Related papers: Fast Lexically Constrained Viterbi Algorithm (FLCV…

Token reduction is an effective way to accelerate long-video vision-language models (VLMs), but most existing methods are designed for dense Transformers and do not directly account for hybrid architectures that interleave attention with…

Vision-Language Models (VLMs) demand substantial computational resources during inference, largely due to the extensive visual input tokens for representing visual information. Previous studies have noted that visual tokens tend to receive…

When using an LLM to process text outside the training domain(s), an often overlooked factor is vocabulary mismatch, where the general-domain tokenizer fails to capture frequent domain-specific terms, leading to higher token fertility and…

Learning-based probabilistic models can be combined with an entropy coder for data compression. However, due to the high complexity of learning-based models, their practical application as text compressors has been largely overlooked. To…

Visual language models encounter challenges in computational efficiency and latency, primarily due to the substantial redundancy in the token representations of high-resolution images and videos. Current attention/similarity-based…

Background: Hidden Markov models (HMM) are powerful machine learning tools successfully applied to problems of computational Molecular Biology. In a predictive task, the HMM is endowed with a decoding algorithm in order to assign the most…

Congestion control is a fundamental component of Internet infrastructure, and researchers have dedicated considerable effort to developing improved congestion control algorithms. However, despite extensive study, existing algorithms…

Large Multimodal Models (LMMs) have shown significant visual reasoning capabilities by connecting a visual encoder and a large language model. LMMs typically take in a fixed and large amount of visual tokens, such as the penultimate layer…

Deploying large language models (LLMs) encounters challenges due to intensive computational and memory requirements. Our research examines vocabulary trimming (VT) inspired by restricting embedding entries to the language of interest to…

Large language models (LLMs) have recently shown remarkable performance across a wide range of tasks. However, the substantial number of parameters in LLMs contributes to significant latency during model inference. This is particularly…

Current autoregressive Vision Language Models (VLMs) usually rely on a large number of visual tokens to represent images, resulting in a need for more compute especially at inference time. To address this problem, we propose Mask-LLaVA, a…

Many of the current state-of-the-art Large Vocabulary Continuous Speech Recognition Systems (LVCSR) are hybrids of neural networks and Hidden Markov Models (HMMs). Most of these systems contain separate components that deal with the…

The classic algorithm of Viterbi computes the most likely path in a Hidden Markov Model (HMM) that results in a given sequence of observations. It runs in time $O(Tn^2)$ given a sequence of $T$ observations from a HMM with $n$ states.…

Audio-Visual Speech Recognition (AVSR) achieves robust speech recognition in noisy environments by combining auditory and visual information. However, recent Large Language Model (LLM) based AVSR systems incur high computational costs due…

Large language models (LLM) trained using the next-token-prediction objective, such as GPT3 and PaLM, have revolutionized natural language processing in recent years by showing impressive zero-shot and few-shot capabilities across a wide…

Recent advancements in vision-language models (VLMs) have expanded their potential for real-world applications, enabling these models to perform complex reasoning on images. In the widely used fully autoregressive transformer-based models…

Transformer models have revolutionized natural language processing, achieving state-of-the-art performance and demonstrating remarkable scalability. However, their memory demands, particularly due to maintaining full context in memory, pose…

Current large language models (LLMs) primarily utilize next-token prediction method for inference, which significantly impedes their processing speed. In this paper, we introduce a novel inference methodology termed next-sentence…

To effectively reduce the visual tokens in Visual Large Language Models (VLLMs), we propose a novel approach called Window Token Concatenation (WiCo). Specifically, we employ a sliding window to concatenate spatially adjacent visual tokens.…

Large language models (LLMs) face significant token efficiency bottlenecks in code generation and logical reasoning tasks, a challenge that directly impacts inference cost and model interpretability. This paper proposes a formal framework…