Ukyo Honda
13 papers · 2018–2026 · 7 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (27)
🧬
Topic Evolution
🗃️
Keyword Collector
(58)
💎
Century Club · Bronze
❓
The Questioner
⚡
Prolific Year · Productive
Top co-authors
Research topics
Artificial Intelligence
(9)
Machine Learning
(9)
Core AI
(8)
Optimization & Theory
(6)
Natural Language Processing
(4)
Learning Types · Machine Learning
(4)
Deep Learning
(3)
Generation · Natural Language Processing
(3)
Learning Types · Deep Learning
(3)
Computer Vision
(1)
Reinforcement Learning
(1)
Application Areas
(1)
Bayesian & Probabilistic
(1)
Core Methods
(1)
Generation · Computer Vision
(1)
Keywords
text generation
(4)
large language model
(2)
minimum bayes risk decoding
(2)
reinforcement learning
(2)
in-context learning
(2)
knowledge distillation
(1)
image captioning
(1)
symbolic reasoning
(1)
preference optimization
(1)
language model
(1)
anomaly detection
(1)
language model alignment
(1)
neural network optimization
(1)
out-of-distribution generalization
(1)
representative sampling
(1)
neural machine translation
(1)
model alignment
(1)
semantic similarity
(1)
token efficiency
(1)
few-shot learning
(1)
Papers
Does Self-Consistency Improve the Recall of Encyclopedic Knowledge?
ACL 2026
Annotation-Efficient Language Model Alignment via Diverse and Representative Response Texts
EMNLP 2025
Distilling Many-Shot In-Context Learning into a Cheat Sheet
EMNLP 2025
Exploring Explanations Improves the Robustness of In-Context Learning
ACL 2025
A Single Linear Layer Yields Task-Adapted Low-Rank Matrices
COLING 2024
CAMERA³: An Evaluation Dataset for Controllable Ad Text Generation in Japanese
COLING 2024
Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding
ACL 2024
Model-Based Minimum Bayes Risk Decoding for Text Generation
ICML 2024
On the True Distribution Approximation of Minimum Bayes-Risk Decoding
NAACL 2024
Reinforcement Learning for Edit-Based Non-Autoregressive Neural Machine Translation
NAACL 2024
Switching to Discriminative Image Captioning by Relieving a Bottleneck of Reinforcement Learning
WACV 2023
Removing Word-Level Spurious Alignment between Images and Pseudo-Captions in Unsupervised Image Captioning
EACL 2021
Pruning Basic Elements for Better Automatic Evaluation of Summaries
NAACL 2018