Sylvain Filoni PRO

fffiloni's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a changelog about 20 hours ago

view changelog

Hugging Face Changelog

Repositories Usage Overview in Settings

about 21 hours ago

• 24

upvoted 5 papers 2 days ago

TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning

Paper • 2603.12529 • Published 6 days ago • 18

Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models

Paper • 2603.15557 • Published 3 days ago • 26

Mixture-of-Depths Attention

Paper • 2603.15619 • Published 3 days ago • 68

Attention Residuals

Paper • 2603.15031 • Published 3 days ago • 103

OmniForcing: Unleashing Real-time Joint Audio-Visual Generation

Paper • 2603.11647 • Published 7 days ago • 30

upvoted a paper 7 days ago

TADA: A Generative Framework for Speech Modeling via Text-Acoustic Dual Alignment

Paper • 2602.23068 • Published 21 days ago • 7

upvoted a collection 8 days ago

TADA

Collection

TADA: A Generative Framework for Speech Modeling via Text-Acoustic Dual Alignment | https://huggingface.co/papers/2602.23068 • 5 items • Updated 8 days ago • 66

upvoted 10 papers 8 days ago

Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance

Paper • 2603.02175 • Published 17 days ago • 22

Utonia: Toward One Encoder for All Point Clouds

Paper • 2603.03283 • Published 16 days ago • 181

MIBURI: Towards Expressive Interactive Gesture Synthesis

Paper • 2603.03282 • Published 16 days ago • 4

Helios: Real Real-Time Long Video Generation Model

Paper • 2603.04379 • Published 15 days ago • 170

RealWonder: Real-Time Physical Action-Conditioned Video Generation

Paper • 2603.05449 • Published 14 days ago • 12

EffectMaker: Unifying Reasoning and Generation for Customized Visual Effect Creation

Paper • 2603.06014 • Published 13 days ago • 9

WildActor: Unconstrained Identity-Preserving Video Generation

Paper • 2603.00586 • Published 19 days ago • 37

HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising

Paper • 2603.08703 • Published 10 days ago • 31

CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editing

Paper • 2603.08589 • Published 10 days ago • 38

LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory

Paper • 2603.03269 • Published 16 days ago • 60

upvoted 2 papers 27 days ago

MIND: Benchmarking Memory Consistency and Action Control in World Models

Paper • 2602.08025 • Published Feb 8 • 12

Stroke of Surprise: Progressive Semantic Illusions in Vector Sketching

Paper • 2602.12280 • Published Feb 12 • 32