8 papers
Interaction Locality in Hierarchical Recursive Reasoning
Yosuke Miyanishi, Tetsuro Morimura
Spatial reasoning requires both location-bound computation and location-invariant structure: agents must make local moves while preserving route, object, or constraint-level plans.…
MO-GRPO: Mitigating Reward Hacking of Group Relative Policy Optimization on Multi-Objective Problems
Yuki Ichihara, Yuu Jinnai, Tetsuro Morimura +3
Group Relative Policy Optimization (GRPO) has been shown to be an effective algorithm when an accurate reward model is available. However, such a highly reliable reward model is no…
Latent Variable Modeling for Robust Causal Effect Estimation
Tetsuro Morimura, Tatsushi Oka, Yugo Suzuki +1
Latent variable models provide a powerful framework for incorporating and inferring unobserved factors in observational data. In causal inference, they help account for hidden fact…
Theoretical Guarantees for Minimum Bayes Risk Decoding
Yuki Ichihara, Yuu Jinnai, Kaito Ariu +2
Minimum Bayes Risk (MBR) decoding optimizes output selection by maximizing the expected utility value of an underlying human distribution. While prior work has shown the effectiven…
Return-Aligned Decision Transformer
Tsunehiko Tanaka, Kenshi Abe, Kaito Ariu +2
Traditional approaches in offline reinforcement learning aim to learn the optimal policy that maximizes the cumulative reward, also known as return. It is increasingly important to…
Evaluation of Best-of-N Sampling Strategies for Language Model Alignment
Yuki Ichihara, Yuu Jinnai, Tetsuro Morimura +4
Best-of-N (BoN) sampling with a reward model has been shown to be an effective strategy for aligning Large Language Models (LLMs) with human preferences at the time of decoding. Bo…