1 code implementation • 2 Feb 2025 • Wenzheng Jiang, Ji Wang, Xiongtao Zhang, Weidong Bao, Cheston Tan, Flint Xiaofeng Fan
Federated Reinforcement Learning (FedRL) improves sample efficiency while preserving privacy; however, most existing studies assume homogeneous agents, limiting its applicability in real-world scenarios.
1 code implementation • 20 Dec 2024 • Flint Xiaofeng Fan, Cheston Tan, Yew-Soon Ong, Roger Wattenhofer, Wei-Tsang Ooi
In the era of increasing privacy concerns and demand for personalized experiences, traditional Reinforcement Learning with Human Feedback (RLHF) frameworks face significant challenges due to their reliance on centralized data.
no code implementations • 20 Nov 2024 • Shantanu Jaiswal, Debaditya Roy, Basura Fernando, Cheston Tan
Complex visual reasoning and question answering (VQA) is a challenging task that requires compositional multi-step processing and higher-level reasoning capabilities beyond the immediate recognition and localization of objects and events.
no code implementations • 12 Nov 2024 • Shang Hong Sim, Clarence Lee, Alvin Tan, Cheston Tan
Understanding spatial relations is a crucial cognitive ability for both humans and AI.
1 code implementation • 9 Sep 2024 • Dylan Hillier, Leon Guertler, Bobby Cheng, Cheston Tan
In this work we explore the relevance of dropout for modern language models, particularly in the context of models on the scale of <100M parameters.
no code implementations • 28 Aug 2024 • Ruirui Chen, Weifeng Jiang, Chengwei Qin, Ishaan Singh Rawal, Cheston Tan, Dongkyu Choi, Bo Xiong, Bo Ai
The important challenge of keeping knowledge in Large Language Models (LLMs) up-to-date has led to the development of various methods for incorporating new facts.
no code implementations • 27 Aug 2024 • Aishik Nagar, Shantanu Jaiswal, Cheston Tan
We focus on two novel aspects of zero-shot visual reasoning: i) evaluating the impact of conveying scene information as either visual embeddings or purely textual scene descriptions to the underlying large language model (LLM) of the VLM, and ii) comparing the effectiveness of chain-of-thought prompting to standard prompting for zero-shot visual reasoning.
no code implementations • 31 Jul 2024 • Dylan Hillier, Cheston Tan, Jing Jiang
As children, we imitate our parents' speech patterns until we are able to produce sounds; we learn from them praising us and scolding us; and as adults, we learn by working with others.
no code implementations • 1 Jul 2024 • Bo Ai, Stephen Tian, Haochen Shi, YiXuan Wang, Cheston Tan, Yunzhu Li, Jiajun Wu
Tactile feedback is critical for understanding the dynamics of both rigid and deformable objects in many manipulation tasks, such as non-prehensile manipulation and dense packing.
1 code implementation • 23 May 2024 • Dylan Hillier, Leon Guertler, Cheston Tan, Palaash Agrawal, Chen Ruirui, Bobby Cheng
The rapid advancement of large language models (LLMs) has led to significant improvements in natural language processing but also poses challenges due to their high computational and energy demands.
1 code implementation • 29 Mar 2024 • Hei Yi Mak, Flint Xiaofeng Fan, Luca A. Lanzendörfer, Cheston Tan, Wei Tsang Ooi, Roger Wattenhofer
CAESAR is an aggregation strategy used by the server that combines convergence-aware sampling with a screening mechanism.
1 code implementation • 2 Feb 2024 • Palaash Agrawal, Shavak Vasania, Cheston Tan
We highlight various limitations, biases and properties of LLMs through this benchmarking process, such as an inverse relation to the average degrees of freedom of traversal per node in graphs, the overall negative impact of k-shot prompting on graph reasoning tasks, and a positive response bias which prevents LLMs from identifying the absence of a valid solution.
no code implementations • 13 Oct 2023 • Palaash Agrawal, Cheston Tan, Heena Rathore
In this review paper, we focus on the cognitive functions of perception, which is the process of taking signals from one's surroundings as input, and processing them to understand the environment.
