Search Results for author: Harold Soh

Found 33 papers, 17 papers with code

Extract, Define, Canonicalize: An LLM-based Framework for Knowledge Graph Construction

no code implementations5 Apr 2024 BoWen Zhang, Harold Soh

A principal issue is that in prior methods, the KG schema has to be included in the LLM prompt to generate valid triplets; larger and more complex schema easily exceed the LLMs' context window length.

graph construction Open Information Extraction

Behavioral Refinement via Interpolant-based Policy Diffusion

no code implementations25 Feb 2024 Kaiqi Chen, Eugene Lim, Kelvin Lin, Yiyang Chen, Harold Soh

However, the target policy to be learned is often significantly different from Gaussian and this mismatch can result in poor performance when using a small number of diffusion steps (to improve inference speed) and under limited data.

Imitation Learning

Probable Object Location (POLo) Score Estimation for Efficient Object Goal Navigation

no code implementations14 Nov 2023 JiaMing Wang, Harold Soh

To advance the field of autonomous robotics, particularly in object search tasks within unexplored environments, we introduce a novel framework centered around the Probable Object Location (POLo) score.


Latent Emission-Augmented Perspective-Taking (LEAPT) for Human-Robot Interaction

no code implementations12 Aug 2023 Kaiqi Chen, Jing Yu Lim, Kingsley Kuan, Harold Soh

Perspective-taking is the ability to perceive or understand a situation or concept from another individual's point of view, and is crucial in daily human interactions.

Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models

1 code implementation NeurIPS 2023 Alvin Heng, Harold Soh

The recent proliferation of large-scale text-to-image models has led to growing concerns that such models may be misused to generate harmful, misleading, and inappropriate content.

Continual Learning

Generative Modeling with Flow-Guided Density Ratio Learning

1 code implementation7 Mar 2023 Alvin Heng, Abdul Fatir Ansari, Harold Soh

We present Flow-Guided Density Ratio Learning (FDRL), a simple and scalable approach to generative modeling which builds on the stale (time-independent) approximation of the gradient flow of entropy-regularized f-divergences introduced in DGflow.

Image-to-Image Translation

Large Language Models as Zero-Shot Human Models for Human-Robot Interaction

1 code implementation6 Mar 2023 BoWen Zhang, Harold Soh

In this work, we explore the potential of large-language models (LLMs) -- which have consumed vast amounts of human-generated text data -- to act as zero-shot human models for HRI.

Translating Natural Language to Planning Goals with Large-Language Models

1 code implementation10 Feb 2023 Yaqi Xie, Chen Yu, Tongyao Zhu, Jinbin Bai, Ze Gong, Harold Soh

Recent large language models (LLMs) have demonstrated remarkable performance on a variety of natural language processing (NLP) tasks, leading to intense excitement about their applicability across various domains.


Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Series

1 code implementation26 Jan 2023 Abdul Fatir Ansari, Alvin Heng, Andre Lim, Harold Soh

Learning accurate predictive models of real-world dynamic phenomena (e. g., climate, biological) remains a challenging task.

Bayesian Inference Imputation +2

Safety-Constrained Policy Transfer with Successor Features

no code implementations10 Nov 2022 Zeyu Feng, BoWen Zhang, Jianxin Bi, Harold Soh

In this work, we focus on the problem of safe policy transfer in reinforcement learning: we seek to leverage existing policies when learning a new task with specified constraints.

SCALES: From Fairness Principles to Constrained Decision-Making

1 code implementation22 Sep 2022 Sreejith Balakrishnan, Jianxin Bi, Harold Soh

This paper proposes SCALES, a general framework that translates well-established fairness principles into a common representation based on the Constraint Markov Decision Process (CMDP).

Decision Making Fairness

MIRROR: Differentiable Deep Social Projection for Assistive Human-Robot Communication

1 code implementation6 Mar 2022 Kaiqi Chen, Jeffrey Fong, Harold Soh

In this work, we present MIRROR, an approach to (i) quickly learn human models from human demonstrations, and (ii) use the models for subsequent communication planning in assistive shared-control settings.

Imitation Learning

Deep Explicit Duration Switching Models for Time Series

1 code implementation NeurIPS 2021 Abdul Fatir Ansari, Konstantinos Benidis, Richard Kurle, Ali Caner Turkmen, Harold Soh, Alexander J. Smola, Yuyang Wang, Tim Januschowski

We propose the Recurrent Explicit Duration Switching Dynamical System (RED-SDS), a flexible model that is capable of identifying both state- and time-dependent switching dynamics.

