17 papers
Training Language Models to Cooperate with Inference-Time Controllers
Moumita Choudhury, Vanshaj Khattar, Jing Liu +4
Large language model (LLM) performance increasingly depends not only on the base model, but also on the inference-time controller used to organize reasoning. Existing post-training…
Beyond Heavy Log Curation: Perplexity-Based APT Detection via Unsupervised, Context-Augmented Language Models
Shoya Otsu, Kei Suzuki, Toshiaki Koike-Akino +2
Advanced Persistent Threats (APTs) remain difficult to detect because only a small fraction of events in large-scale logs are attack-related, and investigation is expensive and har…
ReCoVLA: VLM-Guided Reward Compilation for Failure Recovery in Vision-Language-Action Policies
Haodi Hu, Chung-Ta Huang, Jing Liu +4
Vision-language-action (VLA) policies provide strong priors for language-conditioned manipulation, but remain brittle in off-nominal states requiring targeted recovery. We propose…
EinSort: Sorting is All We Need for Tensorizing LLM
Toshiaki Koike-Akino, Jing Liu, Ye Wang
Tensor networks provide efficient representations for compressing large neural networks. By carefully designing shapes and topologies, they can significantly reduce memory and comp…
Temper and Tilt Lead to SLOP: Reward Hacking Mitigation with Inference-Time Alignment
Ye Wang, Jing Liu, Toshiaki Koike-Akino
Inference-time alignment techniques offer a lightweight alternative or complement to costly reinforcement learning, while enabling continual adaptation as alignment objectives and…
Amplification Effects in Test-Time Reinforcement Learning: Safety and Reasoning Vulnerabilities
Vanshaj Khattar, Md Rafi ur Rashid, Moumita Choudhury +4
Test-time training (TTT) has recently emerged as a promising method to improve the reasoning abilities of large language models (LLMs), in which the model directly learns from test…