Related papers: Efficient Encoders for Streaming Sequence Tagging

Compressed bitmap indexes are used in databases and search engines. Many bitmap compression techniques have been proposed, almost all relying primarily on run-length encoding (RLE). However, on unsorted data, we can get superior performance…

Hyperdimensional computing (HDC) is a paradigm for data representation and learning originating in computational neuroscience. HDC represents data as high-dimensional, low-precision vectors which can be used for a variety of information…

Real-time imaging sonar is crucial for underwater monitoring where optical sensing fails, but its use is limited by low uplink bandwidth and severe sonar-specific artifacts (speckle, motion blur, reverberation, acoustic shadows) affecting…

Deep-learning-based intelligent services have become prevalent in cyber-physical applications including smart cities and health-care. Collaborative end-edge-cloud computing for deep learning provides a range of performance and efficiency…

In applied machine learning, concept drift, which is either gradual or abrupt changes in data distribution, can significantly reduce model performance. Typical detection methods,such as statistical tests or reconstruction-based models,are…

Recent approaches in hierarchical text classification (HTC) rely on the capabilities of a pre-trained transformer model and exploit the label semantics and a graph encoder for the label hierarchy. In this paper, we introduce an effective…

Video service providers need their delivery systems to be able to adapt to network conditions, user preferences, display settings, and other factors. HTTP Adaptive Streaming (HAS) offers dynamic switching between different video…

Large language models are increasingly used for code generation, but many generated programs fail to compile, a prerequisite for further correctness checks such as unit tests. Existing solutions for repairing static errors are costly in…

Logs are a first-hand source of information for software maintenance and failure diagnosis. Log parsing, which converts semi-structured log messages into structured templates, is a prerequisite for automated log analysis tasks such as…

In this work, we investigate proactive Hybrid Automatic Repeat reQuest (HARQ) using link-level simulations for multiple packet sizes, modulation orders, BLock Error Rate (BLER) targets and two delay budgets of 1 ms and 2 ms, in the context…

ISAC enables pervasive monitoring, but modern sensing algorithms are often too complex for energy-constrained edge devices. This motivates the development of learning techniques that balance accuracy performance and energy efficiency.…

Streaming neural network models for fast frame-wise responses to various speech and sensory signals are widely adopted on resource-constrained platforms. Hence, increasing the learning capacity of such streaming models (i.e., by adding more…

Log parsing, which extracts log templates from semi-structured logs and produces structured logs, is the first and the most critical step in automated log analysis. While existing log parsers have achieved decent results, they suffer from…

In this paper, we consider the ChannelComp framework, where multiple transmitters aim to compute a function of their values at a common receiver while using digital modulations over a multiple access channel. ChannelComp provides a general…

Always-on edge cameras generate continuous video streams where redundant frames degrade cross-modal retrieval by crowding correct results out of top-k search. This paper presents a streaming retrieval architecture: an on-device epsilon-net…

Stream Learning (SL) requires models that can quickly adapt to continuously evolving data, posing significant challenges in both computational efficiency and learning accuracy. Effective data selection is critical in SL to ensure a balance…

Fully Homomorphic Encryption (FHE) is a set of powerful cryptographic schemes that allows computation to be performed directly on encrypted data with an unlimited depth. Despite FHE's promising in privacy-preserving computing, yet in most…

Efficient execution of deep learning workloads on dataflow architectures is crucial for overcoming memory bottlenecks and maximizing performance. While streaming intermediate results between computation kernels can significantly improve…

End-to-end (E2E) automatic speech recognition (ASR) can operate in two modes: streaming and non-streaming, each with its pros and cons. Streaming ASR processes the speech frames in real-time as it is being received, while non-streaming ASR…

Long-sequence streaming 3D reconstruction remains a significant open challenge. Existing autoregressive models often fail when processing long sequences because they anchor poses to the first frame, leading to attention decay, scale drift,…