SWE-MISBEHAVIOR: Benchmarking and Mitigating Boundary Violations in Software Coding Agents Paper • 2610.18206 • Published 4 days ago • 15
VEDJE: Video-Efficient Discriminative Joint Encoder for Scalable Video-Text Retrieval Paper • 2610.11850 • Published 5 days ago • 39
DyRAD: Radar Novel View Synthesis for Dynamic Driving Scenes Paper • 2609.39841 • Published 17 days ago • 45
TRIAGE: Direction-Aware Mismatch Stabilization of Native NVFP4 Reinforcement Learning Paper • 2610.07043 • Published 12 days ago • 47
Predictive Credit: Measuring What Scientific Explanations Add to Experimental Forecasts Paper • 2610.00314 • Published 18 days ago • 103
Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering Paper • 2609.38177 • Published 18 days ago • 78
EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery Paper • 2609.40340 • Published 17 days ago • 112
Raven: The Harness of Harnesses for Composable Agentic Intelligence Paper • 2609.33439 • Published 20 days ago • 675
LightMIS: Ultra-Lightweight Medical Image Segmentation Without a Stage-Wise Decoder Paper • 2609.28327 • Published 23 days ago • 12
Jev in the Wild: A Data-Driven Analysis of the Jev Model's Functionality, Applications and Ecosystem Paper • 2609.30216 • Published 23 days ago • 16