6 citations · 30 across the 37 of their papers we have counts for
8 papers · 1 filter
Zero-Shot Textual Explanations via Translating Decision-Critical Features
Toshinori Yamauchi, Hiroshi Kera, Kazuhiko Kawamoto
Textual explanations make image classifier decisions transparent by describing the prediction rationale in natural language. Large vision-language models can generate captions but…
Adversarial Fine-tuning in Offline-to-Online Reinforcement Learning for Robust Robot Control
Shingo Ayabe, Hiroshi Kera, Kazuhiko Kawamoto
Offline reinforcement learning enables sample-efficient policy acquisition without risky online interaction, yet policies trained on static datasets remain brittle under action-spa…
Learning Moderately Input-Sensitive Functions: A Case Study in QR Code Decoding
Kazuki Yoda, Kazuhiko Kawamoto, Hiroshi Kera
The hardness of learning a function that attains a target task relates to its input-sensitivity. For example, image classification tasks are input-insensitive as minor corruptions…
Gradient-Weighted, Data-Driven Normalization for Approximate Border Bases -- Concept and Computation
Hiroshi Kera, Achim Kehrein
This paper studies the concept and the computation of approximately vanishing ideals of a finite set of data points. By data points, we mean that the points contain some uncertaint…
CALT: A Library for Computer Algebra with Transformer
Hiroshi Kera, Shun Arakawa, Yuta Sato
Recent advances in artificial intelligence have demonstrated the learnability of symbolic computation through end-to-end deep learning. Given a sufficient number of examples of sym…
Discovering Learning-Friendly Generation Orders for Sequential Computation
Yuta Sato, Kazuhiko Kawamoto, Hiroshi Kera
Sequential computation via autoregressive generation can make difficult tasks learnable, but the generation order of intermediate states strongly affects whether training succeeds.…