2 papers
cs.AI2026
The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs
Akshit Sinha, Arvindh Arun, Shashwat Goel +2
Does continued scaling of large language models (LLMs) yield diminishing returns? In this work, we show that short-task benchmarks may give an illusion of slowing progress, as even…
cs.LG2025
Paving the way for scientific foundation models: enhancing generalization and robustness in PDEs with constraint-aware pre-training
Amin Totounferoush, Serge Kotchourko, Michael W. Mahoney +1
Partial differential equations (PDEs) govern a wide range of physical systems, but solving them efficiently remains a major challenge. The idea of a scientific foundation model (Sc…