Traffic Signal Control (TSC) is a safety-critical cyber-physical system that relies on real-time sensing. Corrupted observations caused by adversarial perturbations or sensor failures can propagate from the sensing layer into the controller and degrade traffic efficiency. Existing robust Reinforcement Learning (RL)-bas...
Ming-Yuan Li, Chun-Yu Liu, Xiao Liu et al.· 0 citations
Multi-path reasoning methods such as self-consistency (SC) sample $K$ reasoning paths and choose the most frequent answer. However, their gains quickly plateau as $K$ increases, and existing methods do not predict when this saturation will occur. We formalize multi-path LLM reasoning as a diversity combining problem fr...
Guang-Sheng Yu, Litianyi Zhang, Qin Wang et al.· 0 citations
Privacy-sensitive organizations may run large language models (LLMs) in restricted or air-gapped environments while exporting selected diagnostic artifacts. We show that a compromised runtime component can hide sensitive information in intermediate activations that are allowed to leave the restricted environment. An of...
Ming-Yuan Li, Yan-Na Jiang, Guang-Sheng Yu et al.· 0 citations
Learned-memory methods store information in an explicit table and consume it through a separate reader, allowing addressing, storage, and reading to be modified independently. We study whether useful memory can also be generated rather than only retrieved. MemoryAthena uses three pathways: direct Engram retrieval (E),...
Ming-Yuan Li, Guang-Sheng Yu, Ju-Yuan Zhang et al.· 0 citations
Test-time reinforcement learning (TTRL) enables models to improve their reasoning without relying on labeled training data, but existing approaches typically optimize a large fraction of the model parameters. This raises a natural question: can effective test-time adaptation emerge when both the reward signal and the o...
The results suggest that Engram can serve as a reusable external knowledge artifact, provided that the target has access to a compatible reader interface and target-side adaptation can further improve alignment when direct reader reuse is insufficient.
Mingyuan Li, Guangsheng Yu, Xu Wang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
