Physis-Lang: Self-Evolving Language as a Physical Representation for Video World Model Paper • 2609.40358 • Published 16 days ago • 22
SPADE: Self-Play in Adaptive Synthetic Executable Environments Paper • 2608.19197 • Published Aug 19 • 57
NaviDC-OCR: Navigating Document Parsing Across Digital and Camera-Captured Documents Paper • 2608.12898 • Published Aug 13 • 8
view article Article Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps +1 iamleonie, burtenshaw, sergiopaniego • Sep 3 • 150
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments Paper • 2609.04148 • Published Sep 3 • 212
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses Paper • 2609.24972 • Published 25 days ago • 230
It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning Paper • 2609.00638 • Published Sep 1 • 67
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Paper • 2609.19969 • Published 29 days ago • 229
On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability Paper • 2608.30320 • Published Aug 31 • 62
view article Article NeoMME: an efficient Multimodal-native and Multilingual Encoder Hcompany • Sep 3 • 122