Parthiban Ravichandran's picture

Parthiban Ravichandran PRO

Parthiban97

·

https://parthiban-portfolio.vercel.app

AI & ML interests

Natural Language Processing, Computer Vision, Generative AI

Recent Activity

liked a Space 9 days ago

Qwen/Qwen-Image-Layered

liked a Space 12 days ago

ResembleAI/chatterbox-turbo-demo

upvoted a collection 13 days ago

View all activity

Organizations

upvoted 2 collections 13 days ago

sam-audio

11 items • Updated 13 days ago • 103

Molmo2

Artifacts for the Molmo2 release • 6 items • Updated 6 days ago • 28

upvoted a collection 14 days ago

NVIDIA Nemotron v3

Open, Production-ready Enterprise Models • 6 items • Updated 6 days ago • 106

upvoted a collection 19 days ago

PaCoRe

Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning • 3 items • Updated 20 days ago • 8

upvoted an article 24 days ago

Article

Tensor Parallelism (TP) in Transformers: 5 Minutes to Understand

26 days ago

•

63

upvoted a paper 24 days ago

Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length

Paper • 2512.04677 • Published 26 days ago • 167

upvoted an article 25 days ago

Article

We Got Claude to Fine-Tune an Open Source LLM

26 days ago

•

544

upvoted 2 collections about 1 month ago

SAM3

5 items • Updated Nov 19 • 105

DR Tulu

Models and data associated with DR Tulu, http://allenai-web/papers/drtulu • 5 items • Updated Nov 25 • 31

upvoted a paper about 2 months ago

MetaCLIP 2: A Worldwide Scaling Recipe

Paper • 2507.22062 • Published Jul 29 • 36

upvoted a collection about 2 months ago

MetaCLIP2 Multilingual

8 items • Updated Nov 12 • 16

upvoted 5 collections 3 months ago

ColModernVBERT

Resources for ColModernVBERT – the document retrieval–optimized variant of ModernVBERT • 5 items • Updated Oct 3 • 7

Sep 23 Releases

49 items • Updated Oct 1 • 4

Qwen3Guard

7 items • Updated Sep 30 • 58

Sep 16 Releases

39 items • Updated Sep 22 • 13

Qianfan-VL

Qianfan-vl model series. The models are mainly domain enhanced vision language model, targeting enterprise level multi modal understanding scenarios. • 4 items • Updated Sep 24 • 19

upvoted a paper 3 months ago

MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

Paper • 2509.16197 • Published Sep 19 • 56

upvoted a collection 3 months ago

Hunyuan-MT

4 items • Updated 5 days ago • 38

upvoted 2 collections 4 months ago

Sep 11 Releases

43 items • Updated Sep 15 • 3

Tiny Language Model Datasets

Collection of Synthetic Datasets that can be used in pretraining of any the Tiny Language Model • 14 items • Updated Sep 21 • 29