dondosss (Maxim Kurkin)

upvoted 2 articles 4 days ago

Article

PaliGemma – Google's Cutting-Edge Open Vision Language Model

6 days ago

• 95

Article

License to Call: Introducing Transformers Agents 2.0

7 days ago

• 63

upvoted a collection 24 days ago

Models - Multimodal

Collection

15 items • Updated Apr 17 • 2

upvoted a paper 24 days ago

M2-CLIP: A Multimodal, Multi-task Adapting Framework for Video Action Recognition

Paper • 2401.11649 • Published Jan 22 • 3

upvoted a paper about 1 month ago

MoA: Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation

Paper • 2404.11565 • Published Apr 17 • 12

upvoted an article about 1 month ago

Article

Introducing Idefics2: A Powerful 8B Vision-Language Model for the community

Apr 15

• 126

upvoted a collection about 1 month ago

SigLIP

Collection

Contrastive (sigmoid) image-text models from https://arxiv.org/abs/2303.15343 • 8 items • Updated 5 days ago • 24

upvoted 3 papers about 1 month ago

Learn Your Reference Model for Real Good Alignment

Paper • 2404.09656 • Published Apr 15 • 79

InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD

Paper • 2404.06512 • Published Apr 9 • 29

OmniFusion Technical Report

Paper • 2404.06212 • Published Apr 9 • 73

upvoted 3 papers 4 months ago

upvoted a collection 4 months ago

vikhr

Collection

A family of russian translated LLM • 4 items • Updated Jan 8 • 14

upvoted a paper 5 months ago

DocLLM: A layout-aware generative language model for multimodal document understanding

Paper • 2401.00908 • Published Dec 31, 2023 • 173

upvoted a paper 6 months ago

FusionFrames: Efficient Architectural Aspects for Text-to-Video Generation Pipeline

Paper • 2311.13073 • Published Nov 22, 2023 • 53

Maxim Kurkin

AI & ML interests

Organizations

dondosss's activity

PaliGemma – Google's Cutting-Edge Open Vision Language Model

License to Call: Introducing Transformers Agents 2.0

Models - Multimodal

M2-CLIP: A Multimodal, Multi-task Adapting Framework for Video Action Recognition

MoA: Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation

Introducing Idefics2: A Powerful 8B Vision-Language Model for the community

SigLIP

Learn Your Reference Model for Real Good Alignment

InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD

OmniFusion Technical Report

MoE-LLaVA: Mixture of Experts for Large Vision-Language Models

MM-LLMs: Recent Advances in MultiModal Large Language Models

Mamba: Linear-Time Sequence Modeling with Selective State Spaces

vikhr

DocLLM: A layout-aware generative language model for multimodal document understanding

FusionFrames: Efficient Architectural Aspects for Text-to-Video Generation Pipeline