10 papers
PRISM: Calibrating Black-Box Judges with Counterfactual Probes
Kakei Yamamoto, So Kuroki
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 wheth…
Training-Free Pronunciation Transcription via Text-Constrained Acoustic Rescoring
Hikaru Asano, Yotaro Kubo, So Kuroki
Accurate and efficient pronunciation transcription is essential for preparing text-to-speech training data at scale. Existing approaches have different limitations: grapheme-to-pro…
Learning Natural Conversational Behavior in Tandem Speech-to-Speech Models with Randomized Guidance
Manato Yaguchi, Yotaro Kubo, Hikaru Asano +1
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…
Learning and Transferring Closed-Loop Robot Software
So Kuroki, Yujin Tang
Closed-loop robot policies require observation processing, state management, and situation-dependent branching, making them costly to design and tune manually. Although coding agen…
Feedback-to-Rubrics: Can We Learn Expert Criteria from Inline Comments?
Kotaro Yoshida, So Kuroki, Yuki Imajuku +4
Large language models (LLMs) are increasingly used for writing and review support, but their usefulness depends on context-dependent criteria, such as expert preferences or organiz…
SAIL: Test-Time Scaling for In-Context Imitation Learning with VLM
Makoto Sato, Yusuke Iwasawa, Yujin Tang +1
In-context imitation learning allows robots to acquire skills from demonstrations, yet one-shot trajectory generation remains fragile under environmental variation. We propose SAIL…
KAME: Tandem Architecture for Enhancing Knowledge in Real-Time Speech-to-Speech Conversational AI
So Kuroki, Yotaro Kubo, Takuya Akiba +1
Real-time speech-to-speech (S2S) models excel at generating natural, low-latency conversational responses but often lack deep knowledge and semantic understanding. Conversely, casc…
Shachi: A Modular, Controllable Framework for LLM-Based Agent-Based Modeling of Emergent Collective Behavior
So Kuroki, Yingtao Tian, Kou Misaki +3
How collective behaviors emerge from the interactions of individual LLM-driven agents is a central question in artificial life, yet controlled study of these emergent dynamics has…
Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search
Yuichi Inoue, Kou Misaki, Yuki Imajuku +3
Recent advances demonstrate that increasing inference-time computation can significantly boost the reasoning capabilities of large language models (LLMs). Although repeated samplin…
Agent Skill Acquisition for Large Language Models via CycleQD
So Kuroki, Taishi Nakamura, Takuya Akiba +1
Training large language models to acquire specific skills remains a challenging endeavor. Conventional training approaches often struggle with data distribution imbalances and inad…