Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers Paper • 2508.16211 • Published Aug 22, 2025 • 2
Let Features Decide Their Own Solvers: Hybrid Feature Caching for Diffusion Transformers Paper • 2510.04188 • Published Oct 5, 2025 • 2
OSOR: One-Step Diffusion Inpainting for Effect-Aware Object Removal Paper • 2606.28094 • Published 5 days ago • 1
MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research Paper • 2605.26114 • Published May 25 • 65
CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence Paper • 2605.12882 • Published May 13 • 274
DexJoCo: A Benchmark and Toolkit for Task-Oriented Dexterous Manipulation on MuJoCo Paper • 2605.16257 • Published May 15 • 55
OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration Paper • 2602.05400 • Published Feb 5 • 356
Innovator-VL: A Multimodal Large Language Model for Scientific Discovery Paper • 2601.19325 • Published Jan 27 • 85