Search Results for author:
Found 41 papers, 14 papers with code
Learning shared manifold representation of images and attributes for generalized zero-shot learning
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.
ADOPT: Modified Adam Can Converge with Any $β_2$ with the Optimal Rate
Adam is one of the most popular optimization algorithms in deep learning.
Which Programming Language and What Features at Pre-training Stage Affect Downstream Logical Inference Performance?
In addition, we found that models trained with programming languages exhibit a better ability to follow instructions compared to those trained with natural languages.
Answer When Needed, Forget When Not: Language Models Pretend to Forget via In-Context Knowledge Unlearning
As large language models (LLMs) are applied across diverse domains, the ability to selectively unlearn specific information has become increasingly essential.
Language Models Do Hard Arithmetic Tasks Easily and Hardly Do Easy Arithmetic Tasks
The ability (and inability) of large language models (LLMs) to perform arithmetic tasks has been the subject of much theoretical and practical debate.
On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons
Additionally, we tamper with less than 1% of the total neurons in each model during inference and demonstrate that tampering with a few language-specific neurons drastically changes the probability of target language occurrence in text generation.
Towards Empirical Interpretation of Internal Circuits and Properties in Grokked Transformers on Modular Polynomials
Grokking on modular addition has been known to implement Fourier representation and its calculation circuits with trigonometric identities in Transformers.
Unnatural Error Correction: GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text
While Large Language Models (LLMs) have achieved remarkable performance in many tasks, much about their inner workings remains unclear.
Bridging Lottery ticket and Grokking: Is Weight Norm Sufficient to Explain Delayed Generalization?
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.
Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4
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.
GenDOM: Generalizable One-shot Deformable Object Manipulation with Parameter-Aware Policy
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.
GenORM: Generalizable One-shot Rope Manipulation with Parameter-Aware Policy
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
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.
End-to-end Training of Deep Boltzmann Machines by Unbiased Contrastive Divergence with Local Mode Initialization
We address the problem of biased gradient estimation in deep Boltzmann machines (DBMs).
Multimodal Sequential Generative Models for Semi-Supervised Language Instruction Following
This paper proposes using multimodal generative models for semi-supervised learning in the instruction following tasks.
Realtime Fewshot Portrait Stylization Based On Geometric Alignment
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
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.
Langevin Autoencoders for Learning Deep Latent Variable Models
Based on the ALD, we also present a new deep latent variable model named the Langevin autoencoder (LAE).
World Robot Challenge 2020 -- Partner Robot: A Data-Driven Approach for Room Tidying with Mobile Manipulator
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.
Robustifying Vision Transformer without Retraining from Scratch by Test-Time Class-Conditional Feature Alignment
Vision Transformer (ViT) is becoming more popular in image processing.
Large Language Models are Zero-Shot Reasoners
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.
Ranked #1 on
Arithmetic Reasoning
on MultiArith
Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization
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 Prompt Learning for Efficiently Adapting CLIP to Unseen Domains
We propose Domain Prompt Learning (DPL) as a novel approach for domain inference in the form of conditional prompt generation.
Ranked #1 on
Transfer Learning
on Office-Home
Improving the Robustness to Variations of Objects and Instructions with a Neuro-Symbolic Approach for Interactive Instruction Following
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.
Estimating Disentangled Belief about Hidden State and Hidden Task for Meta-RL
Therefore, the meta-RL agent faces the challenge of specifying both the hidden task and states based on small amount of experience.
Making Use of Latent Space in Language GANs for Generating Diverse Text without Pre-training
In this paper, we propose a GAN model that aims to improve the approach to generating diverse texts conditioned by the latent space.
Group Equivariant Conditional Neural Processes
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.
Wheelchair Behavior Recognition for Visualizing Sidewalk Accessibility by Deep Neural Networks
This paper introduces our methodology to estimate sidewalk accessibilities from wheelchair behavior via a triaxial accelerometer in a smartphone installed under a wheelchair seat.
Information Theoretic Regularization for Learning Global Features by Sequential VAE
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.
Learning Deep Latent Variable Models via Amortized Langevin Dynamics
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.
Character-level Japanese Text Generation with Attention Mechanism for Chest Radiography Diagnosis
And, we were confirmed from the generated findings that the proposed method was able to consider the orthographic variants.
Graph-based Knowledge Tracing: Modeling Student Proficiency Using Graph Neural Network
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.
Stablizing Adversarial Invariance Induction by Discriminator Matching
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.
Adversarial Invariant Feature Learning with Accuracy Constraint for Domain Generalization
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.
Invariant Feature Learning by Attribute Perception Matching
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.
Adversarial Feature Learning under Accuracy Constraint for Domain Generalization
Learning domain-invariant representation is a dominant approach for domain generalization.
Domain Generalization via Invariant Representation under Domain-Class Dependency
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.
Expressive Speech Synthesis via Modeling Expressions with Variational Autoencoder
Recent advances in neural autoregressive models have improve the performance of speech synthesis (SS).
Censoring Representations with Multiple-Adversaries over Random Subspaces
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.
Toward learning better metrics for sequence generation training with policy gradient
The partial reward function is a reward function for a partial sequence of a certain length.
Neuron as an Agent
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.
