1.1k citations · 1.2k across the 20 of their papers we have counts for
21 papers
Improving Cross-embodiment Transfer in Latent Action Models with Action-Similarity Supervision
Maxime Alvarez, Renzo Caballero, Tatsuya Matsushima +2
As generalist robot policies gain vision and language from web-scale pretraining, demonstrations remain costly to collect and tied to the robot that recorded them. Latent action mo…
DREAM: Deployment-Time Demonstration Generation via Real-to-Sim for Scalable Policy Adaptation
Makoto Sato, Tatsuya Matsushima, Yutaka Matsuo +1
Vision-language-action (VLA) models have made strong progress in language-conditioned robot manipulation, but improving their performance in a new workspace still often requires ac…
Temporally Centered SIGReg Improves LeWorldModel Representations for Robot Policy Learning
Chang Liu, Fei Suo, Yanzhou Jin +4
Recent work on LeWorldModel (LeWM) has shown that the Sketched Isotropic Gaussian Regularizer (SIGReg) enables stable end-to-end world model learning from pixels by regularizing th…
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…
DreamSparse: Escaping from Plato's Cave with 2D Frozen Diffusion Model Given Sparse Views
Paul Yoo, Jiaxian Guo, Yutaka Matsuo +1
Synthesizing novel view images from a few views is a challenging but practical problem. Existing methods often struggle with producing high-quality results or necessitate per-objec…
Paste, Inpaint and Harmonize via Denoising: Subject-Driven Image Editing with Pre-Trained Diffusion Model
Xin Zhang, Jiaxian Guo, Paul Yoo +2
Text-to-image generative models have attracted rising attention for flexible image editing via user-specified descriptions. However, text descriptions alone are not enough to elabo…
GenORM: Generalizable One-shot Rope Manipulation with Parameter-Aware Policy
So Kuroki, Jiaxian Guo, Tatsuya Matsushima +7
Due to the inherent uncertainty in their deformability during motion, previous methods in rope manipulation often require hundreds of real-world demonstrations to train a manipulat…
End-to-end Training of Deep Boltzmann Machines by Unbiased Contrastive Divergence with Local Mode Initialization
Shohei Taniguchi, Masahiro Suzuki, Yusuke Iwasawa +1
We address the problem of biased gradient estimation in deep Boltzmann machines (DBMs). The existing method to obtain an unbiased estimator uses a maximal coupling based on a Gibbs…
Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice
Toshinori Kitamura, Tadashi Kozuno, Yunhao Tang +12
Mirror descent value iteration (MDVI), an abstraction of Kullback-Leibler (KL) and entropy-regularized reinforcement learning (RL), has served as the basis for recent high-performi…
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…
Multimodal Sequential Generative Models for Semi-Supervised Language Instruction Following
Kei Akuzawa, Yusuke Iwasawa, Yutaka Matsuo
Agents that can follow language instructions are expected to be useful in a variety of situations such as navigation. However, training neural network-based agents requires numerou…
Realtime Data-Efficient Portrait Stylization Based On Geometric Alignment
Xinrui Wang, Zhuoru Li, Xiao Zhou +2
Portrait Stylization aims to imbue portrait photos with vivid artistic effects drawn from style examples. Despite the availability of enormous training datasets and large network w…
Collective Intelligence for 2D Push Manipulations with Mobile Robots
So Kuroki, Tatsuya Matsushima, Jumpei Arima +4
While natural systems often present collective intelligence that allows them to self-organize and adapt to changes, the equivalent is missing in most artificial systems. We explore…
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…
Langevin Autoencoders for Learning Deep Latent Variable Models
Shohei Taniguchi, Yusuke Iwasawa, Wataru Kumagai +1
Markov chain Monte Carlo (MCMC), such as Langevin dynamics, is valid for approximating intractable distributions. However, its usage is limited in the context of deep latent variab…
Recognition of All Categories of Entities by AI
Hiroshi Yamakawa, Yutaka Matsuo
Human-level AI will have significant impacts on human society. However, estimates for the realization time are debatable. To arrive at human-level AI, artificial general intelligen…
Deep Billboards towards Lossless Real2Sim in Virtual Reality
Naruya Kondo, So Kuroki, Ryosuke Hyakuta +3
An aspirational goal for virtual reality (VR) is to bring in a rich diversity of real world objects losslessly. Existing VR applications often convert objects into explicit 3D mode…
World Robot Challenge 2020 -- Partner Robot: A Data-Driven Approach for Room Tidying with Mobile Manipulator
Tatsuya Matsushima, Yuki Noguchi, Jumpei Arima +10
Tidying up a household environment using a mobile manipulator poses various challenges in robotics, such as adaptation to large real-world environmental variations, and safe and ro…
Robustifying Vision Transformer without Retraining from Scratch by Test-Time Class-Conditional Feature Alignment
Takeshi Kojima, Yutaka Matsuo, Yusuke Iwasawa
Vision Transformer (ViT) is becoming more popular in image processing. Specifically, we investigate the effectiveness of test-time adaptation (TTA) on ViT, a technique that has eme…
Large Language Models are Zero-Shot Reasoners
Takeshi Kojima, Shixiang Shane Gu, Machel Reid +2
Pretrained large language models (LLMs) are widely used in many sub-fields of natural language processing (NLP) and generally known as excellent few-shot learners with task-specifi…
Domain Prompt Learning for Efficiently Adapting CLIP to Unseen Domains
Xin Zhang, Shixiang Shane Gu, Yutaka Matsuo +1
Domain generalization (DG) is a difficult transfer learning problem aiming to learn a generalizable model for unseen domains. Recent foundation models (FMs) are robust to many dist…