18 citations · 22 across the 19 of their papers we have counts for
12 papers · 1 filter
Continual Safety Alignment via Gradient-Based Sample Selection
Thong Bach, Dung Nguyen, Thao Minh Le +1
Large language models require continuous adaptation to new tasks while preserving safety alignment. However, fine-tuning on even benign data often compromises safety behaviors, inc…
Uncertainty-Guided Checkpoint Selection for Reinforcement Finetuning of Large Language Models
Manh Nguyen, Dung Nguyen, Dai Do +2
Reinforcement learning (RL) finetuning is crucial to aligning large language models (LLMs), but the process is notoriously unstable and exhibits high variance across model checkpoi…
Reasoning Under 1 Billion: Memory-Augmented Reinforcement Learning for Large Language Models
Hung Le, Dai Do, Dung Nguyen +1
Recent advances in fine-tuning large language models (LLMs) with reinforcement learning (RL) have shown promising improvements in complex reasoning tasks, particularly when paired…
Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement Learning
Hung Le, Kien Do, Dung Nguyen +2
Effective decision-making in partially observable environments demands robust memory management. Despite their success in supervised learning, current deep-learning memory models s…
Enhancing Length Extrapolation in Sequential Models with Pointer-Augmented Neural Memory
Hung Le, Dung Nguyen, Kien Do +2
We propose Pointer-Augmented Neural Memory (PANM) to help neural networks understand and apply symbol processing to new, longer sequences of data. PANM integrates an external neura…
Revisiting the Dataset Bias Problem from a Statistical Perspective
Kien Do, Dung Nguyen, Hung Le +6
In this paper, we study the "dataset bias" problem from a statistical standpoint, and identify the main cause of the problem as the strong correlation between a class attribute u a…
Variational Flow Models: Flowing in Your Style
Kien Do, Duc Kieu, Toan Nguyen +4
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}+σ_{t}X_{1} into a str…
Beyond Surprise: Improving Exploration Through Surprise Novelty
Hung Le, Kien Do, Dung Nguyen +1
We present a new computing model for intrinsic rewards in reinforcement learning that addresses the limitations of existing surprise-driven explorations. The reward is the novelty…
Learning to Transfer Role Assignment Across Team Sizes
Dung Nguyen, Phuoc Nguyen, Svetha Venkatesh +1
Multi-agent reinforcement learning holds the key for solving complex tasks that demand the coordination of learning agents. However, strong coordination often leads to expensive ex…
Learning Theory of Mind via Dynamic Traits Attribution
Dung Nguyen, Phuoc Nguyen, Hung Le +3
Machine learning of Theory of Mind (ToM) is essential to build social agents that co-live with humans and other agents. This capacity, once acquired, will help machines infer the m…
Learning to Constrain Policy Optimization with Virtual Trust Region
Hung Le, Thommen Karimpanal George, Majid Abdolshah +4
We introduce a constrained optimization method for policy gradient reinforcement learning, which uses a virtual trust region to regulate each policy update. In addition to using th…
Episodic Policy Gradient Training
Hung Le, Majid Abdolshah, Thommen K. George +3
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.…