This work proposes LoopWeaver, a hierarchical workflow with two sequential offline preference-optimization stages that produces structured plans, feasibility filtering removes invalid plans, and a shared deterministic reward constructs preference pairs for plan-level and generation-level DPO.
Yi-Fan Zhu, Guan-Ting Chen, Bingzhao Wei et al.· 0 citations
A backbone-flexible probing framework that serializes structured electronic health record variables and leakage-pruned discharge-note sections into a shared frozen-LLM representation space and recovers primary diagnosis categories with linear probes, without fine-tuning the LLM is proposed.
Cheng-Yuan Liu, Xinyu Zhang, Yao Li et al.· 0 citations
The widespread adoption of long-horizon agents has made model workloads increasingly input-heavy. Although prior work has substantially reduced the cost of long-context computation, prefill remains computationally expensive, and large KV caches continue to strain HBM and SSD capacity and data-transfer bandwidth. Togeth...
This study explains why prior works relied on this problematic function without considering well-developed probabilistic outputs for binary linear classification and leads to a more suitable probability estimation for tree-based linear methods.
Sheng-Wei Chen, Kuan-Ting Chen, Guan-Ting Chen et al.· 1 citation
This work introduces a novel LLM-based predictive scheduling system designed to enhance operational efficiency while reducing the environmental impact of data centers, using an LLM to predict key metrics such as execution time and energy consumption from source code.
Hanzhao Wang, Jingxuan Wu, Yumeng Li et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.