103 citations · 187 across the 25 of their papers we have counts for
14 papers · 1 filter
BCT: Bayes-Consistent Tempering for Flow Language Models
Daisuke Oba, Hiroki Furuta, Naoaki Okazaki
Temperature scaling is typically applied as a post-hoc transformation of model probabilities. In posterior-induced flow language models, this creates two mismatches. First, posteri…
Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation
Ku Onoda, Paavo Parmas, Hiroki Furuta +4
Text-to-image (T2I) models can synthesize realistic, prompt-aligned images, yet samples generated for the same prompt often cover only a small subset of visually distinct modes. Th…
Improving Dynamic Object Interactions in Text-to-Video Generation with AI Feedback
Hiroki Furuta, Heiga Zen, Dale Schuurmans +4
Large text-to-video models hold immense potential for a wide range of downstream applications. However, they struggle to accurately depict dynamic object interactions, often result…
Geometric-Averaged Preference Optimization for Soft Preference Labels
Hiroki Furuta, Kuang-Huei Lee, Shixiang Shane Gu +4
Many algorithms for aligning LLMs with human preferences assume that human preferences are binary and deterministic. However, human preferences can vary across individuals, and the…
Towards Empirical Interpretation of Internal Circuits and Properties in Grokked Transformers on Modular Polynomials
Hiroki Furuta, Gouki Minegishi, Yusuke Iwasawa +1
Grokking has been actively explored to reveal the mystery of delayed generalization and identifying interpretable representations and algorithms inside the grokked models is a sugg…
Exposing Limitations of Language Model Agents in Sequential-Task Compositions on the Web
Hiroki Furuta, Yutaka Matsuo, Aleksandra Faust +1
Language model agents (LMA) recently emerged as a promising paradigm on muti-step decision making tasks, often outperforming humans and other reinforcement learning agents. Despite…
A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
Izzeddin Gur, Hiroki Furuta, Austin Huang +4
Pre-trained large language models (LLMs) have recently achieved better generalization and sample efficiency in autonomous web automation. However, the performance on real-world web…
Multimodal Web Navigation with Instruction-Finetuned Foundation Models
Hiroki Furuta, Kuang-Huei Lee, Ofir Nachum +4
The progress of autonomous web navigation has been hindered by the dependence on billions of exploratory interactions via online reinforcement learning, and domain-specific model d…
A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation
Hiroki Furuta, Yusuke Iwasawa, Yutaka Matsuo +1
The rise of generalist large-scale models in natural language and vision has made us expect that a massive data-driven approach could achieve broader generalization in other domain…
Generalized Decision Transformer for Offline Hindsight Information Matching
Hiroki Furuta, Yutaka Matsuo, Shixiang Shane Gu
How to extract as much learning signal from each trajectory data has been a key problem in reinforcement learning (RL), where sample inefficiency has posed serious challenges for p…
Braxlines: Fast and Interactive Toolkit for RL-driven Behavior Engineering beyond Reward Maximization
Shixiang Shane Gu, Manfred Diaz, Daniel C. Freeman +7
The goal of continuous control is to synthesize desired behaviors. In reinforcement learning (RL)-driven approaches, this is often accomplished through careful task reward engineer…
Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning
Hiroki Furuta, Tadashi Kozuno, Tatsuya Matsushima +2
Recently many algorithms were devised for reinforcement learning (RL) with function approximation. While they have clear algorithmic distinctions, they also have many implementatio…
Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning
Hiroki Furuta, Tatsuya Matsushima, Tadashi Kozuno +4
Progress in deep reinforcement learning (RL) research is largely enabled by benchmark task environments. However, analyzing the nature of those environments is often overlooked. In…
Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization
Tatsuya Matsushima, Hiroki Furuta, Yutaka Matsuo +2
Most reinforcement learning (RL) algorithms assume online access to the environment, in which one may readily interleave updates to the policy with experience collection using that…