Prithiv Sakthi's picture

Prithiv Sakthi

prithivMLmods

·

https://huggingface.co./strangerzonehf

AI & ML interests

computer vision, realism engine, adapters

Recent Activity

reacted to AdinaY's post with 🚀 about 3 hours ago

QvQ-72B-Preview🎄 an open weight model for visual reasoning just released by Alibaba_Qwen team https://huggingface.co./collections/Qwen/qvq-676448c820912236342b9888 ✨ Combines visual understanding & language reasoning. ✨ Scores 70.3 on MMMU ✨ Outperforms Qwen2-VL-72B-Instruct in complex problem-solving

liked a dataset about 7 hours ago

gayanin/pubmed-gastro-maskfilling

liked a model about 10 hours ago

answerdotai/ModernBERT-base

View all activity

Articles

GRID-6X : Layout for Seamless Image Assembly

Flux1.1 [pro] Ultra : Endpoint by BFL ⛵

Create Dynamic Typed Videos with 'Type Byte🐧'

Unlocking Creativity with Text-to-Image Generation: Exploring LoRA Models and Styles [Generative Vision]

Organizations

prithivMLmods's activity

upvoted a paper about 16 hours ago

Qwen2.5 Technical Report

Paper • 2412.15115 • Published 6 days ago • 327

upvoted an article 1 day ago

Article

Deriving DPO's Loss

By

•

1 day ago

• 15

upvoted a collection 3 days ago

VisionLM

561 items • Updated 5 days ago • 39

upvoted a paper 4 days ago

Bilateral Reference for High-Resolution Dichotomous Image Segmentation

Paper • 2401.03407 • Published Jan 7 • 2

upvoted a collection 6 days ago

📐 FineMath

FineMath datasets and ablation models • 13 items • Updated 3 days ago • 11

upvoted a collection 7 days ago

Vision Language Models

Grounding, chat • 4 items • Updated 6 days ago • 10

upvoted an article 8 days ago

Article

🇪🇺✍️ EU AI Act: Systemic Risks in the First CoP Draft Comments ✍️🇪🇺

By

•

13 days ago

• 11

upvoted a collection 10 days ago

EXAONE-3.5

EXAONE 3.5 language model series including instruction-tuned models of 2.4B, 7.8B, and 32B. • 10 items • Updated 16 days ago • 80

upvoted 3 articles 12 days ago

Article

Releasing QwQ-LongCoT-130K

By

•

20 days ago

• 8

Article

Building an AI-powered search engine from scratch

By

•

14 days ago

• 8

Article

MotionLCM-V2: Improved Compression Rate for Multi-Latent-Token Diffusion

By

•

14 days ago

• 12

upvoted 2 collections 12 days ago

Sketch Fav

Art & Culture in 3:1 • 8 items • Updated 4 days ago • 8

Automotive 3D

4w's & 2w's • 2 items • Updated 12 days ago • 6

upvoted an article 14 days ago

Article

Power steering: Squeeze massive power from small LLMs

By

•

16 days ago

• 4

upvoted a collection 14 days ago

Christmas Pack

Pack Made for Xmas [ 3D, NFT's, Sketch, Etc,.. ] • 6 items • Updated 7 days ago • 10

upvoted 4 papers 18 days ago

MV-Adapter: Multi-view Consistent Image Generation Made Easy

Paper • 2412.03632 • Published 21 days ago • 21

Negative Token Merging: Image-based Adversarial Feature Guidance

Paper • 2412.01339 • Published 23 days ago • 21

VisionZip: Longer is Better but Not Necessary in Vision Language Models

Paper • 2412.04467 • Published 20 days ago • 104

Structured 3D Latents for Scalable and Versatile 3D Generation

Paper • 2412.01506 • Published 23 days ago • 46

upvoted a collection 19 days ago

Llama 3.3 (All Versions)

Meta's new Llama 3.3 (70B) model in all formats. Includes GGUF, 4-bit bnb and original versions. • 3 items • Updated about 20 hours ago • 27