1 code implementation • 20 May 2024 • Alvin Heng, Alexandre H. Thiery, Harold Soh
To that end, we introduce our method, Diffusion Paths, (DiffPath) in this work.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
1 code implementation • 7 May 2024 • Zeyu Feng, Hao Luan, Pranav Goyal, Harold Soh
Operating effectively in complex environments while complying with specified constraints is crucial for the safe and successful deployment of robots that interact with and operate around people.
no code implementations • 5 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.
no code implementations • 25 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.
no code implementations • 14 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.
no code implementations • 12 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.
no code implementations • 22 Jun 2023 • Xudong Shen, Hannah Brown, Jiashu Tao, Martin Strobel, Yao Tong, Akshay Narayan, Harold Soh, Finale Doshi-Velez
There is increasing attention being given to how to regulate AI systems.
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.
1 code implementation • 7 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.
1 code implementation • 6 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.
1 code implementation • 10 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.
1 code implementation • 26 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.
no code implementations • 10 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.
no code implementations • 13 Oct 2022 • Eugene Lim, Harold Soh
In this work, we point out the problem of observed adversaries for deep policies.
1 code implementation • 22 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).
1 code implementation • 6 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.
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.
1 code implementation • 6 Jul 2021 • Kaiqi Chen, Yong Lee, Harold Soh
This work focuses on learning useful and robust deep world models using multiple, possibly unreliable, sensors.
1 code implementation • 1 Jun 2021 • Tasbolat Taunyazov, Luar Shui Song, Eugene Lim, Hian Hian See, David Lee, Benjamin C. K. Tee, Harold Soh
Humans display the remarkable ability to sense the world through tools and other held objects.
no code implementations • 28 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.
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.
Ranked #1 on Text Generation on One Billion Word
no code implementations • NeurIPS 2020 • Sreejith Balakrishnan, Quoc Phong Nguyen, Bryan Kian Hsiang Low, Harold Soh
The problem of inverse reinforcement learning (IRL) is relevant to a variety of tasks including value alignment and robot learning from demonstration.
1 code implementation • 3 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.
1 code implementation • 1 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.
no code implementations • 29 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.
no code implementations • 8 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.
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.
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.
no code implementations • 3 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.
no code implementations • 30 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.
1 code implementation • 15 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.
2 code implementations • 12 Sep 2018 • Abdul Fatir Ansari, Harold Soh
We address the problem of unsupervised disentanglement of latent representations learnt via deep generative models.
no code implementations • 2 Aug 2018 • Vinh Vo Thanh, Harold Soh
Who would the movies appeal to?
no code implementations • 12 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.
no code implementations • 15 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.