Path Planning using Language-Guided Probabilistic Roadmaps

ロボティクス

MIRU 2024

Not Eliminate but Aggregate: Post-Hoc Control over Mixture-of-Experts to Address Shortcut Shifts in Natural Language Understanding

自然言語処理

Transactions of the Association for Computational Linguistics (TACL)

不確かな欠損モダリティを含む自己蒸留を用いたロバストなマルチモーダル感情認識

接客対話エージェント

MIRU 2024

Generating Attractive Ad Text by Facilitating the Reuse of Landing Page Expressions

自然言語処理

INLG 2024

Exploring the Capability of Mamba in Speech Applications

音声認識

INTERSPEECH 2024

An Attribute Interpolation Method in Speech Synthesis by Model Merging

音声合成

INTERSPEECH 2024

On Universally Optimal Algorithms for A/B Testing

機械学習

Stochastic Networks conference 2024

機械学習が紡ぐゲーム理論のフロンティア

機械学習

JSAI 2024

RLHFにおける分布シフトの評価

強化学習

JSAI 2024

Safe Collaborative Filtering

推薦システム

ICLR 2024

Policy Gradient with Kernel Quadrature

強化学習

Transactions on Machine Learning Research (TMLR)

Reinforcement Learning for Edit-Based Non-Autoregressive Neural Machine Translation

強化学習

NAACL SRW 2024

Policy Gradient Algorithms with Monte-Carlo Tree Learning for Non-Markov Decision Processes

強化学習

Reinforcement Learning Conference (RLC) 2024

On the True Distribution Approximation of Minimum Bayes-Risk Decoding

自然言語処理

NAACL 2024

Model-based minimum bayes risk decoding

強化学習

ICML 2024

Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding

強化学習

Findings of ACL 2024

Hyperparameter-Free Approach for Faster Minimum Bayes Risk Decoding

強化学習

Findings of ACL 2024

Adaptively Perturbed Mirror Descent for Learning in Games

強化学習

ICML 2024

Striking Gold in Advertising: Standardization and Exploration of Ad Text Generation

自然言語処理

ACL 2024

On Universally Optimal Algorithms for A/B Testing

強化学習

ICML 2024

Matroid Semi-Bandits in Sublinear Time

Machine Learning

40th International Conference on Machine Learning (ICML 2024)