Related papers: TransForm: Formally Specifying Transistency Models…

The increasing demand for large language model (LLM) serving has necessitated significant advancements in the optimization and profiling of LLM inference systems. As these models become integral to a wide range of applications, the need for…

Multimodal Large Language Model (MLLM) relies on the powerful LLM to perform multimodal tasks, showing amazing emergent abilities in recent studies, such as writing poems based on an image. However, it is difficult for these case studies to…

The Compute Express Link (CXL) technology facilitates the extension of CPU memory through byte-addressable SerDes links and cascaded switches, creating complex heterogeneous memory systems where CPU access to various endpoints differs in…

Large language models (LLMs) excel in generating coherent text, but they often struggle with context awareness, leading to inaccuracies in tasks requiring faithful adherence to provided information. We introduce FastMem, a novel method…

Transformer-based large language models (LLMs) have achieved strong performance across many natural language processing tasks. Nonetheless, their quadratic computational and memory requirements, particularly in self-attention layers, pose…

The rapid expansion of English technical terminology presents a significant challenge to traditional expert-based standardization, particularly in rapidly developing areas such as artificial intelligence and quantum computing. Manual…

Sequential DeepFake detection is an emerging task that predicts the manipulation sequence in order. Existing methods typically formulate it as an image-to-sequence problem, employing conventional Transformer architectures. However, these…

The Tsetlin Machine (TM) offers high-speed inference on resource-constrained devices such as CPUs. Its logic-driven operations naturally lend themselves to parallel execution on modern CPU architectures. Motivated by this, we propose an…

The reasoning capabilities of Large Language Models (LLMs) have increased greatly over the last few years, as have their size and complexity. Nonetheless, the use of LLMs in production remains challenging due to their unpredictable nature…

Existing Vision Language Models (VLMs) often struggle to preserve logic, entity identity, and artistic style during extended, interleaved image-text interactions. We identify this limitation as "Multimodal Context Drift", which stems from…

Transactional Memory (TM) is an approach to concurrency control that aims to make writing parallel programs both effective and simple. The approach is started in non-distributed multiprocessor systems, but is gaining popularity in…

This work establishes a rigorous theoretical foundation for analyzing deep learning systems by leveraging Infinite Time Turing Machines (ITTMs), which extend classical computation into transfinite ordinal steps. Using ITTMs, we reinterpret…

Modern processors deploy a variety of weak memory models, which for efficiency reasons may execute instructions in an order different to that specified by the program text. The consequences of instruction reordering can be complex and…

With the advent of faster computers, the notion of doing machine translation from a huge stored database of translation examples is no longer unreasonable. This paper describes an attempt to merge the Example-Based Machine Translation…

Recent development in Large Language Models (LLMs) and Multi-modal Large Language Models (MLLMs) have leverage Attention-based Transformer architectures and achieved superior performance and generalization capabilities. They have since…

State-of-the-art \emph{software transactional memory (STM)} implementations achieve good performance by carefully avoiding the overhead of \emph{incremental validation} (i.e., re-reading previously read data items to avoid inconsistency)…

Large Language Models (LLMs) have emerged as a transformative AI paradigm, profoundly influencing daily life through their exceptional language understanding and contextual generation capabilities. Despite their remarkable performance, LLMs…

Memory-based meta-learning is a technique for approximating Bayes-optimal predictors. Under fairly general conditions, minimizing sequential prediction error, measured by the log loss, leads to implicit meta-learning. The goal of this work…

Large language models (LLMs) are increasingly relied upon for complex multi-turn conversations across diverse real-world applications. However, existing benchmarks predominantly focus on single-turn evaluations, overlooking the models'…

The mismatch between an external language model (LM) and the implicitly learned internal LM (ILM) of RNN-Transducer (RNN-T) can limit the performance of LM integration such as simple shallow fusion. A Bayesian interpretation suggests to…