Aritra Roy Gosthipaty's picture

Aritra Roy Gosthipaty PRO

ariG23498

·

https://arig23498.github.io/

AI & ML interests

Deep Representation Learning

Recent Activity

updated a dataset about 3 hours ago

model-metadata/trending_models

updated a dataset 1 day ago

ariG23498/UCF-101

published a dataset 1 day ago

ariG23498/UCF-101

View all activity

Organizations

ariG23498's activity

upvoted a changelog 2 days ago

Changelog

New Model Filtering Options on the Hub

3 days ago

• 46

upvoted an article 8 days ago

Article

🦸🏻#14: What Is MCP, and Why Is Everyone – Suddenly!– Talking About It?

By

•

Mar 17

• 291

upvoted 2 collections 8 days ago

Test-Time-Registers

A collection of models augmented with test-time registers, a training-free way to add register tokens to pretrained models. • 2 items • Updated 9 days ago • 3

V-JEPA 2

A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of https://ai.meta.com/blog/v-jepa-yann • 8 items • Updated 6 days ago • 116

upvoted a collection 10 days ago

LayerSkip

Models continually pretrained using LayerSkip - https://arxiv.org/abs/2404.16710 • 8 items • Updated Nov 21, 2024 • 48

upvoted a collection 13 days ago

Qwen3-Embedding

6 items • Updated 14 days ago • 92

upvoted an article 15 days ago

Article

KV Cache from scratch in nanoVLM

By

and 4 others •

15 days ago

• 71

upvoted a paper 15 days ago

FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation

Paper • 2506.01144 • Published 18 days ago • 14

upvoted an article 15 days ago

Article

SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data

By

and 8 others •

16 days ago

• 147

upvoted a paper 16 days ago

SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics

Paper • 2506.01844 • Published 17 days ago • 96

upvoted 2 changelogs 24 days ago

Changelog

Xet is now the default storage option for new users and organizations

27 days ago

• 66

Changelog

Static Spaces can now have a build step

27 days ago

• 105

upvoted an article 24 days ago

Article

🐯 Liger GRPO meets TRL

By

and 5 others •

25 days ago

• 42

upvoted 3 articles 29 days ago

Article

The Transformers Library: standardizing model definitions

By

and 3 others •

May 15

• 114

Article

nanoVLM: The simplest repository to train your VLM in pure PyTorch

By

and 6 others •

29 days ago

• 157

Article

Microsoft and Hugging Face expand collaboration

By

and 2 others •

May 19

• 22

upvoted a collection about 1 month ago

MobileCLIP Models + DataCompDR Data

MobileCLIP: Mobile-friendly image-text models with SOTA zero-shot capabilities. DataCompDR: Improved datasets for training image-text SOTA models. • 22 items • Updated Oct 4, 2024 • 29

upvoted 2 articles about 1 month ago

Article

Improving Hugging Face Model Access for Kaggle Users

By

and 4 others •

May 14

• 29

Article

Vision Language Models (Better, Faster, Stronger)

By

and 4 others •

May 12

• 444

upvoted a paper about 1 month ago

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

Paper • 2401.15947 • Published Jan 29, 2024 • 54