Related papers: Flash STU: Fast Spectral Transform Units
Spiking neural networks (SNNs) offer energy efficiency over artificial neural networks (ANNs) but suffer from high latency and computational overhead due to their multi-timestep operational nature. While various dynamic computation methods…
Spiking Transformers have shown strong potential for long-range visual modeling through spike-driven self-attention. However, their quadratic token interactions remain fundamentally misaligned with the sparse and event-driven nature of…
Structured state space models (SSMs) have recently emerged as a promising foundation for sequence modeling, with Mamba-based architectures demonstrating strong performance through input-dependent state transitions, albeit at considerable…
Large-scale foundation models have demonstrated exceptional performance in language and vision tasks. However, the numerous dense matrix-vector operations involved in these large networks pose significant computational challenges during…
Spatio-Temporal prediction plays a critical role in smart city construction. Jointly modeling multiple spatio-temporal tasks can further promote an intelligent city life by integrating their inseparable relationship. However, existing…
Decoding in a Transformer based language model is inherently sequential as a token's embedding needs to pass through all the layers in the network before the generation of the next token can begin. In this work, we propose a new…
Remote sensing image fusion aims to generate a high-resolution multi/hyper-spectral image by combining a high-resolution image with limited spectral data and a low-resolution image rich in spectral information. Current deep learning (DL)…
Remote sensing spatiotemporal fusion (STF) addresses the fundamental trade-off between temporal and spatial resolution by combining high temporal-low spatial and high spatial-low temporal imagery. This paper presents the first comprehensive…
State Space Models (SSMs) have emerged as a promising alternative to Transformers for long-context sequence modeling, offering linear $O(N)$ computational complexity compared to the Transformer's quadratic $O(N^2)$ scaling. This paper…
Recently, state space models (SSM), particularly Mamba, have attracted significant attention from scholars due to their ability to effectively balance computational efficiency and performance. However, most existing visual Mamba methods…
Large language models (LLMs) have made significant advances in complex reasoning tasks, yet they remain bottlenecked by two core challenges: architectural inefficiency due to reliance on Transformers, and a lack of structured fine-tuning…
Transformers have revolutionized deep learning across various tasks, including audio representation learning, due to their powerful modeling capabilities. However, they often suffer from quadratic complexity in both GPU memory usage and…
Event cameras unlock new frontiers that were previously unthinkable with standard frame-based cameras. One notable example is low-latency motion estimation (optical flow), which is critical for many real-time applications. In such…
Scaling sequence modeling to extreme contexts requires balancing computational efficiency with representational expressivity. While Transformers provide precise retrieval via the attention mechanism, their quadratic $\mathcal{O}(T^2)$…
Existing models encounter bottlenecks in balancing performance and computational efficiency when modeling long sequences. Although the state space model (SSM) has achieved remarkable success in handling long sequence tasks, it still faces…
Transformer-based architectures have shown remarkable performance in vision and language tasks but pose unique challenges for safety-critical applications. This paper presents a conceptual framework for integrating Transformers into…
Auto-regressive speech-text models pre-trained on interleaved text tokens and discretized speech tokens demonstrate strong speech understanding and generation, yet remain substantially less compute-efficient than text LLMs, partly due to…
Reliable 3D object detection is fundamental to autonomous driving, and multimodal fusion algorithms using cameras and LiDAR remain a persistent challenge. Cameras provide dense visual cues but ill posed depth; LiDAR provides a precise 3D…
Large language models (LLMs) rely on self-attention for contextual understanding, demanding high-throughput inference and large-scale token parallelism (LTPP). Existing dynamic sparsity accelerators falter under LTPP scenarios due to…
Prior efforts in light-weight model development mainly centered on CNN and Transformer-based designs yet faced persistent challenges. CNNs adept at local feature extraction compromise resolution while Transformers offer global reach but…