We show that the causality of language models (LMs) may not be necessary nor optimal. This is the case when system behavior (denoted as $S$) is incorporated as a first-principle Bayesian feature. Here, $S$ refers to extra dominant factors beyond the data space, and they involve coupled effects. Despite being the de fac...
A KL-divergence-driven model fine-tuning and plan updating strategy that dynamically adapts to workload changes is introduced, demonstrating improved scalability and robustness for industrial-scale PQO.
Song-Song Mo, Quan-Qing Xu, Xu-Chen Ding et al.· Proceedings of the VLDB Endo...· 0 citations
This study observes that sparse attention scores exhibit a score concentration phenomenon, where scores tend to fall within a narrow range, and proposes LITETOPK, an efficient fused Indexer-TopK kernel, which exploits the similarity of top-k candidate sets among neighboring tokens and proposes LITEDSA, which exploits t...
This work introduces TOFFEE, a system for synthesizing high-quality data agent trajectories from given data environments via Monte Carlo Tree Search (MCTS) with adaptive model selection and cross-task prefix reuse, and shows that TOFFEE can effectively generate scalable trajectory data for complex analytical tasks acro...
Ziting Wang, Yin Li, Zuhao Yang et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
