Answering in the User's Variety: Calibrated Accommodation Pairs for Post-Training Paper • 2610.28474 • Published 8 days ago • 16
Iris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning Paper • 2610.09450 • Published 21 days ago • 32
From Prompting to Composing: A Spatial Canvas Interface for Poster Generation Paper • 2610.12230 • Published 20 days ago • 21
Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching Paper • 2610.12421 • Published 20 days ago • 22
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments? Paper • 2610.08215 • Published 20 days ago • 63
EmbodiedSmith: Scaling Embodied Data through Recursive Self-Improvement Flywheel in Simulation Paper • 2610.07969 • Published 22 days ago • 22
The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks Paper • 2609.25804 • Published Sep 22 • 166
OmniEdu: Open Foundation Models for Learning and Teaching Paper • 2609.23088 • Published Sep 19 • 242
Refinement Is Inherently Editable: Training-Free Prompt-to-Prompt Image Editing with Generative Refinement Network Paper • 2609.20633 • Published Sep 17 • 13
Srijika: OpenType-Layout-Reusing Font Restyling for Nine Indic Scripts Paper • 2609.05661 • Published Sep 4 • 40
ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments Paper • 2609.19134 • Published Sep 16 • 106