Search Results for author: Yusuke Iwasawa

Found 35 papers, 9 papers with code

Learning shared manifold representation of images and attributes for generalized zero-shot learning

no code implementations ICLR 2019 Masahiro Suzuki, Yusuke Iwasawa, Yutaka Matsuo

To solve this, we propose a concept to learn a mapping that embeds both images and attributes to the shared representation space that can be generalized even for unseen classes by interpolating from the information of seen classes, which we refer to shared manifold learning.

Generalized Zero-Shot Learning

Unnatural Error Correction: GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text

no code implementations30 Nov 2023 Qi Cao, Takeshi Kojima, Yutaka Matsuo, Yusuke Iwasawa

While Large Language Models (LLMs) have achieved remarkable performance in many tasks, much about their inner workings remains unclear.

Grokking Tickets: Lottery Tickets Accelerate Grokking

1 code implementation30 Oct 2023 Gouki Minegishi, Yusuke Iwasawa, Yutaka Matsuo

We aim to analyze the mechanism of grokking from the lottery ticket hypothesis, identifying the process to find the lottery tickets (good sparse subnetworks) as the key to describing the transitional phase between memorization and generalization.

Image Classification Memorization

Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4

1 code implementation29 Sep 2023 Jiaxian Guo, Bo Yang, Paul Yoo, Bill Yuchen Lin, Yusuke Iwasawa, Yutaka Matsuo

Unlike perfect information games, where all elements are known to every player, imperfect information games emulate the real-world complexities of decision-making under uncertain or incomplete information.

Card Games Decision Making +1

GenDOM: Generalizable One-shot Deformable Object Manipulation with Parameter-Aware Policy

no code implementations16 Sep 2023 So Kuroki, Jiaxian Guo, Tatsuya Matsushima, Takuya Okubo, Masato Kobayashi, Yuya Ikeda, Ryosuke Takanami, Paul Yoo, Yutaka Matsuo, Yusuke Iwasawa

Due to the inherent uncertainty in their deformability during motion, previous methods in deformable object manipulation, such as rope and cloth, often required hundreds of real-world demonstrations to train a manipulation policy for each object, which hinders their applications in our ever-changing world.

Deformable Object Manipulation

GenORM: Generalizable One-shot Rope Manipulation with Parameter-Aware Policy

no code implementations14 Jun 2023 So Kuroki, Jiaxian Guo, Tatsuya Matsushima, Takuya Okubo, Masato Kobayashi, Yuya Ikeda, Ryosuke Takanami, Paul Yoo, Yutaka Matsuo, Yusuke Iwasawa

To achieve this, we augment the policy by conditioning it on deformable rope parameters and training it with a diverse range of simulated deformable ropes so that the policy can adjust actions based on different rope parameters.

Paste, Inpaint and Harmonize via Denoising: Subject-Driven Image Editing with Pre-Trained Diffusion Model

no code implementations13 Jun 2023 Xin Zhang, Jiaxian Guo, Paul Yoo, Yutaka Matsuo, Yusuke Iwasawa

To guarantee the visual coherence of the generated or edited image, we introduce an inpainting and harmonizing module to guide the pre-trained diffusion model to seamlessly blend the inserted subject into the scene naturally.

Denoising Image Generation +1

Multimodal Sequential Generative Models for Semi-Supervised Language Instruction Following

no code implementations29 Dec 2022 Kei Akuzawa, Yusuke Iwasawa, Yutaka Matsuo

This paper proposes using multimodal generative models for semi-supervised learning in the instruction following tasks.

Instruction Following

Realtime Fewshot Portrait Stylization Based On Geometric Alignment

no code implementations28 Nov 2022 Xinrui Wang, Zhuoru Li, Xiao Zhou, Yusuke Iwasawa, Yutaka Matsuo

Previous learning based stylization methods suffer from the geometric and semantic gaps between portrait domain and style domain, which obstacles the style information to be correctly transferred to the portrait images, leading to poor stylization quality.

