English
Related papers

Related papers: Latent Flow Transformer

200 papers

Flow-based Transformer models have achieved state-of-the-art image generation performance, but often suffer from high inference latency and computational cost due to their large parameter sizes. To improve inference efficiency without…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Yuhang Ma , Bo Cheng , Shanyuan Liu , Hongyi Zhou , Liebucha Wu , Dawei Leng , Yuhui Yin

Multivariate time-series (MTS) forecasting is fundamental to applications ranging from urban mobility and resource management to climate modeling. While recent generative models based on denoising diffusion have advanced state-of-the-art…

Machine Learning · Computer Science 2025-11-21 Seyed Mohamad Moghadas , Bruno Cornelis , Adrian Munteanu

Most learning-based image compression methods lack efficiency for high image quality due to their non-invertible design. The decoding function of the frequently applied compressive autoencoder architecture is only an approximated inverse of…

Image and Video Processing · Electrical Eng. & Systems 2024-05-24 Marc Windsheimer , Fabian Brand , André Kaup

In Machine Translation, Large Language Models (LLMs) have generally underperformed compared to conventional encoder-decoder systems and thus see limited adoption. However, LLMs excel at modeling contextual information, making them a natural…

Computation and Language · Computer Science 2026-03-24 Ireh Kim , Tesia Sker , Chanwoo Kim

Augmenting large language models (LLMs) with auxiliary tokens has emerged as a promising strategy for enhancing model performance. In this work, we introduce a lightweight method termed latent tokens; these are dummy tokens that may be…

Machine Learning · Computer Science 2025-05-20 Yuchang Sun , Yanxi Chen , Yaliang Li , Bolin Ding

We revisit the design choices in Transformers, and propose methods to address their weaknesses in handling long sequences. First, we propose a simple layer named gated attention unit, which allows the use of a weaker single-head attention…

Machine Learning · Computer Science 2022-06-28 Weizhe Hua , Zihang Dai , Hanxiao Liu , Quoc V. Le

Parameter-efficient fine-tuning (PEFT) allows model builders to capture the task-specific parameters into adapters, which are a fraction of the size of the original base model. Popularity of PEFT technique for fine-tuning has led to the…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-10-24 Saransh Gupta , Umesh Deshpande , Travis Janssen , Swami Sundararaman

Transformer is leading a trend in the field of image processing. Despite the great success that existing lightweight image processing transformers have achieved, they are tailored to FLOPs or parameters reduction, rather than practical…

Computer Vision and Pattern Recognition · Computer Science 2024-04-30 Junbo Qiao , Wei Li , Haizhen Xie , Hanting Chen , Yunshuai Zhou , Zhijun Tu , Jie Hu , Shaohui Lin

Large language models (LLMs) require substantial compute, and thus energy, at inference time. While quantizing weights and activations is effective at improving efficiency, naive quantization of LLMs can significantly degrade performance…

Machine Learning · Computer Science 2025-06-06 Boris van Breugel , Yelysei Bondarenko , Paul Whatmough , Markus Nagel

Transformer-based language models utilize the attention mechanism for substantial performance improvements in almost all natural language processing (NLP) tasks. Similar attention structures are also extensively studied in several other…

Computation and Language · Computer Science 2023-05-17 Nurullah Sevim , Ege Ozan Özyedek , Furkan Şahinuç , Aykut Koç

Multimodal language models (MLLMs) require large parameter capacity to align high-dimensional visual features with linguistic representations, making them computationally heavy and difficult to deploy efficiently. We introduce a progressive…

Computer Vision and Pattern Recognition · Computer Science 2025-12-10 Jawad Ibn Ahad , Maisha Rahman , Amrijit Biswas , Muhammad Rafsan Kabir , Robin Krambroeckers , Sifat Momen , Nabeel Mohammed , Shafin Rahman

We introduce a new paradigm for generative modeling built on Continuous Normalizing Flows (CNFs), allowing us to train CNFs at unprecedented scale. Specifically, we present the notion of Flow Matching (FM), a simulation-free approach for…

Machine Learning · Computer Science 2023-02-09 Yaron Lipman , Ricky T. Q. Chen , Heli Ben-Hamu , Maximilian Nickel , Matt Le

Flow Matching (FM) is a recent generative modelling technique: we aim to learn how to sample from distribution $\mathfrak{X}_1$ by flowing samples from some distribution $\mathfrak{X}_0$ that is easy to sample from. The key trick is that…

Differential Geometry · Mathematics 2025-10-24 Finn M. Sherry , Bart M. N. Smets

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…

Computation and Language · Computer Science 2024-04-19 Pengfei Wu , Jiahao Liu , Zhuocheng Gong , Qifan Wang , Jinpeng Li , Jingang Wang , Xunliang Cai , Dongyan Zhao

The rapid development of the Transformer-based Large Language Models (LLMs) in recent years has been closely linked to their ever-growing and already enormous sizes. Many LLMs contain hundreds of billions of parameters and require dedicated…

Computation and Language · Computer Science 2025-02-26 Mahsa Salmani , Ilya Soloveychik

Non-uniform structured network pruning methods can effectively reduce Large Language Model (LLM) size by eliminating redundant channels or layers, offering lower performance degradation than uniform strategies. However, existing non-uniform…

Machine Learning · Computer Science 2025-08-07 Zuxin Ma , Yunhe Cui , Yongbin Qin

Although large language models (LLMs) have achieved revolutionary breakthroughs in many fields, their large model size and high computational cost pose significant challenges for practical deployment on resource-constrained edge devices. To…

Machine Learning · Computer Science 2025-10-29 Yao Lu , Yuqi Li , Wenbin Xie , Shanqing Yu , Qi Xuan , Zhaowei Zhu , Shiping Wen

While machine learning is widely used to optimize wireless networks, training a separate model for each task in communication and localization is becoming increasingly unsustainable due to the significant costs associated with training and…

Signal Processing · Electrical Eng. & Systems 2025-11-20 Mohammad Cheraghinia , Eli De Poorter , Jaron Fontaine , Kwang Soon Kim , Merouane Debbah , Adnan Shahid

Transformer-based language models traditionally use uniform (isotropic) layer sizes, yet they ignore the diverse functional roles that different depths can play and their computational capacity needs. Building on Layer-Wise Scaling (LWS)…

Computation and Language · Computer Science 2025-09-09 Andrei Baroian , Kasper Notebomer

While the approximation properties of single-layer Transformer architectures have been studied in recent works, a rigorous theoretical understanding of the multi-layer setting remains limited. In this work, we establish that multi-layer…

Machine Learning · Computer Science 2026-05-19 Penghao Yu , Haotian Jiang , Zeyu Bao , Qianxiao Li