activity
20242026
collaborators

6 papers

cs.LG2026

Safety Hacking in Constrained Best-of- Inference-time Scaling

Akifumi Wachi, Takumi Tanabe, Youhei Akimoto

Inference-time pipelines often sample multiple outputs, filter them with a learned safety model, and return the proxy-feasible output with the highest learned reward. We show that…

cs.LG2026

Sample-Efficient Hypergradient Estimation for Decentralized Bi-Level Reinforcement Learning

Mikoto Kudo, Takumi Tanabe, Akifumi Wachi +1

Many strategic decision-making problems, such as environment design for warehouse robots, can be naturally formulated as bi-level reinforcement learning (RL), where a leader agent…

cs.LG2025

Cost-Minimized Label-Flipping Poisoning Attack to LLM Alignment

Shigeki Kusaka, Keita Saito, Mikoto Kudo +3

Large language models (LLMs) are increasingly deployed in real-world systems, making it critical to understand their vulnerabilities. While data poisoning attacks during RLHF/DPO a…

cs.LG2025

A Provable Approach for End-to-End Safe Reinforcement Learning

Akifumi Wachi, Kohei Miyaguchi, Takumi Tanabe +2

A longstanding goal in safe reinforcement learning (RL) is a method to ensure the safety of a policy throughout the entire process, from learning to operation. However, existing sa…

cs.AI2025

Vulnerability Mitigation for Safety-Aligned Language Models via Debiasing

Thien Q. Tran, Akifumi Wachi, Rei Sato +2

Safety alignment is an essential research topic for real-world AI applications. Despite the multifaceted nature of safety and trustworthiness in AI, current safety alignment method…

cs.LG2024

Stepwise Alignment for Constrained Language Model Policy Optimization

Akifumi Wachi, Thien Q. Tran, Rei Sato +2

Safety and trustworthiness are indispensable requirements for real-world applications of AI systems using large language models (LLMs). This paper formulates human value alignment…