Aritra Roy Gosthipaty's picture

Aritra Roy Gosthipaty PRO

ariG23498

·

https://arig23498.github.io/

AI & ML interests

Deep Representation Learning

Recent Activity

liked a Space 4 days ago

lvwerra/distill-blog-template

upvoted a collection 4 days ago

updated a model 5 days ago

ariG23498/layerskip-Llama-3.2-3B-top_v2

View all activity

Organizations

ariG23498's activity

upvoted a collection 4 days ago

Florence

9 items • Updated Jan 8 • 165

upvoted an article 6 days ago

Article

NVIDIA's GTC 2025 Announcement for Physical AI Developers: New Open Models and Datasets

7 days ago

• 29

upvoted an article 12 days ago

Article

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

13 days ago

• 342

upvoted 2 collections 12 days ago

Gemma 3

4 items • Updated 12 days ago • 15

Gemma 3 Release

9 items • Updated 11 days ago • 290

upvoted a collection 18 days ago

Shot categorizer

Fine-tune of Florence-2 to generate shot categories, useful for data curation. Code: https://github.com/huggingface/movie-shot-categorizer. • 3 items • Updated 18 days ago • 2

upvoted a collection 20 days ago

C4AI Aya Vision

Aya Vision is a state-of-the-art family of vision models that brings multimodal capabilities to 23 languages. • 5 items • Updated 20 days ago • 68

upvoted an article 20 days ago

Article

A Deepdive into Aya Vision: Advancing the Frontier of Multilingual Multimodality

21 days ago

• 69

upvoted 2 articles 25 days ago

Article

SigLIP 2: A better multilingual vision language encoder

Feb 21

• 143

Article

HuggingFace, IISc partner to supercharge model building on India's diverse languages

26 days ago

• 17

upvoted a paper 26 days ago

Phi-4 Technical Report

Paper • 2412.08905 • Published Dec 12, 2024 • 111

upvoted a collection 26 days ago

Phi-4

Phi-4 family of small language and multi-modal models. • 7 items • Updated 21 days ago • 110

upvoted an article 28 days ago

Article

Remote VAEs for decoding with HF endpoints 🤗

29 days ago

• 37

upvoted 2 collections about 1 month ago

SigLIP 2

OpenCLIP and timm SigLIP 2 models • 45 items • Updated about 1 month ago • 14

SigLIP2

36 items • Updated 12 days ago • 65

upvoted a paper about 1 month ago

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Paper • 2502.14786 • Published Feb 20 • 133

upvoted 2 articles about 1 month ago

Article

SmolVLM2: Bringing Video Understanding to Every Device

Feb 20

• 214

Article

PaliGemma 2 Mix - New Instruction Vision Language Models by Google

Feb 19

• 65