Related papers: Modulating task outcome value to mitigate real-wor…
The naive application of Reinforcement Learning algorithms to continuous control problems -- such as locomotion and manipulation -- often results in policies which rely on high-amplitude, high-frequency control signals, known colloquially…
Existing Continual Learning (CL) approaches have focused on addressing catastrophic forgetting by leveraging regularization methods, replay buffers, and task-specific components. However, realistic CL solutions must be shaped not only by…
Designing optimal reward functions has been desired but extremely difficult in reinforcement learning (RL). When it comes to modern complex tasks, sophisticated reward functions are widely used to simplify policy learning yet even a tiny…
The advances in natural language processing (NLP) pose both opportunities and challenges. While recent progress enables the development of high-performing models for a variety of tasks, it also poses the risk of models learning harmful…
Pretrained language models have achieved state-of-the-art performance when adapted to a downstream NLP task. However, theoretical analysis of these models is scarce and challenging since the pretraining and downstream tasks can be very…
Deep neural networks often suffer from a critical limitation known as catastrophic forgetting, where performance on past tasks degrades after learning new ones. This paper introduces a novel continual learning approach inspired by human…
Action delays degrade the performance of reinforcement learning in many real-world systems. This paper proposes a formal definition of delay-aware Markov Decision Process and proves it can be transformed into standard MDP with augmented…
Problems arise when using reward functions to capture dependencies between sequential time-constrained goal states because the state-space must be prohibitively expanded to accommodate a history of successfully achieved sub-goals. Also,…
Large vision-language models (LVLMs) achieve strong multimodal performance, but still suffer from hallucinations caused by unstable visual grounding and over-reliance on language priors. Existing training-free decoding methods typically…
Acute stress alters cognitive performance, yet competing models make divergent predictions regarding the mechanisms, scope, and temporal dynamics of these effects. This large-scale randomized controlled trial tested predications from three…
As robot teleoperation increasingly becomes integral in executing tasks in distant, hazardous, or inaccessible environments, the challenge of operational delays remains a significant obstacle. These delays are inherent in signal…
Artificial neural networks encounter a notable challenge known as continual learning, which involves acquiring knowledge of multiple tasks over an extended period. This challenge arises due to the tendency of previously learned weights to…
This work describes our group's submission to the PROCESS Challenge 2024, with the goal of assessing cognitive decline through spontaneous speech, using three guided clinical tasks. This joint effort followed a holistic approach,…
We study episodic linear mixture MDPs with the unknown transition and adversarial rewards under full-information feedback, employing dynamic regret as the performance measure. We start with in-depth analyses of the strengths and limitations…
Reward models (RMs) play a central role in aligning large language models (LLMs) with human preferences. However, RMs are often sensitive to spurious features such as response length. Existing inference-time approaches for mitigating these…
Several works related to spatial crowdsourcing have been proposed in the direction where the task executers are to perform the tasks within the stipulated deadlines. Though the deadlines are set, it may be a practical scenario that majority…
Neural networks exhibit a remarkable degree of representational convergence across diverse architectures, training objectives, and even data modalities. This convergence is predictive of alignment with brain representation. A recent…
Recent electrophysiological experiments have shown that dopamine (D1) modulation of pyramidal cells in prefrontal cortex reduces spike frequency adaptation and enhances NMDA transmission. Using four models, from multicompartmental to…
Debugging is a demanding aspect of programming yet guidance on how to teach it effectively remains limited. Novices often struggle to recognize impasses regulate their problem solving and manage cognitive load and stress. This study…
Cognitive decline is a natural part of aging. However, under some circumstances, this decline is more pronounced than expected, typically due to disorders such as Alzheimer's disease. Early detection of an anomalous decline is crucial, as…