arXiv:2603.29112v1 Announce Type: cross
Abstract: We introduce GISTBench, a benchmark for evaluating Large Language Models’ (LLMs) ability to understand users from their interaction histories in recommendation systems. Unlike traditional RecSys benchm…
arXiv:2512.10805v2 Announce Type: replace-cross
Abstract: Sparse autoencoders (SAEs) promise a unified approach for mechanistic interpretability, concept discovery, and model steering in LLMs and LVLMs. However, realizing this potential requires learn…
arXiv:2603.29441v1 Announce Type: new
Abstract: While the Earth observation community has witnessed a surge in high-impact foundation models and global Earth embedding datasets, a significant barrier remains in translating these academic assets into f…
arXiv:2403.10853v4 Announce Type: replace-cross
Abstract: Online learning methods often rely on supervised data. However, under data distribution shifts, such as in continual learning (CL), where continuously arriving online data streams incorporate n…
arXiv:2510.16635v2 Announce Type: replace-cross
Abstract: Prompt optimization has become a practical way to improve the performance of Large Language Models (LLMs) without retraining. However, most existing frameworks treat evaluation as a black box, …
arXiv:2603.29449v1 Announce Type: new
Abstract: Minimizing invasive diagnostic procedures to reduce the risk of patient injury and infection is a central goal in medical imaging. And yet, noninvasive diagnosis of perineural invasion (PNI), a critical …
arXiv:2603.28768v1 Announce Type: cross
Abstract: Mixture-of-Experts (MoE) has recently emerged as the mainstream architecture for efficiently scaling large language models while maintaining near-constant computational cost. Expert parallelism distrib…
arXiv:2603.29121v1 Announce Type: cross
Abstract: This paper develops a unified framework for evaluating the optimal degree of task automation. Moving beyond binary automate-or-not assessments, we model automation intensity as a continuous choice in w…
arXiv:2603.29460v1 Announce Type: new
Abstract: Superpixels provide a compact region-based representation that preserves object boundaries and local structures, and have therefore been widely used in a variety of vision tasks to reduce computational c…
arXiv:2508.08115v3 Announce Type: replace
Abstract: Complex medical reasoning has historically required frontier language models to achieve clinically-acceptable accuracy, creating computational barriers that limit deployment in resource-constrained c…