5 papers
DREAM: Deployment-Time Demonstration Generation via Real-to-Sim for Scalable Policy Adaptation
Makoto Sato, Tatsuya Matsushima, Yutaka Matsuo +1
Vision-language-action (VLA) models have made strong progress in language-conditioned robot manipulation, but improving their performance in a new workspace still often requires ac…
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…
The Way We Prompt: Conceptual Blending, Neural Dynamics, and Prompt-Induced Transitions in LLMs
Makoto Sato
Large language models (LLMs), inspired by neuroscience, exhibit behaviors that often evoke a sense of personality and intelligence-yet the mechanisms behind these effects remain el…
Triggering Hallucinations in LLMs: A Quantitative Study of Prompt-Induced Hallucination in Large Language Models
Makoto Sato
Hallucinations in large language models (LLMs) present a growing challenge across real-world applications, from healthcare to law, where factual reliability is essential. Despite a…
Waking Up an AI: A Quantitative Framework for Prompt-Induced Phase Transition in Large Language Models
Makoto Sato
What underlies intuitive human thinking? One approach to this question is to compare the cognitive dynamics of humans and large language models (LLMs). However, such a comparison r…