T. Koike-Akino

Test-Time Attention: Can Robots Better Follow Commands?

TacSushi: Tactile-Grounded World-Action Modeling for Dexterous Sushi Manipulation

Comparisons support complementary benefits of feature-wise gated tactile fusion and training-only predictive supervision of TacSushi, a tactile-grounded, Cosmos3-based world-action policy that learns from recorded future consequences while acting on current observations.

Vibe Patenting: Evaluating LLM Judges for Professional Patent-Drafting Agents

Vibe Patenting, an end-to-end patent-drafting testbed for AI-agent evaluation, validates the judge against independent evaluation by a professional patent attorney and finds meaningful but strongly metric-dependent agreement and systematic calibration differences.

Beyond Heavy Log Curation: Perplexity-Based APT Detection via Unsupervised, Context-Augmented Language Models

CAPTAIN (Context-Augmented Perplexity-based Threat Activity log detectIoN), a perplexity-based detector that leverages general, pre-trained language models with minimal, domain-agnostic preprocessing, enabling robust scoring of long, minimally processed log entries, is proposed.

Training Language Models to Cooperate with Inference-Time Controllers

CALM (Controller-Aware Language Models), a post-training framework that explicitly places controllers in the training loop, is introduced, showing that controller-aware post-training improves generalization across inference-time workflows beyond single-controller optimization.