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 2 hours ago

model-metadata/custom_code_execution_files

updated a dataset about 2 hours ago

model-metadata/custom_code_execution_files

updated a dataset about 2 hours ago

model-metadata/custom_code_execution_files

View all activity

Organizations

upvoted an article about 5 hours ago

Article

Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders

By

and 1 other •

about 15 hours ago

• 184

upvoted a collection about 22 hours ago

🧠 SmolLM3

Smol, multilingual, long-context reasoner • 9 items • Updated about 6 hours ago • 39

upvoted 2 articles about 23 hours ago

Article

Efficient MultiModal Data Pipeline

By

and 4 others •

1 day ago

• 35

Article

SmolLM3: smol, multilingual, long-context reasoner

By

and 22 others •

1 day ago

• 364

upvoted an article 1 day ago

Article

cocogold: training Marigold for text-grounded segmentation

By

•

1 day ago

• 20

upvoted an article 13 days ago

Article

Gemma 3n fully available in the open-source ecosystem!

By

and 7 others •

14 days ago

• 105

upvoted a collection 13 days ago

Gemma 3n

4 items • Updated about 1 hour ago • 163

upvoted an article 19 days ago

Article

(LoRA) Fine-Tuning FLUX.1-dev on Consumer Hardware

By

and 4 others •

21 days ago

• 73

upvoted a changelog 22 days ago

Changelog

New Model Filtering Options on the Hub

23 days ago

• 63

upvoted an article 28 days ago

Article

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

By

•

Mar 17

• 308

upvoted 2 collections 28 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. • 3 items • Updated 17 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 26 days ago • 144

upvoted 2 collections about 1 month ago

LayerSkip

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

Qwen3-Embedding

6 items • Updated Jun 5 • 100

upvoted an article about 1 month ago

Article

KV Cache from scratch in nanoVLM

By

and 4 others •

Jun 4

• 83

upvoted a paper about 1 month ago

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

Paper • 2506.01144 • Published Jun 1 • 14

upvoted an article about 1 month ago

Article

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

By

and 8 others •

Jun 3

• 185

upvoted a paper about 1 month ago

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

Paper • 2506.01844 • Published Jun 2 • 111

upvoted 2 changelogs about 1 month ago

Changelog

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

May 23

• 66

Changelog

Static Spaces can now have a build step

May 23

• 105