8 papers
Test-time reward-guided alignment of language models by importance sampling on pre-logit space
Sekitoshi Kanai, Tsukasa Yoshida, Hiroshi Takahashi +2
Test-time alignment of large language models (LLMs) attracts attention because fine-tuning of LLMs requires high computational costs. In this paper, we propose a new test-time rewa…
Receding-Horizon Maximum-Likelihood Estimation of Neural-ODE Dynamics and Thresholds from Event Cameras
Kazumune Hashimoto, Kazunobu Serizawa, Masako Kishida
Event cameras emit asynchronous brightness-change events where each pixel triggers an event when the last event exceeds a threshold, yielding a history-dependent measurement model.…
Structural-Ambiguity-Aware Translation from Natural Language to Signal Temporal Logic
Kosei Fushimi, Kazunobu Serizawa, Junya Ikemoto +1
Signal Temporal Logic (STL) is widely used to specify timed and safety-critical tasks for cyber-physical systems, but writing STL formulas directly is difficult for non-expert user…
Data-driven Exploration of Tropical Cyclone's Controllability
Yohei Sawada, Masashi Minamide, Yuyue Yan +2
Although the chaotic nature of the atmosphere may enable efficient control of tropical cyclones (TCs) via small-scale perturbations, few studies have proposed data-driven optimizat…
MM-LMPC: Multi-Modal Learning Model Predictive Control via Bandit-Based Mode Selection
Wataru Hashimoto, Kazumune Hashimoto
Learning Model Predictive Control (LMPC) improves performance on iterative tasks by leveraging data from previous executions. At each iteration, LMPC constructs a sampled safe set…
Reference-Free Iterative Learning Model Predictive Control with Neural Certificates
Wataru Hashimoto, Kazumune Hashimoto, Masako Kishida +1
In this paper, we propose a novel reference-free iterative learning model predictive control (MPC). In the proposed method, a certificate function based on the concept of Control L…