PatchWorld: Gradient-Free Optimization of Executable World Models Paper • 2605.30880 • Published May 29 • 12
MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models Paper • 2605.14906 • Published May 14 • 79
Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context Paper • 2605.13831 • Published May 13 • 90