collaborators

8 papers

cs.LG2026

Gradient Regularization Mitigates Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards

Johannes Ackermann, Michael Noukhovitch, Takashi Ishida +1

Reinforcement Learning from Human Feedback (RLHF) or Verifiable Rewards (RLVR) are two key steps in the post-training of modern Language Models (LMs). A common problem is reward ha…

cs.LG2026

Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests

Thanawat Lodkaew, Johannes Ackermann, Soichiro Nishimori +3

A growing failure mode in agent evaluation and training is that models can achieve high evaluation scores by exploiting shortcuts instead of solving the intended task, producing de…

cs.LG2026

Practical estimation of the optimal classification error with soft labels and calibration

Ryota Ushio, Takashi Ishida, Masashi Sugiyama

While the performance of machine learning systems has experienced significant improvement in recent years, relatively little attention has been paid to the fundamental question: to…

cs.LG2026

Proteo-R1: Reasoning Foundation Models for De Novo Protein Design

Fang Wu, Weihao Xuan, Heli Qi +26

Deep learning in de novo protein design has achieved atomic-level fidelity. However, existing models remain largely non-deliberative: they directly synthesize molecular geometries…

cs.LG2026

Mitigating Reward Hacking in RLHF via Advantage Sign Robustness

Shinnosuke Ono, Johannes Ackermann, Soichiro Nishimori +2

Reward models (RMs) used in reinforcement learning from human feedback (RLHF) are vulnerable to reward hacking: as the policy maximizes a learned proxy reward, true quality plateau…

cs.LG2026

Towards Scalable Oversight via Partitioned Human Supervision

Ren Yin, Takashi Ishida, Masashi Sugiyama

As artificial intelligence (AI) systems approach and surpass expert human performance across a broad range of tasks, obtaining high-quality human supervision for evaluation and tra…