Related papers: Elastic CoCoA: Scaling In to Improve Convergence
This paper considers a cross-layer optimization problem driven by multi-timescale stochastic exogenous processes in wireless communication networks. Due to the hierarchical information structure in a wireless network, a mixed timescale…
Current AI alignment through RLHF follows a single directional paradigm that AI conforms to human preferences while treating human cognition as fixed. We propose a shift to co-alignment through Bidirectional Cognitive Alignment (BiCA),…
Distributed systems often serve dynamic workloads and resource demands evolve over time. Such a temporal behavior stands in contrast to the static and demand-oblivious nature of most data structures used by these systems. In this paper, we…
Brain representations must strike a balance between generalizability and adaptability. Neural codes capture general statistical regularities in the world, while dynamically adjusting to reflect current goals. One aspect of this adaptation…
Cellular Automata (CA) are a class of discrete dynamical systems that have been widely used to model complex systems in which the dynamics is specified at local cell-scale. Classically, CA are run on a regular lattice and with perfect…
Multi-task learning (MTL) benefits the fine-tuning of large language models (LLMs) by providing a single model with improved performance and generalization ability across tasks, presenting a resource-efficient alternative to developing…
Hardware compute power has been growing at an unprecedented rate in recent years. The utilization of such advancements plays a key role in producing better results in less time -- both in academia and industry. However, merging the existing…
Finding codes given natural language query isb eneficial to the productivity of software developers. Future progress towards better semantic matching between query and code requires richer supervised training resources. To remedy this, we…
Despite recent progress in video generation, inference speed remains a major bottleneck. A common acceleration strategy involves reusing model outputs via caching mechanisms at fixed intervals. However, we find that such fixed-frequency…
On-device training is essential for neural networks (NNs) to continuously adapt to new online data, but can be time-consuming due to the device's limited computing power. To speed up on-device training, existing schemes select trainable NN…
With the proliferation of sensors, such as accelerometers, in mobile devices, activity and motion tracking has become a viable technology to understand and create an engaging user experience. This paper proposes a fast adaptation and…
This paper develops an adaptive observation-based efficient reinforcement learning (RL) approach for systems with uncertain drift dynamics. A novel concurrent learning adaptive extended observer (CL-AEO) is first designed to jointly…
Variable stiffness actuators undergo lower peak force in contacts compared to their rigid counterparts, and are thus safer for human-robot interaction. Furthermore, they can store energy in their elastic element and can release it later to…
Modern foundation models rely heavily on using scaling laws to guide crucial training decisions. Researchers often extrapolate the optimal architecture and hyper parameters settings from smaller training runs by describing the relationship…
The integration of Artificial Intelligence (AI) in education requires scalable and efficient frameworks that balance performance, adaptability, and cost. This paper addresses these needs by proposing a shared backbone model architecture…
The goal of Continual Learning (CL) task is to continuously learn multiple new tasks sequentially while achieving a balance between the plasticity and stability of new and old knowledge. This paper analyzes that this insufficiency arises…
Effective coordination among unfamiliar partners remains a major challenge in multi-agent systems. Existing approaches, such as population-based methods, improve robustness through diversity but often lack mechanisms for efficient…
We present the parallel and interacting stochastic approximation annealing (PISAA) algorithm, a stochastic simulation procedure for global optimisation, that extends and improves the stochastic approximation annealing (SAA) by using…
Flexibility at hardware level is the main driving force behind adaptive systems whose aim is to realise microarhitecture deconfiguration 'online'. This feature allows the software/hardware stack to tolerate drastic changes of the workload…
We propose a system to adapt a user's music to their exercise by aligning high-energy music segments with intense intervals of the workout. Listening to music during exercise can boost motivation and performance. However, the structure of…