Julien BLANCHON PRO

blanchon's activity

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

upvoted an article about 19 hours ago

view article

Article

Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps

• 
• 
• +1

iamleonie, burtenshaw, sergiopaniego

•

2 days ago

• 47

upvoted an article 2 days ago

view article

Article

Training a coding model to paint watercolours with TRL and OpenEnv

• 

sergiopaniego

•

2 days ago

• 45

upvoted 5 papers 4 days ago

Video Generative Models as Geometry Learner

Paper • 2608.28549 • Published 8 days ago • 15

Ring Forcing: Towards Precise Long-Term Memory for Autoregressive Video Diffusion

Paper • 2608.26794 • Published 9 days ago • 16

Act with Intent: Distilling Behavior Intent for Vision-Language-Action Models

Paper • 2608.23478 • Published 12 days ago • 30

Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090

Paper • 2608.27370 • Published 9 days ago • 36

Beyond Pixels: From Video Priors to 4D Worlds

Paper • 2608.10744 • Published 25 days ago • 189

upvoted a paper 5 days ago

Sliding-window beats linear attention

Paper • 2608.28444 • Published 8 days ago • 15

upvoted a collection 9 days ago

BVD: Big Video Dataset

Collection

A 10-Million-Hour Open Video Dataset for Multimodal Pre-training • 11 items • Updated 10 days ago • 7

upvoted a collection 15 days ago

EgoSuite-Open100K

Collection

The largest fully-annotated open egocentric human dataset. 100,000 hours across 15,000+ tasks and scenes. • 3 items • Updated 17 days ago • 51

upvoted an article 16 days ago

view article

Article

Skill Evolving: What Happens When Agents Learn From Each Other

• 

AmberLJC

•

Feb 13

• 1

upvoted a collection 16 days ago

RoboCOIN

Collection

RoboCOIN • 431 items • Updated May 20 • 8

upvoted a collection 18 days ago

TPIPS

Collection

This is the collection of models and data for our paper "The Many Senses of Visual Similarity: A Text-Prompted Image Perceptual Metric" • 7 items • Updated Aug 1 • 1

upvoted an article 19 days ago

view article

Article

How NVIDIA Builds Open Data for AI

• 

nvidia

•

Mar 10

• 21

upvoted a collection 23 days ago

NaFlexCLAP

Collection

Experiments in OpenCLIP (main branch) with `timm` NaFlexViT audio encoder + modern text encoder for variable-time , variable-length text CLAP models • 4 items • Updated 26 days ago • 3

upvoted a paper 24 days ago

Motif 3: Technical Report

Paper • 2608.09119 • Published 26 days ago • 46

upvoted a collection 24 days ago

LTX-2.5

Collection

LTX-2.5 base models, quantized models and accompanying LoRAs and IC-LoRAs • 5 items • Updated 4 days ago • 56

upvoted a collection about 1 month ago

Boogu-Image-Edit-Turbo

Collection

2 items • Updated Jul 9 • 3

upvoted a paper about 1 month ago

You Don't Need Strong Assumptions: Visual Representation Learning via Temporal Differences

Paper • 2606.15956 • Published Jun 14 • 13

upvoted an article about 1 month ago

view article

Article

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

• 
• 
• +2

hlarcher, XciD, raphael-gl, chris-rannou

•

Jul 27

• 486