20 39 23

Pavlo Molchanov PRO

pmolchanov

https://www.pmolchanov.com

AI & ML interests

Efficiency in Multi-Modal LLMs

Recent Activity

upvoted an article 1 day ago

Bamba: Inference-Efficient Hybrid Mamba2 Model

upvoted an article 1 day ago

Finally, a Replacement for BERT: Introducing ModernBERT

upvoted a paper 5 days ago

SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer

View all activity

Organizations

pmolchanov's activity

upvoted 2 articles 1 day ago

Article

Bamba: Inference-Efficient Hybrid Mamba2 Model

Dec 18, 2024

• 43

Article

Finally, a Replacement for BERT: Introducing ModernBERT

Dec 19, 2024

• 525

upvoted a paper 5 days ago

SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer

Paper • 2501.18427 • Published 6 days ago • 15

upvoted a collection 29 days ago

Cosmos

Collection

The collection of Cosmos models • 31 items • Updated 20 days ago • 254

upvoted 2 papers 2 months ago

NVILA: Efficient Frontier Visual Language Models

Paper • 2412.04468 • Published Dec 5, 2024 • 57

Cautious Optimizers: Improving Training with One Line of Code

Paper • 2411.16085 • Published Nov 25, 2024 • 15

upvoted a collection 2 months ago

Hymba

Collection

A series of Hybrid Small Language Models. • 2 items • Updated 20 days ago • 27

upvoted a paper 2 months ago

Star Attention: Efficient LLM Inference over Long Sequences

Paper • 2411.17116 • Published Nov 26, 2024 • 49

upvoted 3 papers 3 months ago

Hymba: A Hybrid-head Architecture for Small Language Models

Paper • 2411.13676 • Published Nov 20, 2024 • 41

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

Paper • 2410.21465 • Published Oct 28, 2024 • 11

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

Paper • 2410.19313 • Published Oct 25, 2024 • 19

upvoted 4 papers 4 months ago

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

Paper • 2410.01680 • Published Oct 2, 2024 • 33

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

Paper • 2409.18124 • Published Sep 26, 2024 • 32

MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models

Paper • 2409.17481 • Published Sep 26, 2024 • 47

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

Paper • 2409.17422 • Published Sep 25, 2024 • 25

upvoted a collection 4 months ago

Llama 3.2

Collection

This collection hosts the transformers and original repos of the Llama 3.2 and Llama Guard 3 • 15 items • Updated Dec 6, 2024 • 566

upvoted 4 collections 5 months ago