SWE-MISBEHAVIOR: Benchmarking and Mitigating Boundary Violations in Software Coding Agents Paper • 2610.18206 • Published 3 days ago • 11
An Optimal Transport-driven Approach for Cultivating Latent Space in Online Incremental Learning Paper • 2211.16780 • Published Apr 16 • 2
VISTA: A Test-Time Self-Improving Video Generation Agent Paper • 2510.15831 • Published Oct 17, 2025 • 24