Pavlo Molchanov's picture

Pavlo Molchanov PRO

pmolchanov

·

https://www.pmolchanov.com

AI & ML interests

Efficiency in Multi-Modal LLMs

Recent Activity

new activity 8 days ago

nvidia/Hymba-1.5B-Base:Update LMFlow support

updated a Space 11 days ago

pmolchanov/Hymba-chat

updated a model 16 days ago

nvidia/Hymba-1.5B-Instruct

View all activity

Organizations

pmolchanov's activity

upvoted a paper 16 days ago

NVILA: Efficient Frontier Visual Language Models

Paper • 2412.04468 • Published 17 days ago • 54

upvoted a paper 19 days ago

Cautious Optimizers: Improving Training with One Line of Code

Paper • 2411.16085 • Published 28 days ago • 15

upvoted a collection 26 days ago

Hymba

A series of Hybrid Small Language Models. • 2 items • Updated about 1 month ago • 24

upvoted a paper 26 days ago

Star Attention: Efficient LLM Inference over Long Sequences

Paper • 2411.17116 • Published 27 days ago • 47

upvoted a paper about 1 month ago

Hymba: A Hybrid-head Architecture for Small Language Models

Paper • 2411.13676 • Published Nov 20 • 38

upvoted 2 papers about 2 months ago

ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference

Paper • 2410.21465 • Published Oct 28 • 11

COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training

Paper • 2410.19313 • Published Oct 25 • 19

upvoted 4 papers 3 months ago

PHI-S: Distribution Balancing for Label-Free Multi-Teacher Distillation

Paper • 2410.01680 • Published Oct 2 • 32

Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction

Paper • 2409.18124 • Published Sep 26 • 32

MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models

Paper • 2409.17481 • Published Sep 26 • 46

Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction

Paper • 2409.17422 • Published Sep 25 • 24

upvoted 3 collections 3 months ago

Llama 3.2

This collection hosts the transformers and original repos of the Llama 3.2 and Llama Guard 3 • 15 items • Updated 16 days ago • 546

MagpieLM

Aligning LMs with Fully Open Recipe (data+training configs+logs) • 9 items • Updated Sep 22 • 15

RADIO

A collection of Foundation Vision Models that combine multiple models (CLIP, DINOv2, SAM, etc.). • 6 items • Updated 3 days ago • 5

upvoted 2 collections 4 months ago

Qwen2-VL

Vision-language model series based on Qwen2 • 16 items • Updated 17 days ago • 180

VILA: On Pre-training for Visual Language Models

10 items • Updated Oct 31 • 47

upvoted a paper 4 months ago

Learning to Move Like Professional Counter-Strike Players

Paper • 2408.13934 • Published Aug 25 • 22

upvoted a collection 4 months ago

Nemotron in vLLM

Nemotron models that have been converted and/or quantized to work well in vLLM • 7 items • Updated Jul 25 • 1

upvoted a paper 4 months ago

Show-o: One Single Transformer to Unify Multimodal Understanding and Generation

Paper • 2408.12528 • Published Aug 22 • 50

upvoted a collection 4 months ago

To read... eventually

A collection of papers that i have read or plan to read all in one place. Includes a wide range of topics. • 137 items • Updated 3 days ago • 3