Large language models are increasingly used as judges to reduce reliance on costly human evaluation, yet their scores can systematically disagree with human judgments. We ask whether responses to an explicitly imposed evaluative bias can help correct a judge's implicit scoring biases. We introduce PRISM (Probe-based Re...
A training-free ST2P pipeline that integrates both lexical and acoustic information at inference time is proposed that outperforms all baselines, including a trained ST2P model and commercial multimodal LLMs.
Hikaru Asano, Yotaro Kubo, So Kuroki· arXiv.org· 0 citations
Tandem speech-to-speech architectures couple a responsive speech frontend with an asynchronous text backend. In KAME, a large language model (LLM) serves as the backend, supplying candidate responses as guidance to the speech frontend while the user is still speaking. Ordinary conversation recordings capture the eventu...
This work proposes Feedback-to-Rubrics, a problem setting for learning criteria from inline comments on artifacts, which infers rubrics from these comments and iteratively refines them by observing errors in comment prediction based on the inferred rubrics.
Kotaro Yoshida, So Kuroki, Yuki Imajuku et al.· 0 citations
SAIL is a framework that reframes robot imitation as an iterative refinement problem capable of scaling with test-time compute, and utilizes Monte Carlo Tree Search, where each node is a complete trajectory and edges correspond to trajectory refinements.
The value of execution-improved software as a resource for acquiring new policies in this setting is demonstrated, although initial references remain better on two target tasks when averaged across runs.
So Kuroki, Yu-Jin Tang· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.