Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Dimitris N. Metaxas

Dimitris N. Metaxas

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

AI×3ML×1

Frequent co-authors

Jiakang Li2×
Can Jin2×
Guanyu Zhu1×
Chenxi Huang1×
Dexu Yu1×
Ronghao Chen1×

Research Timeline

2026
Weak Critics Make Strong Learners: On-Policy Critique Distillation for Scalable Oversight

The paper introduces Weak-Critic Strong Oversight, a method where a weak model guides a strong model's self-improvement by providing non-misleading revision directions, leading to scalable oversight.

PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning

The paper proposes Predictive Routing Replay (PR2) to stabilize reinforcement learning on Mixture of Experts (MoE) LLMs by predicting and incorporating short-horizon router evolution during training and rollout.

Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs

The paper introduces Latent Reward Steering (LRS), an adaptive inference-time framework that implicitly improves the reasoning ability of LLMs by guiding the model's internal latent states based on a reward signal derived from final answer correctness.

Highlighted terms show continued research focus across papers

Papers

cs.AIRecentMay 30, 2026

Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs

Jiakang Li, Guanyu Zhu, Can Jin, Chenxi Huang +7 more

The paper introduces Latent Reward Steering (LRS), an adaptive inference-time framework that implicitly improves the reasoning ability of LLMs by guiding the model's internal latent states based on a…

View →
cs.AIRecentMay 29, 2026

Weak Critics Make Strong Learners: On-Policy Critique Distillation for Scalable Oversight

Can Jin, Jiakang Li, Rui Wu, Eddy Zhang +1 more

The paper introduces Weak-Critic Strong Oversight, a method where a weak model guides a strong model's self-improvement by providing non-misleading revision directions, leading to scalable oversight.

View →
cs.LGcs.AIRecentMay 29, 2026

PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning

Daize Dong, Junlin Chen, Haolong Jia, Jiawei Wu +8 more

The paper proposes Predictive Routing Replay (PR2) to stabilize reinforcement learning on Mixture of Experts (MoE) LLMs by predicting and incorporating short-horizon router evolution during training a…

View →