Evgenii Pishchik's picture

Evgenii Pishchik

epishchik

·

AI & ML interests

None yet

Recent Activity

upvoted a collection 1 day ago

Qwen3-Embedding

liked a model 3 days ago

JuliaWolkenstein/MeLlamo_Llama_3_8B

upvoted a paper about 2 months ago

TULIP: Towards Unified Language-Image Pretraining

View all activity

Organizations

None yet

epishchik's activity

upvoted a collection 1 day ago

Qwen3-Embedding

6 items • Updated 1 day ago • 56

upvoted a paper about 2 months ago

TULIP: Towards Unified Language-Image Pretraining

Paper • 2503.15485 • Published Mar 19 • 49

upvoted 2 collections about 2 months ago

Perception Encoder

9 items • Updated Apr 17 • 60

blt

4 items • Updated Apr 17 • 23

upvoted a collection 2 months ago

Llama 4

Llama 4 release • 13 items • Updated Apr 29 • 522

upvoted 4 collections 3 months ago

GemmaX2

GemmaX2 language models, including pretrained and instruction-tuned models of 2 sizes, including 2B, 9B. • 7 items • Updated Feb 7 • 22

Gemma 3 Release

24 items • Updated 8 days ago • 380

LLaVA-Video

Models focus on video understanding (previously known as LLaVA-NeXT-Video). • 8 items • Updated Feb 21 • 61

SigLIP2

36 items • Updated 8 days ago • 74

upvoted an article 4 months ago

Article

Model2Vec: Distill a Small Fast Model from any Sentence Transformer

By

and 1 other •

Oct 14, 2024

• 91

upvoted a collection 4 months ago

Qwen2.5-VL

Vision-language model series based on Qwen2.5 • 11 items • Updated Apr 28 • 484

upvoted a collection 5 months ago

Multimodal Models

Multimodal models with leading performance. • 17 items • Updated Jan 17 • 35

upvoted 5 collections 6 months ago

Molmo

Artifacts for open multimodal language models. • 5 items • Updated Apr 30 • 305

KaLM-embedding

11 items • Updated Mar 11 • 24

SAGE v1.0.0 release

5 items • Updated Mar 26 • 1

SAGE v1.1.0 release

4 items • Updated Mar 26 • 6

AIMv2

A collection of AIMv2 vision encoders that supports a number of resolutions, native resolution, and a distilled checkpoint. • 19 items • Updated Nov 22, 2024 • 77

upvoted a paper 8 months ago

Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models

Paper • 2409.17146 • Published Sep 25, 2024 • 115

upvoted a collection 8 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 Dec 6, 2024 • 610

upvoted a collection 9 months ago

LLaVa-1.5

LLaVa-1.5 is a series of vision-language models (VLMs) trained on a variety of visual instruction datasets. • 3 items • Updated Mar 18, 2024 • 8