1 code implementation • 13 Sep 2023 • Palaash Agrawal, Haidi Azaman, Cheston Tan
In addition to spatial relations, we also propose 50K visual depictions across 10 temporal relations, consisting of videos depicting event/time-point interactions.
1 code implementation • 8 Sep 2023 • Zijun Lin, Haidi Azaman, M Ganesh Kumar, Cheston Tan
Overall, our results are the first to demonstrate that RL agents can be trained to implicitly learn concepts and compositionality, to solve more complex environments in zero-shot fashion.
1 code implementation • ICCV 2023 • Clarence Lee, M Ganesh Kumar, Cheston Tan
We find that current state-of-the-art visual grounding models do not perform well on the dataset, highlighting the limitations of existing models on reference and quantification tasks.
no code implementations • 15 Jun 2023 • Ishaan Singh Rawal, Alexander Matyasko, Shantanu Jaiswal, Basura Fernando, Cheston Tan
Consistent with the findings of QUAG, we find that most of the models achieve near-trivial performance on CLAVI.
no code implementations • 6 Mar 2023 • Jenny Zhang, Samson Yu, Jiafei Duan, Cheston Tan
This paper presents a framework for training an agent to actively request help in object-goal navigation tasks, with feedback indicating the location of the target object in its field of view.
no code implementations • 26 Jan 2023 • Flint Xiaofeng Fan, Yining Ma, Zhongxiang Dai, Cheston Tan, Bryan Kian Hsiang Low, Roger Wattenhofer
Federated Reinforcement Learning (FedRL) encourages distributed agents to learn collectively from each other's experience to improve their performance without exchanging their raw trajectories.
1 code implementation • 24 Oct 2022 • Clement Tan, Chai Kiat Yeo, Cheston Tan, Basura Fernando
In this paper, we introduce "Abductive Past Action Inference", a novel research task aimed at identifying the past actions performed by individuals within homes to reach specific states captured in a single image, using abductive inference.
no code implementations • 21 Jun 2022 • Jiafei Duan, Samson Yu, Nicholas Tan, Li Yi, Cheston Tan
Humans with an average level of social cognition can infer the beliefs of others based solely on the nonverbal communication signals (e. g. gaze, gesture, pose and contextual information) exhibited during social interactions.
1 code implementation • 20 Jun 2022 • Jenny Zhang, Samson Yu, Jiafei Duan, Cheston Tan
In reality, it is often more efficient to ask for help than to search the entire space to find an object with an unknown location.
no code implementations • 10 Jun 2022 • Jieyi Ye, Jiafei Duan, Samson Yu, Bihan Wen, Cheston Tan
How can the most common 1, 000 concepts (89\% of everyday use) be learnt in a naturalistic children's setting?
no code implementations • 14 Feb 2022 • Jiafei Duan, Arijit Dasgupta, Jason Fischer, Cheston Tan
Despite the wide range of work in physical reasoning for machine cognition, there is a scarcity of reviews that organize and group these deep learning approaches.
1 code implementation • 26 Nov 2021 • Shantanu Jaiswal, Basura Fernando, Cheston Tan
Attention modules for Convolutional Neural Networks (CNNs) are an effective method to enhance performance on multiple computer-vision tasks.
no code implementations • 16 Nov 2021 • Arijit Dasgupta, Jiafei Duan, Marcelo H. Ang Jr, Yi Lin, Su-hua Wang, Renée Baillargeon, Cheston Tan
Recent work in computer vision and cognitive reasoning has given rise to an increasing adoption of the Violation-of-Expectation (VoE) paradigm in synthetic datasets.
