no code implementations • 3 Apr 2025 • Hung Le, Dai Do, Dung Nguyen, Svetha Venkatesh
Recent advances in fine-tuning large language models (LLMs) with reinforcement learning (RL) have shown promising improvements in complex reasoning tasks, particularly when paired with chain-of-thought (CoT) prompting.
no code implementations • 12 Mar 2025 • Thuan Than, Nhat-Anh Nguyen-Dang, Dung Nguyen, Salwa K. Al Khatib, Ahmed Elhagry, Hai Phan, Yihui He, Zhiqiang Shen, Marios Savvides, Dang Huynh
Semi-Supervised Semantic Segmentation reduces reliance on extensive annotations by using unlabeled data and state-of-the-art models to improve overall performance.
no code implementations • 11 Nov 2024 • Thang Nguyen, Dung Nguyen, Kha Pham, Truyen Tran
Data-driven methods such as deep neural networks make no such assumptions and can capture the generative process in more detail, but fail in long-term forecasting due to data limitations.
no code implementations • 14 Oct 2024 • Hung Le, Kien Do, Dung Nguyen, Sunil Gupta, Svetha Venkatesh
To this end, we leverage the Hadamard product for calibrating and updating memory, specifically designed to enhance memory capacity while mitigating numerical and learning challenges.
no code implementations • 7 Jun 2024 • Dung Nguyen, Ariel Vetzler, Sarit Kraus, Anil Vullikanti
In each contrastive scenario, we designate a specific data point as the fixed centroid position, enabling us to measure the impact of this constraint on clustering utility under differential privacy.
no code implementations • 4 Jun 2024 • Dung Nguyen, Anil Vullikanti
A fundamental problem in SBMs is the recovery of the community structure, and sharp information-theoretic bounds are known for recoverability for many versions of SBMs.
no code implementations • 26 May 2024 • Hung Le, Quan Tran, Dung Nguyen, Kien Do, Saloni Mittal, Kelechi Ogueji, Svetha Venkatesh
Recent approaches, such as direct preference optimization (DPO), have eliminated the need for unstable and sluggish reinforcement learning optimization by introducing close-formed supervised losses.
no code implementations • 18 Apr 2024 • Hung Le, Dung Nguyen, Kien Do, Svetha Venkatesh, Truyen Tran
We propose Pointer-Augmented Neural Memory (PANM) to help neural networks understand and apply symbol processing to new, longer sequences of data.
no code implementations • 5 Feb 2024 • Kien Do, Dung Nguyen, Hung Le, Thao Le, Dang Nguyen, Haripriya Harikumar, Truyen Tran, Santu Rana, Svetha Venkatesh
To overcome this challenge, we propose to approximate \frac{1}{p(u|b)} using a biased classifier trained with "bias amplification" losses.
1 code implementation • 5 Feb 2024 • Kien Do, Duc Kieu, Toan Nguyen, Dang Nguyen, Hung Le, Dung Nguyen, Thin Nguyen
We propose a systematic training-free method to transform the probability flow of a "linear" stochastic process characterized by the equation X_{t}=a_{t}X_{0}+\sigma_{t}X_{1} into a straight constant-speed (SC) flow, reminiscent of Rectified Flow.
1 code implementation • IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024 • Vuong D. Nguyen, Khadija Khaldi, Dung Nguyen, Pranav Mantini, Shishir Shah
In this paper, we propose "Contrastive Viewpoint-aware Shape Learning for Long-term Person Re-Identification" (CVSL) to address these challenges.
Cloth-Changing Person Re-Identification
Contrastive Learning
+1
1 code implementation • 9 Aug 2023 • Hung Le, Kien Do, Dung Nguyen, Svetha Venkatesh
We present a new computing model for intrinsic rewards in reinforcement learning that addresses the limitations of existing surprise-driven explorations.
no code implementations • 17 Jan 2023 • Dung Nguyen, Phuoc Nguyen, Hung Le, Kien Do, Svetha Venkatesh, Truyen Tran
Social reasoning necessitates the capacity of theory of mind (ToM), the ability to contextualise and attribute mental states to others without having access to their internal cognitive structure.
