Prithiv Sakthi's picture

Building on HF

Prithiv Sakthi PRO

prithivMLmods

hugging-science

·

https://linktr.ee/prithivsakthi

AI & ML interests

computer vision, nlp, multimodality - HuggingFace Fellow🤗

Recent Activity

upvoted an article about 10 hours ago

AI evals are becoming the new compute bottleneck

upvoted an article about 11 hours ago

Pallas for people who know JAX but not kernels yet

liked a model about 11 hours ago

prithivMLmods/Q3.5-27B-Opus-DA

View all activity

Organizations

upvoted an article about 10 hours ago

Article

AI evals are becoming the new compute bottleneck

3 days ago

•

17

upvoted an article about 11 hours ago

Article

Pallas for people who know JAX but not kernels yet

4 days ago

•

17

upvoted a paper 1 day ago

Efficient Training on Multiple Consumer GPUs with RoundPipe

Paper • 2604.27085 • Published 4 days ago • 30

upvoted a collection 1 day ago

CapQwen3.6 - Caption Qwen3.6 Distilled (exp)

Collection of Qwen3.6 Captioning Expert System Models (+abliteration ) • 4 items • Updated about 13 hours ago • 1

upvoted 2 papers 1 day ago

ExoActor: Exocentric Video Generation as Generalizable Interactive Humanoid Control

Paper • 2604.27711 • Published 3 days ago • 35

Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling

Paper • 2604.28185 • Published 3 days ago • 78

upvoted a collection 4 days ago

Q3.5-Opus-DA

Collection of Opus-Reasoning-Distilled abliteration variants of Qwen3.5 • 4 items • Updated about 16 hours ago • 2

upvoted a collection 5 days ago

Auto-Aggressive (Uncensored Qwen 3.6 Native Multimodal)

Collection of Uncensored Variants of Qwen3.6 Native Multimodal Models • 4 items • Updated 5 days ago • 3

upvoted a collection 7 days ago

Sapiens2

26 items • Updated 8 days ago • 19

upvoted a paper 9 days ago

WorldMark: A Unified Benchmark Suite for Interactive Video World Models

Paper • 2604.21686 • Published 10 days ago • 36

upvoted 2 collections 9 days ago

Garnet OCR

Collection of Garnet OCR Models • 4 items • Updated 4 days ago • 1

DeepSeek-V4

4 items • Updated 9 days ago • 602

upvoted 2 collections 11 days ago

Qwen3.6-27B Compressions

Collection of various compressed versions of the Qwen3.6-27B native multimodal model. • 7 items • Updated 6 days ago • 2

WildDet3D

This is the collection of WildDet3D artifacts, including demos, model checkpoints and data. https://github.com/allenai/WildDet3D • 8 items • Updated 20 days ago • 17

upvoted an article 12 days ago

Article

Building a Fast Multilingual OCR Model with Synthetic Data

15 days ago

•

31

upvoted 2 papers 13 days ago

KV Packet: Recomputation-Free Context-Independent KV Caching for LLMs

Paper • 2604.13226 • Published 19 days ago • 10

HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System

Paper • 2604.14125 • Published 18 days ago • 20

upvoted a changelog 14 days ago

Hugging Face Changelog

Spaces agents.md for your coding agents

16 days ago

• 204

upvoted a collection 15 days ago

Qwen3.6-35B-A3B Compressions

Collection of various compressed versions of the Qwen3.6-35B-A3B native multimodal model. • 4 items • Updated 6 days ago • 2

upvoted a paper 15 days ago

GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens

Paper • 2604.15284 • Published 17 days ago • 24