79 citations · 218 across the 30 of their papers we have counts for
31 papers
GRaCE: Balancing Multiple Criteria to Achieve Stable, Collision-Free, and Functional Grasps
Tasbolat Taunyazov, Kelvin Lin, Harold Soh
This paper addresses the multi-faceted problem of robot grasping, where multiple criteria may conflict and differ in importance. We introduce a probabilistic framework, Grasp Ranki…
Latent Emission-Augmented Perspective-Taking (LEAPT) for Human-Robot Interaction
Kaiqi Chen, Jing Yu Lim, Kingsley Kuan +1
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. Enabling rob…
Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models
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.…
Generative Modeling with Flow-Guided Density Ratio Learning
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 gradie…
Large Language Models as Zero-Shot Human Models for Human-Robot Interaction
Bowen Zhang, Harold Soh
Human models play a crucial role in human-robot interaction (HRI), enabling robots to consider the impact of their actions on people and plan their behavior accordingly. However, c…
Translating Natural Language to Planning Goals with Large-Language Models
Yaqi Xie, Chen Yu, Tongyao Zhu +3
Recent large language models (LLMs) have demonstrated remarkable performance on a variety of natural language processing (NLP) tasks, leading to intense excitement about their appl…
Heterogeneous Beliefs and Multi-Population Learning in Network Games
Shuyue Hu, Harold Soh, Georgios Piliouras
The effect of population heterogeneity in multi-agent learning is practically relevant but remains far from being well-understood. Motivated by this, we introduce a model of multi-…
Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Series
Abdul Fatir Ansari, Alvin Heng, Andre Lim +1
Learning accurate predictive models of real-world dynamic phenomena (e.g., climate, biological) remains a challenging task. One key issue is that the data generated by both natural…
Safety-Constrained Policy Transfer with Successor Features
Zeyu Feng, Bowen Zhang, Jianxin Bi +1
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.…
Observed Adversaries in Deep Reinforcement Learning
Eugene Lim, Harold Soh
In this work, we point out the problem of observed adversaries for deep policies. Specifically, recent work has shown that deep reinforcement learning is susceptible to adversarial…
SCALES: From Fairness Principles to Constrained Decision-Making
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 (C…
MIRROR: Differentiable Deep Social Projection for Assistive Human-Robot Communication
Kaiqi Chen, Jeffrey Fong, Harold Soh
Communication is a hallmark of intelligence. In this work, we present MIRROR, an approach to (i) quickly learn human models from human demonstrations, and (ii) use the models for s…
The Dynamics of Q-learning in Population Games: a Physics-Inspired Continuity Equation Model
Shuyue Hu, Chin-Wing Leung, Ho-fung Leung +1
Although learning has found wide application in multi-agent systems, its effects on the temporal evolution of a system are far from understood. This paper focuses on the dynamics o…
Deep Explicit Duration Switching Models for Time Series
Abdul Fatir Ansari, Konstantinos Benidis, Richard Kurle +5
Many complex time series can be effectively subdivided into distinct regimes that exhibit persistent dynamics. Discovering the switching behavior and the statistical patterns in th…
Multi-Modal Mutual Information (MuMMI) Training for Robust Self-Supervised Deep Reinforcement Learning
Kaiqi Chen, Yong Lee, Harold Soh
This work focuses on learning useful and robust deep world models using multiple, possibly unreliable, sensors. We find that current methods do not sufficiently encourage a shared…
Embedding Symbolic Temporal Knowledge into Deep Sequential Models
Yaqi Xie, Fan Zhou, Harold Soh
Sequences and time-series often arise in robot tasks, e.g., in activity recognition and imitation learning. In recent years, deep neural networks (DNNs) have emerged as an effectiv…
Refining Deep Generative Models via Discriminator Gradient Flow
Abdul Fatir Ansari, Ming Liang Ang, Harold Soh
Deep generative modeling has seen impressive advances in recent years, to the point where it is now commonplace to see simulated samples (e.g., images) that closely resemble real-w…
Efficient Exploration of Reward Functions in Inverse Reinforcement Learning via Bayesian Optimization
Sreejith Balakrishnan, Quoc Phong Nguyen, Bryan Kian Hsiang Low +1
The problem of inverse reinforcement learning (IRL) is relevant to a variety of tasks including value alignment and robot learning from demonstration. Despite significant algorithm…
Event-Driven Visual-Tactile Sensing and Learning for Robots
Tasbolat Taunyazov, Weicong Sng, Hian Hian See +5
This work contributes an event-driven visual-tactile perception system, comprising a novel biologically-inspired tactile sensor and multi-modal spike-based learning. Our neuromorph…
Getting to Know One Another: Calibrating Intent, Capabilities and Trust for Human-Robot Collaboration
Joshua Lee, Jeffrey Fong, Bing Cai Kok +1
Common experience suggests that agents who know each other well are better able to work together. In this work, we address the problem of calibrating intention and capabilities in…
TactileSGNet: A Spiking Graph Neural Network for Event-based Tactile Object Recognition
Fuqiang Gu, Weicong Sng, Tasbolat Taunyazov +1
Tactile perception is crucial for a variety of robot tasks including grasping and in-hand manipulation. New advances in flexible, event-driven, electronic skins may soon endow robo…
The Evolutionary Dynamics of Independent Learning Agents in Population Games
Shuyue Hu, Chin-Wing Leung, Ho-fung Leung +1
Understanding the evolutionary dynamics of reinforcement learning under multi-agent settings has long remained an open problem. While previous works primarily focus on 2-player gam…
ST-MNIST -- The Spiking Tactile MNIST Neuromorphic Dataset
Hian Hian See, Brian Lim, Si Li +4
Tactile sensing is an essential modality for smart robots as it enables them to interact flexibly with physical objects in their environment. Recent advancements in electronic skin…
Embedding Symbolic Knowledge into Deep Networks
Yaqi Xie, Ziwei Xu, Mohan S. Kankanhalli +2
In this work, we aim to leverage prior symbolic knowledge to improve the performance of deep models. We propose a graph embedding network that projects propositional formulae (and…