Andres Marafioti

andito

·

AI & ML interests

Multimodal models, VLM and TTS

Recent Activity

updated a bucket about 9 hours ago

smolagents/dev-s2s-dashboard

updated a bucket about 9 hours ago

smolagents/demo-s2s-dashboard

upvoted an article about 15 hours ago

Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident

View all activity

Organizations

liked a model 7 days ago

moonshotai/Kimi-K3

Image-Text-to-Text • 2.8T • Updated 2 days ago • 99.2k • • 8.63k

liked a model 9 days ago

thinkingmachines/Inkling

Image-Text-to-Text • 952B • Updated 6 days ago • 39.1k • • 1.64k

liked a Space 13 days ago

MOSS Transcribe Diarize

Transcribe audio/video with speaker diarization

liked a model 13 days ago

OpenMOSS-Team/MOSS-Transcribe-Diarize

Audio-Text-to-Text • 0.9B • Updated 6 days ago • 163k • 344

liked a Space 13 days ago

Agent Manager

Private cloud manager for AI coding CLI sessions

liked a Space 20 days ago

An Open Realtime Voice You Can Actually Run Yourself

Generate real‑time spoken AI conversations

liked a dataset 21 days ago

allenai/pixmo-cap

Viewer • Updated Nov 27, 2024 • 717k • 633 • 47

liked a Space 26 days ago

Gemma Avatar

Talk to Gemma 4 face to face, with a 3D lip-synced avatar

liked a Space 28 days ago

HF Realtime Voice

Voice chat over WebSocket against a HF speech-to-speech

liked 4 Spaces about 1 month ago

CUGA Apps

2 dozen real-life agents optimized for open models & stack

Minimal Conversation (S2S backend, WebSocket)

Voice chat over WebSocket against a HF speech-to-speech

Encoder-Free VLM

Train Your Own Encoder-Free VLM in $100

Encoder-Free VLM (DenseFusion-1M + ShareGPT4V)

Encoder-free VLM (Qwen3-1.7B) on DenseFusion-1M + ShareGPT4V

liked a Space about 2 months ago

PEEK Frame Selector

Query-free frame selection + captioning for video

liked a model 2 months ago

Serveurperso/Qwen3-TTS-GGUF

Text-to-Speech • 0.9B • Updated May 11 • 89k • 29

liked 2 Spaces 2 months ago

Supertonic 3 (TTS)

Lightning-Fast, On-Device, Multilingual, Accurate TTS

Supertonic 2 (TTS)

Lightning-Fast, On-Device, Multilingual TTS

liked 2 Spaces 3 months ago

Hutter Prize Dashboard

Dashboard for the Hutter Prize (100MB) collab

Robotics research should think (and do) more about sustainability!

Explore robotics papers mapped to UN Sustainable Development Goals

liked a model 3 months ago

facebook/sapiens2

Updated May 15 • 156