English
Related papers

Related papers: What Is the Minimum Architecture for Prolepsis? Ea…

200 papers

The extent to which decoder-only language models (LMs) engage in planning, that is, organizing intermediate computations to support coherent long-range generation, remains an important question, with implications for interpretability,…

Artificial Intelligence · Computer Science 2026-02-17 Muhammed Ustaomeroglu , Baris Askin , Gauri Joshi , Carlee Joe-Wong , Guannan Qu

We train Transformer-based language models on ten foundational algorithmic tasks and observe pronounced phase transitions in their loss curves that deviate from established power-law scaling trends. Over large ranges of compute, the…

Machine Learning · Computer Science 2026-01-15 Prudhviraj Naidu , Zixian Wang , Leon Bergen , Ramamohan Paturi

Despite the popularity of transformers in practice, their architectures are empirically designed and neither mathematically justified nor interpretable. Moreover, as indicated by many empirical studies, some components of transformer…

Machine Learning · Computer Science 2025-06-05 Peng Wang , Yifu Lu , Yaodong Yu , Druv Pai , Qing Qu , Yi Ma

Existing adaptation techniques typically require architectural modifications or added parameters, leading to high computational costs and complexity. We introduce Attention Projection Layer Adaptation (APLA), a simple approach to adapt…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Moein Sorkhei , Emir Konuk , Kevin Smith , Christos Matsoukas

The design of Large Language Models (LLMs) has long been hampered by a fundamental conflict within their core attention mechanism: its remarkable expressivity is built upon a computational complexity of O(H N^2) that grows quadratically…

Machine Learning · Computer Science 2025-12-01 Mingkuan Zhao , Wentao Hu , Jiayin Wang , Xin Lai , Tianchen Huang , Yuheng Min , Rui Yan , Xiaoyan Zhu

Frozen encoder--decoder language models are stateless: the latent representation is discarded after every forward pass, so no information persists across sessions. This paper presents a \textbf{proof-of-concept pilot study} showing that…

Machine Learning · Computer Science 2026-03-18 Hong Jeong

Transformers have become one of the dominant architectures in deep learning, particularly as a powerful alternative to convolutional neural networks (CNNs) in computer vision. However, Transformer training and inference in previous works…

Computer Vision and Pattern Recognition · Computer Science 2021-12-24 Zizheng Pan , Bohan Zhuang , Haoyu He , Jing Liu , Jianfei Cai

How much information do NLP tasks really need from a transformer's attention mechanism at application-time (inference)? From recent work, we know that there is sparsity in transformers and that the floating-points within its computation can…

Computation and Language · Computer Science 2021-06-03 Tianchu Ji , Shraddhan Jain , Michael Ferdman , Peter Milder , H. Andrew Schwartz , Niranjan Balasubramanian

Different transformer architectures implement identical linguistic computations via distinct connectivity patterns, yielding model imprinted ``computational fingerprints'' detectable through spectral analysis. Using graph signal processing…

Computation and Language · Computer Science 2025-10-23 Valentin Noël

Various layer-skipping methods have been proposed to accelerate token generation in large language models (LLMs). However, limited attention has been paid to a fundamental question: How do computational demands vary across the generation of…

Computation and Language · Computer Science 2025-10-10 Xuan Luo , Weizhi Wang , Xifeng Yan

Since transformer was firstly published in 2017, several works have been proposed to optimize it. However, the major structure of transformer remains unchanged, ignoring one of its main intrinsic limitations, which is the same static value…

Machine Learning · Computer Science 2025-12-30 Xiaowei Wang

Transformers have achieved extraordinary success in modern machine learning due to their excellent ability to handle sequential data, especially in next-token prediction (NTP) tasks. However, the theoretical understanding of their…

Machine Learning · Computer Science 2024-10-01 Ruiquan Huang , Yingbin Liang , Jing Yang

We present a miniature brain transformer architecture that extends the attention-coupled latent memory framework with four additional brain-region analogues: a thalamic relay, an amygdaloid salience module, a prefrontal working-memory (PFC)…

Neurons and Cognition · Quantitative Biology 2026-03-10 Hong Jeong

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…

Computation and Language · Computer Science 2025-11-04 Juan Gabriel Kostelec , Qinghai Guo

Compressing transformer weights makes large language models cheaper to deploy. But each layer's compression introduces an error. These errors accumulate as the signal passes through later layers, and how they accumulate is not well…

Machine Learning · Computer Science 2026-05-08 Abhinaba Basu , Kumkum Basu , Koushik Deb

While transformers achieve strong performance, their internal decision-making processes remain opaque. We investigate whether architectural constraints can enforce interpretability by design through architectural stream independence:…

Machine Learning · Computer Science 2026-03-10 Clayton Kerce , Alexis Fox

Multi-turn prompt injection follows a known attack path -- trust-building, pivoting, escalation but text-level defenses miss covert attacks where individual turns appear benign. We show this attack path leaves an activation-level signature…

Cryptography and Security · Computer Science 2026-05-01 Prashant Kulkarni

Architectural obfuscation - e.g., permuting hidden-state tensors, linearly transforming embedding tables, or remapping tokens - has recently gained traction as a lightweight substitute for heavyweight cryptography in privacy-preserving…

Cryptography and Security · Computer Science 2025-06-24 Marcos Florencio , Thomas Barton

Transformers resist surgical control. Ablating an attention head identified as critical for capitalization produces minimal behavioral change because distributed redundancy compensates for damage. This Hydra effect renders interpretability…

Machine Learning · Computer Science 2026-03-20 J. Clayton Kerce

Attention is a key component of the now ubiquitous pre-trained language models. By learning to focus on relevant pieces of information, these Transformer-based architectures have proven capable of tackling several tasks at once and…

Computation and Language · Computer Science 2021-04-14 Vincent Micheli , Quentin Heinrich , François Fleuret , Wacim Belblidia