English
Related papers

Related papers: Crown, Frame, Reverse: Layer-Wise Scaling Variants…

200 papers

Structured pruning of modern large language models (LLMs) has emerged as a way of decreasing their high computational needs. Width pruning reduces the size of projection weight matrices (e.g., by removing attention heads) while maintaining…

Machine Learning · Computer Science 2024-06-25 Bo-Kyeong Kim , Geonmin Kim , Tae-Ho Kim , Thibault Castells , Shinkook Choi , Junho Shin , Hyoung-Kyu Song

Large Language Models (LLMs) have delivered impressive results in language understanding, generation, reasoning, and pushes the ability boundary of multimodal models. Transformer models, as the foundation of modern LLMs, offer a strong…

Computation and Language · Computer Science 2025-08-14 Weigao Sun , Jiaxi Hu , Yucheng Zhou , Jusen Du , Disen Lan , Kexin Wang , Tong Zhu , Xiaoye Qu , Yu Zhang , Xiaoyu Mo , Daizong Liu , Yuxuan Liang , Wenliang Chen , Guoqi Li , Yu Cheng

Despite the rapid evolution of training paradigms, the decoder backbone of large vision--language models (LVLMs) remains fundamentally rooted in the residual-connection Transformer architecture. Therefore, deciphering the distinct roles of…

Artificial Intelligence · Computer Science 2026-05-08 Gongli Xi , Ye Tian , Mengyu Yang , Huahui Yi , Liang Lin , Xiaoshuai Hao , Kun Wang , Wendong Wang

Recent works show we can linearize large language models (LLMs) -- swapping the quadratic attentions of popular Transformer-based LLMs with subquadratic analogs, such as linear attention -- avoiding the expensive pretraining costs. However,…

Machine Learning · Computer Science 2025-03-07 Michael Zhang , Simran Arora , Rahul Chalamala , Alan Wu , Benjamin Spector , Aaryan Singhal , Krithik Ramesh , Christopher Ré

Transformer architecture gradually dominates the LLM field. Recent advances in training optimization for Transformer-based large language models (LLMs) primarily focus on architectural modifications or optimizer adjustments. However, these…

Transformers have achieved great success in machine learning applications. Normalization techniques, such as Layer Normalization (LayerNorm, LN) and Root Mean Square Normalization (RMSNorm), play a critical role in accelerating and…

Machine Learning · Computer Science 2023-10-27 Zixuan Jiang , Jiaqi Gu , Hanqing Zhu , David Z. Pan

Large language models (LLMs) are fluent but largely static after pre-training; new or shifting knowledge is typically added with retrieval-augmented generation (RAG) or fine-tuning. RAG raises latency and engineering overhead and often…

Artificial Intelligence · Computer Science 2025-12-23 Rimom Costa

Large language models are powerful but costly. We ask whether meta-learning can make the pretraining of small language models not only better but also more interpretable. We integrate first-order MAML with subset-masked LM pretraining,…

Computation and Language · Computer Science 2025-11-10 David Demitri Africa , Yuval Weiss , Paula Buttery , Richard Diehl Martinez

Linear transformers have emerged as a subquadratic-time alternative to softmax attention and have garnered significant interest due to their fixed-size recurrent state that lowers inference cost. However, their original formulation suffers…

Computation and Language · Computer Science 2024-05-13 Jean Mercat , Igor Vasiljevic , Sedrick Keh , Kushal Arora , Achal Dave , Adrien Gaidon , Thomas Kollar

Large language models (LLMs) based on transformer architectures are typically described through collections of architectural components and training procedures, obscuring their underlying computational structure. This review article…

Machine Learning · Computer Science 2026-02-03 Vikram Krishnamurthy

Large language model (LLM) inference is increasingly bottlenecked by the Key-Value (KV) cache, yet the fine-grained structure of attention-head activations remains poorly understood. We show that pretrained Transformers exhibit a pervasive…

Machine Learning · Computer Science 2026-03-17 Khalid Shaikh , Asmit Kumar Singh , Rebecca Christopher Dsouza , Shikhar Shiromani

We propose Lizard, a linearization framework that transforms pretrained Transformer-based Large Language Models (LLMs) into subquadratic architectures. Transformers faces severe computational and memory bottlenecks with long sequences due…

Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive. Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger…

Machine Learning · Computer Science 2025-02-20 Yifei Yang , Zouying Cao , Xinbei Ma , Yao Yao , Libo Qin , Zhi Chen , Hai Zhao

This work analyzes the training dynamics of Image Restoration (IR) Transformers and uncovers a critical yet overlooked issue: conventional LayerNorm (LN) drives feature magnitudes to diverge to a million scale and collapses channel-wise…

Computer Vision and Pattern Recognition · Computer Science 2026-02-23 MinKyu Lee , Sangeek Hyun , Woojin Jun , Hyunjun Kim , Jiwoo Chung , Jae-Pil Heo

Continual learning (CL) in large language models (LLMs) is an evolving domain that focuses on developing efficient and sustainable training strategies to adapt models to emerging knowledge and achieve robustness in dynamic environments. Our…

Computation and Language · Computer Science 2025-02-13 Çağatay Yıldız , Nishaanth Kanna Ravichandran , Nitin Sharma , Matthias Bethge , Beyza Ermis

Learning rate configuration is a fundamental aspect of modern deep learning. The prevailing practice of applying a uniform learning rate across all layers overlooks the structural heterogeneity of Transformers, potentially limiting their…

Machine Learning · Computer Science 2026-05-28 Di He , Songjun Tu , Keyu Wang , Lu Yin , Shiwei Liu

Large Transformer-based language models are pre-trained on corpora of varying sizes, for a different number of steps and with different batch sizes. At the same time, more fundamental components, such as the pre-training objective or…

Computation and Language · Computer Science 2021-05-12 M. Aßenmacher , P. Schulze , C. Heumann

Despite the exciting performance, Transformer is criticized for its excessive parameters and computation cost. However, compressing Transformer remains as an open problem due to its internal complexity of the layer designs, i.e., Multi-Head…

Computer Vision and Pattern Recognition · Computer Science 2022-05-25 Gen Luo , Yiyi Zhou , Xiaoshuai Sun , Yan Wang , Liujuan Cao , Yongjian Wu , Feiyue Huang , Rongrong Ji

Multilingual Machine Translation promises to improve translation quality between non-English languages. This is advantageous for several reasons, namely lower latency (no need to translate twice), and reduced error cascades (e.g., avoiding…

Computation and Language · Computer Science 2023-05-05 Telmo Pessoa Pires , Robin M. Schmidt , Yi-Hsiu Liao , Stephan Peitz

Dynamic evaluation of language models (LMs) adapts model parameters at test time using gradient information from previous tokens and substantially improves LM performance. However, it requires over 3x more compute than standard inference.…

Computation and Language · Computer Science 2022-12-06 Kevin Clark , Kelvin Guu , Ming-Wei Chang , Panupong Pasupat , Geoffrey Hinton , Mohammad Norouzi