相关论文: Encoding Tight Typing in a Unified Framework

A method for encoding and decoding spectrum shaped binary run-length constrained sequences is described. The binary sequences with predefined range of exponential sums are introduced. On the base of Cover's enumerative scheme, recurrence…

Large language models face significant computational bottlenecks during inference due to the expensive output layer computation over large vocabularies. We present CSV-Decode, a novel approach that uses geometric upper bounds to construct…

Existing codecs are designed to eliminate intrinsic redundancies to create a compact representation for compression. However, strong external priors from Multimodal Large Language Models (MLLMs) have not been explicitly explored in video…

Enhanced sampling methods typically require predefined collective variables (CVs) that presuppose knowledge of reaction coordinates, restricting the discovery of unanticipated transition mechanisms or intermediates. Here, we show that a…

Strictness analysis is critical to efficient implementation of languages with non-strict evaluation, mitigating much of the performance overhead of laziness. However, reasoning about strictness at the source level can be challenging and…

Vision-Language Models (VLMs) face severe memory and latency bottlenecks due to high-resolution visual tokens. While current token reduction methods theoretically save FLOPs, post-hoc pruning introduces structural overhead, failing to yield…

The success of deep learning (DL) is often achieved with large models and high complexity during both training and post-training inferences, hindering training in resource-limited settings. To alleviate these issues, this paper introduces a…

As semiconductor technologies continue to scale down to the nanoscale, the efficient prediction of material properties becomes increasingly critical. The tight-binding (TB) method is a widely used semi-empirical approach that offers a…

We present the first fully abstract normal form bisimulation for call-by-value PCF (PCF$_{\textsf{v}}$). Our model is based on a labelled transition system (LTS) that combines elements from applicative bisimulation, environmental…

Deep learning has been used as a powerful tool for various tasks in computer vision, such as image segmentation, object recognition and data generation. A key part of end-to-end training is designing the appropriate encoder to extract…

This paper presents the first general (supervised) statistical learning framework for point processes in general spaces. Our approach is based on the combination of two new concepts, which we define in the paper: i) bivariate innovations,…

This paper proposes a novel approach to create an unit set for CTC based speech recognition systems. By using Byte Pair Encoding we learn an unit set of an arbitrary size on a given training text. In contrast to using characters or words as…

A key problem in constrained random verification (CRV) concerns generation of input stimuli that result in good coverage of the system's runs in targeted corners of its behavior space. Existing CRV solutions however provide no formal…

Many-body entanglement is an essential resource for many quantum technologies, but its scalable generation has been challenging on qubit platforms. However, the generation of continuous-variable (CV) entanglement can be extremely efficient,…

This paper presents a video coding scheme that combines traditional optimization methods with deep learning methods based on the Enhanced Compression Model (ECM). In this paper, the traditional optimization methods adaptively adjust the…

A Pseudo-Boolean (PB) constraint is a linear arithmetic constraint over Boolean variables. PB constraints are convenient and widely used in expressing NP-complete problems. We introduce a new, two step, method for transforming PB…

Three block encoding methods are evaluated for solving linear systems of equations using QSVT (Quantum Singular Value Transformation). These are ARCSIN, FABLE and PREPARE-SELECT. The performance of the encoders is evaluated using a suite of…

Query-by-Vocal Imitation (QBV) is about searching audio files within databases using vocal imitations created by the user's voice. Since most humans can effectively communicate sound concepts through voice, QBV offers the more intuitive and…

Variational dimensionality reduction methods are widely used for their accuracy, generative capabilities, and robustness. We introduce a unifying framework that generalizes both such as traditional and state-of-the-art methods. The…

Concept Activation Vectors (CAVs) provide a powerful approach for interpreting deep neural networks by quantifying their sensitivity to human-defined concepts. However, when computed independently at different layers, CAVs often exhibit…