A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation

1 code implementation25 Nov 2022 Hiroki Furuta, Yusuke Iwasawa, Yutaka Matsuo, Shixiang Shane Gu

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 domains such as continuous control.

Continuous Control Imitation Learning

Langevin Autoencoders for Learning Deep Latent Variable Models

1 code implementation15 Sep 2022 Shohei Taniguchi, Yusuke Iwasawa, Wataru Kumagai, Yutaka Matsuo

Based on the ALD, we also present a new deep latent variable model named the Langevin autoencoder (LAE).

Image Generation valid +1

World Robot Challenge 2020 -- Partner Robot: A Data-Driven Approach for Room Tidying with Mobile Manipulator

no code implementations20 Jul 2022 Tatsuya Matsushima, Yuki Noguchi, Jumpei Arima, Toshiki Aoki, Yuki Okita, Yuya Ikeda, Koki Ishimoto, Shohei Taniguchi, Yuki Yamashita, Shoichi Seto, Shixiang Shane Gu, Yusuke Iwasawa, Yutaka Matsuo

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 robust deployment in the presence of humans. The Partner Robot Challenge in World Robot Challenge (WRC) 2020, a global competition held in September 2021, benchmarked tidying tasks in the real home environments, and importantly, tested for full system performances. For this challenge, we developed an entire household service robot system, which leverages a data-driven approach to adapt to numerous edge cases that occur during the execution, instead of classical manual pre-programmed solutions.

Motion Planning

Large Language Models are Zero-Shot Reasoners

2 code implementations24 May 2022 Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, Yusuke Iwasawa

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-specific exemplars.

Arithmetic Reasoning Date Understanding +3

Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization

no code implementations NeurIPS 2021 Yusuke Iwasawa, Yutaka Matsuo

This paper presents a new algorithm for domain generalization (DG), \textit{test-time template adjuster (T3A)}, aiming to robustify a model to unknown distribution shift.

Domain Generalization Stochastic Optimization +1

Domain Prompt Learning for Efficiently Adapting CLIP to Unseen Domains

1 code implementation25 Nov 2021 Xin Zhang, Shixiang Shane Gu, Yutaka Matsuo, Yusuke Iwasawa

We propose Domain Prompt Learning (DPL) as a novel approach for domain inference in the form of conditional prompt generation.

Domain Generalization Image Classification +2

Improving the Robustness to Variations of Objects and Instructions with a Neuro-Symbolic Approach for Interactive Instruction Following

no code implementations13 Oct 2021 Kazutoshi Shinoda, Yuki Takezawa, Masahiro Suzuki, Yusuke Iwasawa, Yutaka Matsuo

An interactive instruction following task has been proposed as a benchmark for learning to map natural language instructions and first-person vision into sequences of actions to interact with objects in 3D environments.

Instruction Following

Estimating Disentangled Belief about Hidden State and Hidden Task for Meta-RL

no code implementations14 May 2021 Kei Akuzawa, Yusuke Iwasawa, Yutaka Matsuo

Therefore, the meta-RL agent faces the challenge of specifying both the hidden task and states based on small amount of experience.

Inductive Bias Meta Reinforcement Learning

Group Equivariant Conditional Neural Processes

no code implementations ICLR 2021 Makoto Kawano, Wataru Kumagai, Akiyoshi Sannai, Yusuke Iwasawa, Yutaka Matsuo

We present the group equivariant conditional neural process (EquivCNP), a meta-learning method with permutation invariance in a data set as in conventional conditional neural processes (CNPs), and it also has transformation equivariance in data space.

Meta-Learning Translation

Wheelchair Behavior Recognition for Visualizing Sidewalk Accessibility by Deep Neural Networks

no code implementations11 Jan 2021 Takumi Watanabe, Hiroki Takahashi, Goh Sato, Yusuke Iwasawa, Yutaka Matsuo, Ikuko Eguchi Yairi

This paper introduces our methodology to estimate sidewalk accessibilities from wheelchair behavior via a triaxial accelerometer in a smartphone installed under a wheelchair seat.

