activity
20242026
collaborators

17 papers

cs.AI2026

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…

cs.LG2026

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…

cs.RO2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…