Related papers: Balancing Computation Load and Representation Expr…

Large language models (LLMs) have demonstrated exceptional proficiency in understanding and generating human language, but efficient inference on resource-constrained embedded devices remains challenging due to large model sizes and…

The existing crowd counting methods usually adopted attention mechanism to tackle background noise, or applied multi-level features or multi-scales context fusion to tackle scale variation. However, these approaches deal with these two…

Existing event stream-based pattern recognition models usually represent the event stream as the point cloud, voxel, image, etc., and design various deep neural networks to learn their features. Although considerable results can be achieved…

Linear recurrent networks (LRNNs) and linear state space models (SSMs) promise computational and memory efficiency on long-sequence modeling tasks, yet their diagonal state transitions limit expressivity. Dense and nonlinear architectures…

As the landscape of deep neural networks evolves, heterogeneous dataflow accelerators, in the form of multi-core architectures or chiplet-based designs, promise more flexibility and higher inference performance through scalability. So far,…

Quantum neural networks represent a new machine learning paradigm that has recently attracted much attention due to its potential promise. Under certain conditions, these models approximate the distribution of their dataset with a truncated…

Large language models (LLMs) have significantly advanced generative applications in natural language processing (NLP). Recent trends in model architectures revolve around efficient variants of transformers or state-space/gated-recurrent…

Neural network architecture design requires making many crucial decisions. The common desiderata is that similar decisions, with little modifications, can be reused in a variety of tasks and applications. To satisfy that, architectures must…

Current multi-modal image fusion methods typically rely on task-specific models, leading to high training costs and limited scalability. While generative methods provide a unified modeling perspective, they often suffer from slow inference…

We propose an accelerated computational fluid dynamics framework based on a hybrid Fourier Neural Operator-Lattice Boltzmann Method (FNO-LBM) for steady and unsteady weakly compressible flows. FNO-based initialization significantly…

Multimodal classification requires robust integration of visual and textual signals, yet common fusion strategies are brittle and vulnerable to modality-specific noise. In this paper, we present \textsc{FLUID}-Flow-Latent Unified…

The architecture of a neural network and the selection of its activation function are both fundamental to its performance. Equally vital is ensuring these two elements are well-matched, as their alignment is key to achieving effective…

Emerging applications such as AR are driving demands for machine intelligence capable of processing continuous and/or long-context inputs on local devices. However, currently dominant models based on Transformer architecture suffers from…

Spiking Neural Networks(SNNs) provide a brain-inspired and event-driven mechanism that is believed to be critical to unlock energy-efficient deep learning. The mixture-of-experts approach mirrors the parallel distributed processing of…

Mixture of Experts (MoE) models enhance neural network scalability by dynamically selecting relevant experts per input token, enabling larger model sizes while maintaining manageable computation costs. However, efficient training of…

Foundational language models show a remarkable ability to learn new concepts during inference via context data. However, similar work for images lag behind. To address this challenge, we introduce FLoWN, a flow matching model that learns to…

Transformers excel at in-context retrieval but suffer from quadratic complexity with sequence length, while State Space Models (SSMs) offer efficient linear-time processing but have limited retrieval capabilities. We investigate whether…

This paper explores the synergistic potential of neuromorphic and edge computing to create a versatile machine learning (ML) system tailored for processing data captured by dynamic vision sensors. We construct and train hybrid models,…

Prevailing LLM serving engines employ expert parallelism (EP) to implement multi-device inference of massive MoE models. However, the efficiency of expert parallel inference is largely bounded by inter-device communication, as EP embraces…

Recurrent spiking neural networks (RSNNs) can be implemented very efficiently in neuromorphic systems. Nevertheless, training of these models with powerful gradient-based learning algorithms is mostly performed on standard digital hardware…