Learning Deep Latent Variable Models via Amortized Langevin Dynamics

no code implementations1 Jan 2021 Shohei Taniguchi, Yusuke Iwasawa, Yutaka Matsuo

Developing a latent variable model and an inference model with neural networks, yields Langevin autoencoders (LAEs), a novel Langevin-based framework for deep generative models.

Unsupervised Anomaly Detection

Information Theoretic Regularization for Learning Global Features by Sequential VAE

no code implementations1 Jan 2021 Kei Akuzawa, Yusuke Iwasawa, Yutaka Matsuo

However, by analyzing the sequential VAEs from the information theoretic perspective, we can claim that simply maximizing the MI encourages the latent variables to have redundant information and prevents the disentanglement of global and local features.


Graph-based Knowledge Tracing: Modeling Student Proficiency Using Graph Neural Network

1 code implementation ACM 2019 Hiromi Nakagawa, Yusuke Iwasawa, Yutaka Matsuo

Inspired by the recent successes of the graph neural network (GNN), we herein propose a GNN-based knowledge tracing method, i. e., graph-based knowledge tracing.

Inductive Bias Knowledge Tracing +2

Stablizing Adversarial Invariance Induction by Discriminator Matching

no code implementations25 Sep 2019 Yusuke Iwasawa, Kei Akuzawa, Yutaka Matsuo

An adversarial invariance induction (AII) shows its power on this purpose, which maximizes the proxy of the conditional entropy between representations and attributes by adversarial training between an attribute discriminator and feature extractor.

Domain Generalization Fairness +1

Adversarial Invariant Feature Learning with Accuracy Constraint for Domain Generalization

no code implementations29 Apr 2019 Kei Akuzawa, Yusuke Iwasawa, Yutaka Matsuo

However, previous domain-invariance-based methods overlooked the underlying dependency of classes on domains, which is responsible for the trade-off between classification accuracy and domain invariance.

Domain Generalization

Invariant Feature Learning by Attribute Perception Matching

no code implementations ICLR Workshop LLD 2019 Yusuke Iwasawa, Kei Akuzawa, Yutaka Matsuo

An adversarial feature learning (AFL) is a powerful framework to learn representations invariant to a nuisance attribute, which uses an adversarial game between a feature extractor and a categorical attribute classifier.

Domain Generalization via Invariant Representation under Domain-Class Dependency

no code implementations27 Sep 2018 Kei Akuzawa, Yusuke Iwasawa, Yutaka Matsuo

Learning domain-invariant representation is a dominant approach for domain generalization, where we need to build a classifier that is robust toward domain shifts induced by change of users, acoustic or lighting conditions, etc.

Domain Generalization

Expressive Speech Synthesis via Modeling Expressions with Variational Autoencoder

no code implementations6 Apr 2018 Kei Akuzawa, Yusuke Iwasawa, Yutaka Matsuo

Recent advances in neural autoregressive models have improve the performance of speech synthesis (SS).

Expressive Speech Synthesis

Neuron as an Agent

no code implementations ICLR 2018 Shohei Ohsawa, Kei Akuzawa, Tatsuya Matsushima, Gustavo Bezerra, Yusuke Iwasawa, Hiroshi Kajino, Seiya Takenaka, Yutaka Matsuo

Existing multi-agent reinforcement learning (MARL) communication methods have relied on a trusted third party (TTP) to distribute reward to agents, leaving them inapplicable in peer-to-peer environments.

counterfactual Multi-agent Reinforcement Learning +3

Censoring Representations with Multiple-Adversaries over Random Subspaces

no code implementations ICLR 2018 Yusuke Iwasawa, Kotaro Nakayama, Yutaka Matsuo

AFL learn such a representations by training the networks to deceive the adversary that predict the sensitive information from the network, and therefore, the success of the AFL heavily relies on the choice of the adversary.

Cannot find the paper you are looking for? You can Submit a new open access paper.