🔄 In a Training Loop

Julien BLANCHON PRO

blanchon

·

https://guybrush.ink/

AI & ML interests

None yet

Recent Activity

updated a Space about 2 hours ago

blanchon/multimodal-flow-demo

published a Space about 2 hours ago

blanchon/multimodal-flow-demo

liked a Space about 2 hours ago

blanchon/elf-reg-demo

View all activity

Organizations

upvoted 2 papers about 4 hours ago

Multimodal Flow: Unified Flow Modeling of Language and Vision in Embedding Spaces

Paper • 2609.40362 • Published 3 days ago • 14

SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation

Paper • 2610.00686 • Published 3 days ago • 4

upvoted an article about 6 hours ago

Article

Bringing Humanoids to LeRobot

nepyope

•

7 days ago

• 23

upvoted an article 1 day ago

Article

FLUX 3 Action: a world action model you can fine-tune

black-forest-labs

•

9 days ago

• 13

upvoted an article 2 days ago

Article

Open TTS Leaderboard: Scalable Evaluation for Multilingual Text-to-Speech and Voice Cloning

+2

bezzam, Steveeeeeeen, eustlb, mrfakename

•

3 days ago

• 36

upvoted a paper 3 days ago

TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining

Paper • 2609.33419 • Published 6 days ago • 18

upvoted 2 collections 4 days ago

UniMate

UniMate: One Unified Model to Animate Diverse Skeletons (SIGGRAPH Asia 2026). Paper & project page: https://linzhanmou.com/unimate/ • 7 items • Updated 5 days ago • 15

InternW0-Δ

The collection includes the pretrained and finetuned checkpoints of InternW0-Δ • 4 items • Updated 5 days ago • 4

upvoted an article 4 days ago

Article

YODAS v3: A 1 Million Hour Dataset for the Next Generation of Open Voice AI Research

espnet

•

5 days ago

• 30

upvoted a collection 6 days ago

Ming-Image (MLX)

Ming-Image-0.1 (MIT): design text-to-image with native RGBA + layer decomposition. Swift/MLX: github.com/xocialize/ming-image-swift • 6 items • Updated 5 days ago • 1

upvoted a paper 7 days ago

WISA: World Simulator Assistant for Physics-Aware Text-to-Video Generation

Paper • 2503.08153 • Published Mar 11, 2025 • 4

upvoted a collection 7 days ago

SmolDataEnvs

5.5K+ RL tasks for hill-climbing small models in code and data science. Deterministic grading, no LLM judge. • 10 items • Updated 1 day ago • 8

upvoted a paper 7 days ago

RoboChallenge: Large-scale Real-robot Evaluation of Embodied Policies

Paper • 2510.17950 • Published Oct 20, 2025 • 11

upvoted a collection 7 days ago

DDM Actions Artifacts

Canonical DDM Actions models and caches mapped to GitHub families. • 4 items • Updated 6 days ago • 1

upvoted a paper 8 days ago

Why Do Video Diffusion Models Violate Physics? Unveiling the Flaws in Attention Mechanisms

Paper • 2609.23658 • Published 13 days ago • 30

upvoted a changelog 8 days ago

Hugging Face Changelog

Preview LeRobot Episodes

8 days ago

• 58

upvoted an article 8 days ago

Article

Prediction preview images with modular diffusers

OzzyGT

•

8 days ago

• 2

upvoted a collection 9 days ago

FLUX 3 Action

Open weights 7B world action model: base and shared encoders, SO-101 and DROID policies. Code: https://github.com/black-forest-labs/flux-action • 3 items • Updated about 9 hours ago • 41

upvoted a collection 11 days ago

MiMo-V2.6

5 items • Updated 6 days ago • 124

upvoted an article 11 days ago

Article

tokenizers v1: encode, decode and scaling, measured

+2

ArthurZ, sbrandeis, mcpotato, lysandre

•

12 days ago

• 86