Prithiv Sakthi

7.4K posts

Prithiv Sakthi banner
Prithiv Sakthi

Prithiv Sakthi

@prithivMLmods

Computer Vision • Multimodal AI • @huggingface Fellow ML🤗 • Computational Intelligence • Diffusion-Driven Adapters • https://t.co/CZfzd6KVRA

India Katılım Ekim 2022
765 Takip Edilen524 Takipçiler
Sabitlenmiş Tweet
Prithiv Sakthi
Prithiv Sakthi@prithivMLmods·
Introducing QIE-Bbox-Studio! 🔥🤗 The QIE-Bbox-Studio demo is now live: more precise and packed with powerful new features. You can manipulate images with ease: remove objects, add designs, and even move elements from one place to another, all in a fast 4-step inference process.
Prithiv Sakthi tweet mediaPrithiv Sakthi tweet mediaPrithiv Sakthi tweet media
English
1
1
1
266
Prithiv Sakthi
Prithiv Sakthi@prithivMLmods·
Map-Anything v1 (Universal Feed-Forward Metric 3D Reconstruction) demo is now available on Hugging Face Spaces. Built with @Gradio and integrated with @rerundotio , it performs multi-image and video-based 3D reconstruction, depth, normal map, and interactive measurements.
English
1
17
93
5.1K
Ellie Sleightholm
Ellie Sleightholm@elsleightholm·
My mathematics channel just reached 200k on Instagram 🥹
Ellie Sleightholm tweet media
English
77
135
4K
54.7K
merve
merve@mervenoyann·
AI2 released new family of vision LMs for pointing (SOTA!) 🔥 > MolmoPoint-8B (general use) > MolmoPoint-GUI-8B (graphical computer use) > MolmoPoint-Vid-4B (counting/tracking in videos) also with their datasets 🥵
Ai2@allen_ai

Grounding lets vision-language models do more than describe—they can point to where a robot should grasp, which button to click, or which object to track across video frames. Today we're releasing MolmoPoint, a better way for models to point. 🧵

English
6
11
84
9.4K
Prithiv Sakthi retweetledi
elie
elie@eliebakouch·
new 1T+ parameter model from @XiaomiMiMo, support 1M context length thanks to 7:1 hybrid sliding window attention!!
elie tweet media
English
3
6
89
8.4K
Prithiv Sakthi
Prithiv Sakthi@prithivMLmods·
Introducing QIE-Bbox-Studio! 🔥🤗 The QIE-Bbox-Studio demo is now live: more precise and packed with powerful new features. You can manipulate images with ease: remove objects, add designs, and even move elements from one place to another, all in a fast 4-step inference process.
Prithiv Sakthi tweet mediaPrithiv Sakthi tweet mediaPrithiv Sakthi tweet media
English
1
1
1
266
Prithiv Sakthi retweetledi
Niels Rogge
Niels Rogge@NielsRogge·
Introducing the Paper Pages skill! Simply paste this SKILL.md, so your coding agent knows how to work with @huggingface papers Ask it to summarize papers, search papers, or list linked models or datasets
English
6
29
162
15.9K