相关论文: Generalizing the Paige-Tarjan Algorithm by Abstrac…

Quantum simulation is a promising application of future quantum computers. Product formulas, or Trotterization, are the oldest and still remain an appealing method to simulate quantum systems. For an accurate product formula approximation,…

Training large language models (LLMs) from scratch can yield models with unique functionalities and strengths, but it is costly and often leads to redundant capabilities. A more cost-effective alternative is to fuse existing pre-trained…

Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation, with the potential to overcome many of the weaknesses of conventional phrase-based translation systems. Unfortunately, NMT systems are known to…

The relationship between abstract interpretation and partial deduction has received considerable attention and (partial) integrations have been proposed starting from both the partial deduction and abstract interpretation perspectives. In…

Compressive covariance estimation has arisen as a class of techniques whose aim is to obtain second-order statistics of stochastic processes from compressive measurements. Recently, these methods have been used in various image processing…

Large language models (LLMs) have revolutionized AI applications, yet their enormous computational demands severely limit deployment and real-time performance. Quantization methods can help reduce computational costs, however, attaining the…

This study proposes a knowledge distillation algorithm based on large language models and feature alignment, aiming to effectively transfer the knowledge of large pre-trained models into lightweight student models, thereby reducing…

Language models (LMs) pre-trained on massive amounts of text, in particular bidirectional encoder representations from Transformers (BERT), generative pre-training (GPT), and GPT-2, have become a key technology for many natural language…

Particle smoothers are widely used algorithms allowing to approximate the smoothing distribution in hidden Markov models. Existing algorithms often suffer from slow computational time or degeneracy. We propose in this paper a way to improve…

Continual post-training (CPT) is a popular and effective technique for adapting foundation models like multimodal large language models to specific and ever-evolving downstream tasks. While existing research has primarily concentrated on…

Deep neural networks (DNNs) have been proven to be effective in solving many real-life problems, but its high computation cost prohibits those models from being deployed to edge devices. Pruning, as a method to introduce zeros to model…

Transformer-based models, exemplified by GPT-3, ChatGPT, and GPT-4, have recently garnered considerable attention in both academia and industry due to their promising performance in general language tasks. Nevertheless, these models…

A promising route towards fault-tolerant quantum error correction is the concatenation of a Gottesman-Kitaev-Preskill (GKP) code with a qubit code. Development of such concatenated codes requires simulation tools which realistically model…

Adaptive learning is necessary for non-stationary environments where the learning machine needs to forget past data distribution. Efficient algorithms require a compact model update to not grow in computational burden with the incoming data…

With the rapid progress of speech language models (SLMs), discrete speech tokens have emerged as a core interface between speech and text, enabling unified modeling across modalities. Recent speech tokenization approaches aim to isolate…

Post-editing (PE) machine translation (MT) is widely used for dissemination because it leads to higher productivity than human translation from scratch (HT). In addition, PE translations are found to be of equal or better quality than HTs.…

While the use of machine learning for the detection of propaganda techniques in text has garnered considerable attention, most approaches focus on "black-box" solutions with opaque inner workings. Interpretable approaches provide a…

Tracing just-in-time compilation is a popular compilation technique for the efficient implementation of dynamic languages, which is commonly used for JavaScript, Python and PHP. We provide a formal model of tracing JIT compilation of…

Quantum stabilizer codes constructed from sparse matrices have good performance and can be efficiently decoded by belief propagation (BP). A conventional BP decoding algorithm treats binary stabilizer codes as additive codes over GF(4).…

Probabilistic graphical models are a key tool in machine learning applications. Computing the partition function, i.e., normalizing constant, is a fundamental task of statistical inference but it is generally computationally intractable,…