Pavlo Molchanov

12

Papers

775

Total Citations

Papers (12)

VILA: On Pre-training for Visual Language Models

Hymba: A Hybrid-head Architecture for Small Language Models

VILA-M3: Enhancing Vision-Language Models with Medical Expert Knowledge

LLaMaFlex: Many-in-one LLMs via Generalized Pruning and Weight Sharing

FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting

Token-Efficient VLM: High-Resolution Image Understanding via Dynamic Region Proposal

RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models

NVILA: Efficient Frontier Visual Language Models

Scaling Vision Pre-Training to 4K Resolution

AM-RADIO: Agglomerative Vision Foundation Model Reduce All Domains Into One

DoRA: Weight-Decomposed Low-Rank Adaptation

Flextron: Many-in-One Flexible Large Language Model