When Privileged Guidance Misaligns: State-Matched Routing and Contextualized Self-Distillation for Multi-Turn Agents Paper • 2608.05219 • Published 12 days ago • 4
CtrlVTON: Controllable Virtual Try-On via Visual-Instance-Prompt Segmentation Paper • 2607.09362 • Published Jul 10 • 12
Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models Paper • 2607.12463 • Published Jul 14 • 108
From SRA to Self-Flow: Data Augmentation or Self-Supervision? Paper • 2607.02508 • Published Jul 2 • 15
HakushoBench: A Japanese Chart and Table VQA Benchmark from Governmental White Papers Paper • 2606.01132 • Published May 31 • 5
PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion Paper • 2605.23902 • Published May 22 • 47