21 accepted papers
State space models (SSMs) often sacrifice capacity, search space, or stability to offset the memory and compute costs of large state dimensions. We introduce a structured post-training pruning method for SSMs — AIRE-Prune (Asymptotic Impulse- Response Energy for State PRUN(E)ing ) — that reduces eac…
In this work, we introduce an adaptive hierarchical framework for efficient 3D object detection from point cloud data, designed to dynamically balance computational efficiency and detection performance. Our approach employs a shared feature extractor and multiple detector backbones of varying widths…
We introduce RAVEN, a deep learning architecture for processing frequency-modulated continuous-wave (FMCW) radar data that is designed for high computational efficiency. RAVEN reduces computation by using a learnable antenna mixer module on independent receiver state space encoders (SSM) to compress
Graph Neural Networks (GNNs) face a critical limitation known as oversmoothing, where increasing network depth leads to homogenized node representations, severely compromising their expressiveness. We present a novel dynamical systems perspective on this challenge, revealing oversmoothing as an emer…
In this work, we introduce an adaptive hierarchical framework for efficient 3D object detection from point cloud data, designed to dynamically balance computational efficiency and detection performance. Our approach employs a shared feature extractor and multiple detector backbones of varying widths
We propose Fast Long-range Adaptive Memory for Event (FLAME), a novel scalable architecture that combines neuro-inspired feature extraction with robust structured sequence modeling to efficiently process asynchronous and sparse event camera data. As a departure from conventional input encoding metho…
This paper presents the first systematic study of evaluating Deep Neural Networks (DNNs) designed to forecast the evolution of stochastic complex systems. We show that traditional evaluation methods like threshold-based classification metrics and error-based scoring rules assess a DNN's ability to r…
"Leveraging the high temporal resolution of an event-based camera requires highly efficient event-by-event processing. However, dense prediction tasks require explicit pixel-level association, which is challenging for event-based processing frameworks. Existing works aggregate the events into a stat…
We introduce a novel framework, Online Relational Inference (ORI), designed to efficiently identify hidden interaction graphs in evolving multi-agent interacting systems using streaming data. Unlike traditional offline methods that rely on a fixed training set, ORI employs online backpropagation, up…
Developing agents that can perform complex control tasks from high-dimensional observations is a core ability of autonomous agents that requires underlying robust task control policies and adapting the underlying visual representations to the task. Most existing policies need a lot of training sampl…
Recurrent Spiking Neural Networks (RSNNs) have emerged as a computationally efficient and brain-inspired machine learning model. The design of sparse RSNNs with fewer neurons and synapses helps reduce the computational complexity of RSNNs. Traditionally, sparse SNNs are obtained by first training a…
We propose $\textit{EventFormer}$, a computationally efficient event-based representation learning framework for asynchronously processing event camera data. EventFormer treats sparse input events as a spatially unordered set and models their spatial interactions using self-attention mechanism. An a…
This paper shows that the heterogeneity in neuronal and synaptic dynamics reduces the spiking activity of a Recurrent Spiking Neural Network (RSNN) while improving prediction performance, enabling spike-efficient (unsupervised) learning. We analytically show that the diversity in neurons' integratio…
This letter investigates the scope of deep neural network (DNN) based controller in the path following task for unicycle mobile robots. A DNN-based controller is trained to follow paths with arbitrary curvature in two-dimensional space. The training process does not require initialization or supervi
We present an unsupervised deep learning model for 3D object classification. Conventional Hebbian learning, a well-known unsupervised model, suffers from loss of local features leading to reduced performance for tasks with complex geometric objects. We present a deep network with a novel Neuron Acti…
A dynamical system of spiking neurons with only feedforward connections can classify spatiotemporal patterns without recurrent connections. However, the theoretical construct of a feedforward spiking neural network (SNN) for approximating a temporal sequence remains unclear, making it challenging to…
We present a new method for learning control law that stabilizes an unknown nonlinear dynamical system at an equilibrium point. We formulate a system identification task in a self-supervised learning setting that jointly learns a controller and corresponding stable closed-loop dynamics hypothesis. T
We present the MagNet, a neural network-based multi-agent interaction model to discover the governing dynamics and predict evolution of a complex multi-agent system from observations. We formulate a multi-agent system as a coupled non-linear network with a generic ordinary differential equation (ODE…
This paper presents a novel problem of detection and localization of anomalous events due to a certain class of objects in video data with applications to smart surveillance. A baseline system is proposed that uses a convolutional neural network (CNN) to generate pixel level masks corresponding to o…
Injecting adversarial examples during training, known as adversarial training, can improve robustness against one-step attacks, but not for unknown iterative attacks. To address this challenge, we first show iteratively generated adversarial images easily transfer between networks trained with the s…
The robotic systems continuously interact with complex dynamical systems in the physical world. Reliable predictions of spatiotemporal evolution of these dynamical systems, with limited knowledge of system dynamics, are crucial for autonomous operation. In this paper, we present HybridNet, a framewo