Emma Lefevre

emmalef's activity

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

upvoted 2 papers 3 days ago

Self-Conditioning Enables Deep Sequential Reasoning in Flow Matching

Paper • 2610.19628 • Published 9 days ago • 15

APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation

Paper • 2610.18097 • Published 9 days ago • 31

upvoted 3 papers 5 days ago

From Prompting to Composing: A Spatial Canvas Interface for Poster Generation

Paper • 2610.12230 • Published 15 days ago • 21

Pristine Models

Paper • 2610.14091 • Published 14 days ago • 30

EgoExplorer: A Vision-Motion-Touch Observatory for Human Loco-Manipulation In Situ

Paper • 2610.18872 • Published 10 days ago • 28

upvoted a paper 6 days ago

Simplifying and Improving On-Policy Distillation for Few-Step Diffusion

Paper • 2610.18472 • Published 10 days ago • 33

upvoted 2 papers 10 days ago

VIEScore2: Unified Image Evaluation with Spatially Grounded Explanations

Paper • 2610.00994 • Published 22 days ago • 35

UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation

Paper • 2610.09823 • Published 16 days ago • 199

upvoted a paper 16 days ago

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

Paper • 2609.40362 • Published 23 days ago • 40

upvoted 2 papers 17 days ago

DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence

Paper • 2609.39222 • Published 23 days ago • 47

UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement

Paper • 2609.38721 • Published 23 days ago • 227

upvoted 3 papers 21 days ago

SciGen-Verifier: A Multimodal Reasoner for Explainable Verification in Scientific Image Generation

Paper • 2609.33399 • Published 26 days ago • 19

Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning

Paper • 2609.35767 • Published 25 days ago • 50

VisionHOPE: Visual Backbones as Self-Modifying Learning Systems

Paper • 2609.33325 • Published 26 days ago • 93

upvoted 2 papers 23 days ago

ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation

Paper • 2609.28923 • Published 29 days ago • 11

Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs

Paper • 2609.29845 • Published 29 days ago • 104

upvoted 2 papers 25 days ago

StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training

Paper • 2609.26774 • Published about 1 month ago • 56

Ovis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings

Paper • 2609.25165 • Published Sep 21 • 78

upvoted 2 papers 26 days ago

UFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image Generation

Paper • 2609.12397 • Published Sep 17 • 46

Srijika: OpenType-Layout-Reusing Font Restyling for Nine Indic Scripts

Paper • 2609.05661 • Published Sep 4 • 40