… Through careful ablations, we show how FutureSim offers a realistic setting to study emerging re search directions like long-horizon test-time adaptation , search , memory , and reasoning about uncertainty . …
… Unlike prior work that focuses on limited datasets or settings, MMDG-Bench unifies evaluation across multiple tasks, modalities, and real-world challenges, including corruption robustness, missing modalities, and model trustworthiness. the take-away from mmdg-bench is that, under fair comparisons, … …
… We also release the EDU-CIRCUIT-HW dataset to support future research on handwritten STEM understanding, recognition robustness, and educational AI evaluation. …