Time Series Time Series Analysis

Embedding Symbolic Temporal Knowledge into Deep Sequential Models

no code implementations28 Jan 2021 Yaqi Xie, Fan Zhou, Harold Soh

However, when data is limited, simpler models such as logic/rule-based methods work surprisingly well, especially when relevant prior knowledge is applied in their construction.

Action Recognition Imitation Learning +2

Refining Deep Generative Models via Discriminator Gradient Flow

1 code implementation ICLR 2021 Abdul Fatir Ansari, Ming Liang Ang, Harold Soh

We introduce Discriminator Gradient flow (DGflow), a new technique that improves generated samples via the gradient flow of entropy-regularized f-divergences between the real and the generated data distributions.

Image Generation Text Generation

Getting to Know One Another: Calibrating Intent, Capabilities and Trust for Human-Robot Collaboration

1 code implementation3 Aug 2020 Joshua Lee, Jeffrey Fong, Bing Cai Kok, Harold Soh

Common experience suggests that agents who know each other well are better able to work together.

TactileSGNet: A Spiking Graph Neural Network for Event-based Tactile Object Recognition

1 code implementation1 Aug 2020 Fuqiang Gu, Weicong Sng, Tasbolat Taunyazov, Harold Soh

In this paper, we propose a novel spiking graph neural network for event-based tactile object recognition.

Object Recognition

The Evolutionary Dynamics of Independent Learning Agents in Population Games

no code implementations29 Jun 2020 Shuyue Hu, Chin-Wing Leung, Ho-fung Leung, Harold Soh

Understanding the evolutionary dynamics of reinforcement learning under multi-agent settings has long remained an open problem.

ST-MNIST -- The Spiking Tactile MNIST Neuromorphic Dataset

no code implementations8 May 2020 Hian Hian See, Brian Lim, Si Li, Haicheng Yao, Wen Cheng, Harold Soh, Benjamin C. K. Tee

We anticipate that our ST-MNIST dataset will be of interest and useful to the neuromorphic and robotics research communities.

A Characteristic Function Approach to Deep Implicit Generative Modeling

1 code implementation CVPR 2020 Abdul Fatir Ansari, Jonathan Scarlett, Harold Soh

In this paper, we formulate the problem of learning an IGM as minimizing the expected distance between characteristic functions.

Image Generation

Robot Capability and Intention in Trust-based Decisions across Tasks

no code implementations3 Sep 2019 Yaqi Xie, Indu P Bodala, Desmond C. Ong, David Hsu, Harold Soh

In this paper, we present results from a human-subject study designed to explore two facets of human mental models of robots---inferred capability and intention---and their relationship to overall trust and eventual decisions.

Embedding Symbolic Knowledge into Deep Networks

1 code implementation NeurIPS 2019 Yaqi Xie, Ziwei Xu, Mohan S. Kankanhalli, Kuldeep S. Meel, Harold Soh

Interestingly, we observe a connection between the tractability of the propositional theory representation and the ease of embedding.

Graph Embedding Representation Learning

Factorized Inference in Deep Markov Models for Incomplete Multimodal Time Series

no code implementations30 May 2019 Tan Zhi-Xuan, Harold Soh, Desmond C. Ong

Integrating deep learning with latent state space models has the potential to yield temporal models that are powerful, yet tractable and interpretable.

Time Series Time Series Analysis +1

Applying Probabilistic Programming to Affective Computing

1 code implementation15 Mar 2019 Desmond C. Ong, Harold Soh, Jamil Zaki, Noah D. Goodman

Affective Computing is a rapidly growing field spurred by advancements in artificial intelligence, but often, held back by the inability to translate psychological theories of emotion into tractable computational models.

Probabilistic Programming

Hyperprior Induced Unsupervised Disentanglement of Latent Representations

2 code implementations12 Sep 2018 Abdul Fatir Ansari, Harold Soh

We address the problem of unsupervised disentanglement of latent representations learnt via deep generative models.


Trust-Aware Decision Making for Human-Robot Collaboration: Model Learning and Planning

no code implementations12 Jan 2018 Min Chen, Stefanos Nikolaidis, Harold Soh, David Hsu, Siddhartha Srinivasa

The trust-POMDP model provides a principled approach for the robot to (i) infer the trust of a human teammate through interaction, (ii) reason about the effect of its own actions on human trust, and (iii) choose actions that maximize team performance over the long term.

Decision Making

Probabilistic Network Metrics: Variational Bayesian Network Centrality

no code implementations15 Sep 2014 Harold Soh

The sparse variational Bayesian centrality Gaussian process (VBC-GP) learns a mapping between node attributes to latent centrality and hence, is capable of predicting centralities from node features and can potentially represent a large number of nodes using only a limited number of inducing inputs.

Gaussian Processes

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