervised Learning CVPR 2018 Making Convolutional Networks Recurrent for Visual Sequence Learning CVPR 2018 Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals CVPR 2018 A Lightweight Approach for On-The-Fly Reflectance Estimation ICCV 2017 Online Detection and Classification of Dynamic Hand Gestures With Recurrent 3D Convolutional Neural Network CVPR 2016