Related papers: FLAMES: A Hybrid Spiking-State Space Model for Ada…
Large Reasoning Models (LRMs) often suffer from computational inefficiency due to overthinking, where a fixed reasoning budget fails to match the varying complexity of tasks. To address this issue, we propose Adaptive Overclocking, a method…
Hybrid memory systems, comprised of emerging non-volatile memory (NVM) and DRAM, have been proposed to address the growing memory demand of applications. Emerging NVM technologies, such as phase-change memories (PCM), memristor, and 3D…
Reinforcement learning has achieved remarkable success in robot learning. However, under challenging exploration and contact-rich dynamics, early-stage training is frequently dominated by premature terminations such as collisions and falls.…
Spiking Neural Networks (SNNs) are considered to have enormous potential in the future development of Artificial Intelligence due to their brain-inspired and energy-efficient properties. Compared to vanilla Spatial-Temporal Back-propagation…
Energy efficiency and low latency are crucial requirements for designing wearable AI-empowered human activity recognition systems, due to the hard constraints of battery operations and closed-loop feedback. While neural network models have…
The human brain is the most powerful and efficient machine in existence today, surpassing in many ways the capabilities of modern computers. Currently, lines of research in neuromorphic engineering are trying to develop hardware that mimics…
Whilst most engineered systems use signals that are continuous in time, there is a domain of systems in which signals consist of events. Events, like Dirac delta functions, have no meaningful time duration. Many important real-world systems…
This paper proposes a new meta-learning method -- named HARMLESS (HAwkes Relational Meta LEarning method for Short Sequences) for learning heterogeneous point process models from short event sequence data along with a relational network.…
This paper presents a novel cloud-edge framework for addressing computational and energy constraints in complex control systems. Our approach centers around a learning-based controller using Spiking Neural Networks (SNN) on physical plants.…
Large language model (LLM) agents demonstrate strong performance in short-text contexts but often underperform in extended dialogues due to inefficient memory management. Existing approaches face a fundamental trade-off between efficiency…
Large reasoning models (LRMs) have demonstrated strong performance on complex reasoning tasks, but often suffer from overthinking, generating redundant content regardless of task difficulty. Inspired by the dual process theory in cognitive…
We propose reinforcement learning on simple networks consisting of random connections of spiking neurons (both recurrent and feed-forward) that can learn complex tasks with very little trainable parameters. Such sparse and randomly…
Spiking neural networks have garnered increasing attention due to their energy efficiency, multiplication-free computation, and sparse event-based processing. In parallel, state space models have emerged as scalable alternatives to…
Spiking neural networks (SNNs) present a promising computing paradigm for neuromorphic processing of event-based sensor data. The resonate-and-fire (RF) neuron, in particular, appeals through its biological plausibility, complex dynamics,…
In the field of robotics, event-based cameras are emerging as a promising low-power alternative to traditional frame-based cameras for capturing high-speed motion and high dynamic range scenes. This is due to their sparse and asynchronous…
Event cameras are considered to have great potential for computer vision and robotics applications because of their high temporal resolution and low power consumption characteristics. However, the event stream output from event cameras has…
Manifold-based combustion models decrease the cost of turbulent combustion simulations by projecting the thermochemical state onto a lower-dimensional manifold, allowing the thermochemical state to be computed separately from the flow…
Spiking Neural Networks (SNNs) offer a promising energy-efficient alternative to Artificial Neural Networks (ANNs) by utilizing sparse and asynchronous processing through discrete spike-based computation. However, the performance of deep…
Recent progress in robotic manipulation has been fueled by large-scale datasets collected across diverse environments. Training robotic manipulation policies on these datasets is traditionally performed in a centralized manner, raising…
Human action recognition (HAR) plays a key role in various applications such as video analysis, surveillance, autonomous driving, robotics, and healthcare. Most HAR algorithms are developed from RGB images, which capture detailed visual…