Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models Paper • 2607.12463 • Published 8 days ago • 107
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget Paper • 2607.14952 • Published 6 days ago • 185
Scalable Visual Pretraining for Language Intelligence Paper • 2607.09657 • Published 12 days ago • 56
EVA-Client: A Unified Data Collection, Inference, and Deployment Framework for Embodied Policies on Real Robots Paper • 2607.02646 • Published 20 days ago • 27
PANDO: Efficient Multimodal AI Agents via Online Skill Distillation Paper • 2605.24785 • Published May 26 • 11
Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations Paper • 2605.27958 • Published May 27 • 2
Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments Paper • 2605.30280 • Published May 28 • 146
How LoRA Remembers? A Parametric Memory Law for LLM Finetuning Paper • 2605.30260 • Published May 28 • 44
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published May 27 • 433
WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation Paper • 2605.25874 • Published May 25 • 105