Sylvain Filoni's picture

Sylvain Filoni PRO

fffiloni

·

AI & ML interests

ML for Animation • Alumni Arts Déco Paris • PSL

Recent Activity

updated a Space about 10 hours ago

fffiloni/Gaze-LLE

updated a Space about 10 hours ago

fffiloni/text2any-batch-hf-jobs-orchestration

updated a Space about 10 hours ago

fffiloni/text-guided-image-colorization

View all activity

Organizations

updated 3 Spaces about 10 hours ago

Gaze LLE

Gaze Target Estimation

Text2Any Batch with HF Jobs Orchestration

Run and monitor Hugging Face model jobs

Text Guided Image Colorization

Colorize grayscale images with AI-driven caption guidance

updated a Space about 11 hours ago

DALL·E mini JAX Docker

Generate images from text prompts with customizable settings

updated a Space about 19 hours ago

NVILA HD Video + AutoGaze

Long video understanding with smart attention

updated a collection about 20 hours ago

Rebuilt AI Research Demos

Research demos rebuilt for clarity, exploration, and better understanding of AI models. • 2 items • Updated about 20 hours ago

liked a Space 2 days ago

Cohere Multilingual ASR

Transcribe audio clips to text in many languages

upvoted 3 papers 2 days ago

The Pulse of Motion: Measuring Physical Frame Rate from Visual Dynamics

Paper • 2603.14375 • Published 14 days ago • 16

RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models

Paper • 2603.25502 • Published 3 days ago • 46

Voxtral TTS

Paper • 2603.25551 • Published 3 days ago • 40

liked a Space 2 days ago

Voxtral TTS Demo

Generate realistic speech from text and custom voice

liked a model 2 days ago

mistralai/Voxtral-4B-TTS-2603

Text-to-Speech • Updated 2 days ago • 2.45k • 447

updated a collection 2 days ago

My Spaces running on ZeroGPU

32 items • Updated 2 days ago • 1

New activity in fffiloni/NVILA-HD-Video-AutoGaze 3 days ago

Apply for a GPU community grant: Academic project

#1 opened 3 days ago by

published a Space 3 days ago

NVILA HD Video + AutoGaze

Long video understanding with smart attention

upvoted a paper 3 days ago

One View Is Enough! Monocular Training for In-the-Wild Novel View Generation

Paper • 2603.23488 • Published 5 days ago • 4

liked a Space 3 days ago

AutoGaze

Generate gaze pattern and reconstruction videos from any video

upvoted 2 papers 3 days ago

Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing

Paper • 2603.12254 • Published 17 days ago • 21

2Xplat: Two Experts Are Better Than One Generalist

Paper • 2603.21064 • Published 8 days ago • 25

updated a Space 4 days ago

Space Credential & Dependency Risk Scanner

Scan Spaces for supply chain & credential risks