8 papers
Prior-Conditioned Gaussian Discriminants for Generalizable AI-generated Image Detection
Shashank Kotyan, Makoto Shing, Yuki Imajuku +2
Diffusion-based generators have made synthetic images ubiquitous, but detectors often fail under simultaneous shifts in generator, prompt/style, and source-domain. We study AI-gene…
Feedback-to-Rubrics: Can We Learn Expert Criteria from Inline Comments?
Kotaro Yoshida, So Kuroki, Yuki Imajuku +4
Large language models (LLMs) are increasingly used for writing and review support, but their usefulness depends on context-dependent criteria, such as expert preferences or organiz…
Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search
Yuichi Inoue, Kou Misaki, Yuki Imajuku +3
Recent advances demonstrate that increasing inference-time computation can significantly boost the reasoning capabilities of large language models (LLMs). Although repeated samplin…
ALE-Bench: A Benchmark for Long-Horizon Objective-Driven Algorithm Engineering
Yuki Imajuku, Kohki Horie, Yoichi Iwata +3
How well do AI systems perform in algorithm engineering for hard optimization problems in domains such as package-delivery routing, crew scheduling, factory production planning, an…
ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
Robert Tjarko Lange, Yuki Imajuku, Edoardo Cetin
We introduce ShinkaEvolve: a new open-source framework leveraging large language models (LLMs) to advance scientific discovery with state-of-the-art performance and unprecedented e…
Sudoku-Bench: Evaluating creative reasoning with Sudoku variants
Jeffrey Seely, Yuki Imajuku, Tianyu Zhao +2
Existing reasoning benchmarks for large language models (LLMs) frequently fail to capture authentic creativity, often rewarding memorization of previously observed patterns. We add…