1 code implementation • 7 Oct 2022 • Tien-Phat Nguyen, Trong-Thang Pham, Tri Nguyen, Hieu Le, Dung Nguyen, Hau Lam, Phong Nguyen, Jennifer Fowler, Minh-Triet Tran, Ngan Le
The transformer expanding path models the temporal coherency between embryo images to ensure monotonic non-decreasing constraint and is optimized by a segmentation head.
no code implementations • 21 Sep 2022 • Kien Do, Hung Le, Dung Nguyen, Dang Nguyen, Haripriya Harikumar, Truyen Tran, Santu Rana, Svetha Venkatesh
Since the EMA generator can be considered as an ensemble of the generator's old versions and often undergoes a smaller change in updates compared to the generator, training on its synthetic samples can help the student recall the past knowledge and prevent the student from adapting too quickly to new updates of the generator.
no code implementations • 21 Jul 2022 • George Z. Li, Dung Nguyen, Anil Vullikanti
Using our algorithm for Partial Set Cover as a subroutine, we give a differentially private (bicriteria) approximation algorithm for a facility location problem which generalizes $k$-center/$k$-supplier with outliers.
no code implementations • 20 Apr 2022 • Hung Le, Thommen Karimpanal George, Majid Abdolshah, Dung Nguyen, Kien Do, Sunil Gupta, Svetha Venkatesh
We introduce a constrained optimization method for policy gradient reinforcement learning, which uses a virtual trust region to regulate each policy update.
no code implementations • 17 Apr 2022 • Dung Nguyen, Phuoc Nguyen, Svetha Venkatesh, Truyen Tran
In particular, we train a role assignment network for small teams by demonstration and transfer the network to larger teams, which continue to learn through interaction with the environment.
no code implementations • 17 Apr 2022 • Dung Nguyen, Phuoc Nguyen, Hung Le, Kien Do, Svetha Venkatesh, Truyen Tran
Inspired by the observation that humans often infer the character traits of others, then use it to explain behaviour, we propose a new neural ToM architecture that learns to generate a latent trait vector of an actor from the past trajectories.
no code implementations • 24 Feb 2022 • Kien Do, Haripriya Harikumar, Hung Le, Dung Nguyen, Truyen Tran, Santu Rana, Dang Nguyen, Willy Susilo, Svetha Venkatesh
Trojan attacks on deep neural networks are both dangerous and surreptitious.
no code implementations • 31 Jan 2022 • Mohamed Seif, Dung Nguyen, Anil Vullikanti, Ravi Tandon
To the best of our knowledge, this is the first work to study the impact of privacy constraints on the fundamental limits for community detection.
no code implementations • 1 Jan 2022 • Dung Nguyen, Alix Boc, Abdoulaye Banire Diallo, Vladimir Makarenkov
Phages are one of the most present groups of organisms in the biosphere.
1 code implementation • 3 Dec 2021 • Hung Le, Majid Abdolshah, Thommen K. George, Kien Do, Dung Nguyen, Svetha Venkatesh
We introduce a novel training procedure for policy gradient methods wherein episodic memory is used to optimize the hyperparameters of reinforcement learning algorithms on-the-fly.
no code implementations • 27 May 2021 • Dung Nguyen, Anil Vullikanti
We study the densest subgraph problem in the edge privacy model, in which the edges of the graph are private.
no code implementations • 2 Nov 2020 • In Seop Na, Chung Tran, Dung Nguyen, Sang Dinh
A promising approach to deal with pose variation is to fulfill incomplete UV maps extracted from in-the-wild faces, then attach the completed UV map to a fitted 3D mesh and finally generate different 2D faces of arbitrary poses.
no code implementations • 16 Sep 2020 • Dung Nguyen, Svetha Venkatesh, Phuoc Nguyen, Truyen Tran
In psychological game theory, guilt aversion necessitates modelling of agents that have theory about what other agents think, also known as Theory of Mind (ToM).
no code implementations • 23 Jun 2020 • Dung Nguyen, Sridha Sridharan, Duc Thanh Nguyen, Simon Denman, David Dean, Clinton Fookes
To mitigate this challenge, transfer learning performing fine-tuning on pre-trained models has been applied.
Facial Expression Recognition
Facial Expression Recognition (FER)
+2
no code implementations • 28 Apr 2020 • Dung Nguyen, Duc Thanh Nguyen, Rui Zeng, Thanh Thi Nguyen, Son N. Tran, Thin Nguyen, Sridha Sridharan, Clinton Fookes
Multimodal dimensional emotion recognition has drawn a great attention from the affective computing community and numerous schemes have been extensively investigated, making a significant progress in this area.
no code implementations • 24 Mar 2020 • Dung Nguyen, Sridha Sridharan, Duc Thanh Nguyen, Simon Denman, Son N. Tran, Rui Zeng, Clinton Fookes
Deep learning has been applied to achieve significant progress in emotion recognition.
no code implementations • 21 Nov 2018 • Thanh T. Nguyen, Dung Nguyen
Attentively important regions in video frames account for a majority part of the semantics in each frame.
no code implementations • 25 May 2018 • Dung Nguyen, Kien Nguyen, Sridha Sridharan, Iman Abbasnejad, David Dean, Clinton Fookes
The use of deep learning techniques for automatic facial expression recognition has recently attracted great interest but developed models are still unable to generalize well due to the lack of large emotion datasets for deep learning.