2 code implementations • NeurIPS 2021 • Flint Xiaofeng Fan, Yining Ma, Zhongxiang Dai, Wei Jing, Cheston Tan, Bryan Kian Hsiang Low
The growing literature of Federated Learning (FL) has recently inspired Federated Reinforcement Learning (FRL) to encourage multiple agents to federatively build a better decision-making policy without sharing raw trajectories.
1 code implementation • 12 Oct 2021 • Arijit Dasgupta, Jiafei Duan, Marcelo H. Ang Jr, Cheston Tan
Recent work in cognitive reasoning and computer vision has engendered an increasing popularity for the Violation-of-Expectation (VoE) paradigm in synthetic datasets.
no code implementations • 10 Sep 2021 • Jiafei Duan, Samson Yu, Soujanya Poria, Bihan Wen, Cheston Tan
However, there is a lack of intuitive physics models that are tested on long physical interaction sequences with multiple interactions among different objects.
Ranked #1 on
Semantic Object Interaction Classification
on SPACE
2 code implementations • 13 Aug 2021 • Jiafei Duan, Samson Yu Bai Jian, Cheston Tan
We then further evaluate it with a state-of-the-art physics-based deep model and show that the SPACE dataset improves the learning of intuitive physics with an approach inspired by curriculum learning.
1 code implementation • 25 Jun 2021 • M Ganesh Kumar, Cheston Tan, Camilo Libedinsky, Shih-Cheng Yen, Andrew Yong-Yi Tan
Biologically plausible classic actor-critic agents have been shown to learn to navigate to single reward locations, but which biologically plausible agents are able to learn multiple cue-reward location tasks has remained unclear.
2 code implementations • 7 Jun 2021 • M Ganesh Kumar, Cheston Tan, Camilo Libedinsky, Shih-Cheng Yen, Andrew Yong-Yi Tan
Rodent one-shot learning in a multiple paired association navigation task has been postulated to be schema-dependent.
no code implementations • 8 Mar 2021 • Jiafei Duan, Samson Yu, Hui Li Tan, Hongyuan Zhu, Cheston Tan
This paper aims to provide an encyclopedic survey for the field of embodied AI, from its simulators to its research.
1 code implementation • 3 Oct 2020 • Jiafei Duan, Samson Yu, Hui Li Tan, Cheston Tan
The problem of task planning for artificial agents remains largely unsolved.
no code implementations • 11 Dec 2019 • Tianying Wang, Hao Zhang, Wei Qi Toh, Hongyuan Zhu, Cheston Tan, Yan Wu, Yong liu, Wei Jing
The proposed method is able to efficiently generalize the previously learned task by model fusion to solve the environment adaptation problem.
no code implementations • 24 Sep 2019 • Yi Cheng, Hongyuan Zhu, Ying Sun, Cihan Acar, Wei Jing, Yan Wu, Liyuan Li, Cheston Tan, Joo-Hwee Lim
To our best knowledge, this is the first work to explore effective intra- and inter-modality fusion in 6D pose estimation.
no code implementations • CVPR 2019 • Arushi Goel, Keng Teck Ma, Cheston Tan
Inferring the social context in a given visual scene not only involves recognizing objects, but also demands a more in-depth understanding of the relationships and attributes of the people involved.
no code implementations • 5 Aug 2015 • Fabio Anselmi, Lorenzo Rosasco, Cheston Tan, Tomaso Poggio
In i-theory a typical layer of a hierarchical architecture consists of HW modules pooling the dot products of the inputs to the layer with the transformations of a few templates under a group.
no code implementations • 15 Jun 2014 • Cheston Tan, Tomaso Poggio
The main aim of this work is to further the fundamental understanding of what causes the visual processing of faces to be different from that of objects.
no code implementations • NeurIPS 2013 • Cheston Tan, Jedediah M. Singer, Thomas Serre, David Sheinberg, Tomaso Poggio
The macaque Superior Temporal Sulcus (STS) is a brain area that receives and integrates inputs from both the ventral and dorsal visual processing streams (thought to specialize in form and motion processing respectively).