Razvan's picture

Razvan

razvanab

·

AI & ML interests

None yet

Recent Activity

liked a Space about 13 hours ago

rednote-hilab/dots-demo

liked a model about 19 hours ago

lightonai/Reason-ModernColBERT

liked a model 2 days ago

tencent/HunyuanVideo-Avatar

View all activity

Organizations

razvanab's activity

upvoted a collection 10 days ago

Wan2.1 14B 480p I2V LoRAs

A collection of Remade's Wan2.1 14B 480p I2V LoRAs • 49 items • Updated 15 days ago • 167

upvoted a paper 11 days ago

Rendering-Aware Reinforcement Learning for Vector Graphics Generation

Paper • 2505.20793 • Published 12 days ago • 11

upvoted a paper 18 days ago

VACE: All-in-One Video Creation and Editing

Paper • 2503.07598 • Published Mar 10 • 51

upvoted a collection 25 days ago

Voila

Voila: Voice-Language Foundation Models. https://voila.maitrix.org • 7 items • Updated May 6 • 23

upvoted a collection about 1 month ago

Qwen3-abliterated

12 items • Updated 2 days ago • 20

upvoted a collection about 2 months ago

Wan2.1 14B T2V LoRAs

A collection of Remade's Wan2.1 14B T2V LoRAs • 20 items • Updated Mar 27 • 25

upvoted a paper 2 months ago

Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation

Paper • 2504.02542 • Published Apr 3 • 45

upvoted 2 collections 2 months ago

Gemma 3 QAT

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 15 items • Updated 9 days ago • 195

xLAM-2

A family of Large Action Model for multi-turn conversation and tool-use • 10 items • Updated May 5 • 16

upvoted 3 collections 3 months ago

💫StarVector Models

StarVector is a multimodal LLM for Scalable Vector Graphics (SVG) generation, producing structured SVG code directly from images and text. • 2 items • Updated Mar 20 • 96

BD3-LMs

https://m-arriola.com/bd3lms/ • 4 items • Updated Apr 12 • 23

Babel

Open Multilingual Large Language Models Serving Over 90% of Global Speakers • 5 items • Updated Apr 15 • 17

upvoted an article 4 months ago

Article

SigLIP 2: A better multilingual vision language encoder

By

and 2 others •

Feb 21

• 165

upvoted 7 collections 5 months ago

PixArt-Alpha

This collection organize all the PixArt-Alpha related models, datasets and so on. • 9 items • Updated May 4, 2024 • 4

OS-Genesis

11 items • Updated Jan 6 • 6

ViTPose

Collection for ViTPose models based on transformers implementation. • 10 items • Updated Jan 12 • 15

LLMs [UNCENSORED]

7 items • Updated May 16, 2024 • 8

🪐 SmolLM

A series of smol LLMs: 135M, 360M and 1.7B. We release base and Instruct models as well as the training corpus and some WebGPU demos • 12 items • Updated May 5 • 227

Human-Like LLMs

Human-Like LLMs series. • 5 items • Updated Jan 20 • 13

Cosmos

The collection of Cosmos models • 31 items • Updated 2 days ago • 291