相关论文: PAHQ: Accelerating Automated Circuit Discovery thr…

Attention mechanism is a significant part of Transformer models. It helps extract features from embedded vectors by adding global information and its expressivity has been proved to be powerful. Nevertheless, the quadratic complexity…

Machine comprehension (MC), answering a query about a given context paragraph, requires modeling complex interactions between the context and the query. Recently, attention mechanisms have been successfully extended to MC. Typically these…

Approximate computing emerges as a promising approach to enhance the efficiency of compute-in-memory (CiM) systems in deep neural network processing. However, traditional approximate techniques often significantly trade off accuracy for…

Property Directed Reachability (PDR) is a powerful algorithm for formal verification of hardware and software systems, but its performance is highly sensitive to parameter configurations. Manual parameter tuning is time-consuming and…

The design of complexity-aware cascaded detectors, combining features of very different complexities, is considered. A new cascade design procedure is introduced, by formulating cascade learning as the Lagrangian optimization of a risk that…

We present FACADE, a novel probabilistic and geometric framework designed for unsupervised mechanistic anomaly detection in deep neural networks. Its primary goal is advancing the understanding and mitigation of adversarial attacks. FACADE…

Anchor-based detectors have been continuously developed for object detection. However, the individual anchor box makes it difficult to predict the boundary's offset accurately. Instead of taking each bounding box as a closed individual, we…

Manual visual inspection performed by certified inspectors is still the main form of road pothole detection. This process is, however, not only tedious, time-consuming and costly, but also dangerous for the inspectors. Furthermore, the road…

Multi-head self-attention is a distinctive feature extraction mechanism of vision transformers that computes pairwise relationships among all input patches, contributing significantly to their high performance. However, it is known to incur…

To achieve parsimonious inference in per-pixel labeling tasks with a limited computational budget, we propose a \emph{Pixel-wise Attentional Gating} unit (\emph{PAG}) that learns to selectively process a subset of spatial locations at each…

Photonic tensor cores (PTCs) are essential building blocks for optical artificial intelligence (AI) accelerators based on programmable photonic integrated circuits. PTCs can achieve ultra-fast and efficient tensor operations for neural…

Optimization of the last-mile delivery and first-mile pickup of parcels is integral to the logistics optimization pipeline as it entails both cost and resource efficiency and a heightened service quality. Such optimization requires accurate…

This work considers downlink incremental redundancy Hybrid Automatic Repeat Request (IR-HARQ) over unreliable feedback channels. Since the impact of positive feedback (i.e., ACK) error is smaller than that of negative feedback (i.e., NACK)…

Privacy and security have rapidly emerged as priorities in system design. One powerful solution for providing both is privacy-preserving computation, where functions are computed directly on encrypted data and control can be provided over…

Reducing the key-value (KV) cache burden in Large Language Models (LLMs) significantly accelerates inference. Dynamically selecting critical KV caches during decoding helps maintain performance. Existing methods use random linear hashing to…

Robustly predicting attention regions of interest for self-driving systems is crucial for driving safety but presents significant challenges due to the labor-intensive nature of obtaining large-scale attention labels and the domain gap…

Medical image segmentation can provide detailed information for clinical analysis which can be useful for scenarios where the detailed location of a finding is important. Knowing the location of disease can play a vital role in treatment…

Existing fine-grained hashing methods typically lack code interpretability as they compute hash code bits holistically using both global and local features. To address this limitation, we propose ConceptHash, a novel method that achieves…

Prior studies investigating the internal workings of LLMs have uncovered sparse subnetworks, often referred to as circuits, that are responsible for performing specific tasks. Additionally, it has been shown that model performance…

Automated program repair (APR) attempts to generate correct patches and has drawn wide attention from both academia and industry in the past decades. However, APR is continuously struggling with the patch overfitting issue due to the weak…