English
Related papers

Related papers: Architecture Determines Observability of Transform…

200 papers

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

Instruction tuned reasoning models are increasingly deployed with safety classifiers trained on frozen embeddings, assuming representation stability across model updates. We systematically investigate this assumption and find it fails:…

Machine Learning · Computer Science 2026-03-03 Subramanyam Sahoo , Vinija Jain , Divya Chaudhary , Aman Chadha

Chain-of-thought (CoT) prompting assumes that generated reasoning reflects a model's internal computation. We show this assumption is wrong in a specific, measurable way: models internally detect their own reasoning errors but outwardly…

Computation and Language · Computer Science 2026-05-12 Aojie Yuan , Zhiyuan Julian Su , Haiyue Zhang , Yi Nian , Yue Zhao

In this paper we investigate transformer architectures designed for partially observable online reinforcement learning. The self-attention mechanism in the transformer architecture is capable of capturing long-range dependencies and it is…

Machine Learning · Computer Science 2024-10-16 Subhojeet Pramanik , Esraa Elelimy , Marlos C. Machado , Adam White

With the perpetual increase of complexity of the state-of-the-art deep neural networks, it becomes a more and more challenging task to maintain their interpretability. Our work aims to evaluate the effects of adversarial training utilized…

Computer Vision and Pattern Recognition · Computer Science 2023-11-21 Delyan Boychev

Transformer architectures have revolutionized artificial intelligence (AI) through their attention mechanisms, yet the computational principles underlying their success remain opaque. We present a novel theoretical framework that…

Machine Learning · Computer Science 2026-05-07 Mu Qiao

Selective Prediction is the task of rejecting inputs a model would predict incorrectly on. This involves a trade-off between input space coverage (how many data points are accepted) and model utility (how good is the performance on accepted…

The architectural blueprint of today's leading text-to-image models contains a fundamental flaw: an inability to handle logical composition. This survey investigates this breakdown across three core primitives-negation, counting, and…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Mayank Vatsa , Aparna Bharati , Richa Singh

Recent studies have put into question the belief that emergent abilities in language models are exclusive to large models. This skepticism arises from two observations: 1) smaller models can also exhibit high performance on emergent…

Computation and Language · Computer Science 2025-01-16 Zhengxiao Du , Aohan Zeng , Yuxiao Dong , Jie Tang

As machine learning gets adopted into the industry quickly, trustworthiness is increasingly in focus. Yet, efficiency and sustainability of robust training pipelines still have to be established. In this work, we consider a simple pipeline…

Machine Learning · Computer Science 2025-07-15 Benedict Gerlach , Marie Anastacio , Holger H. Hoos

The design of metaprogramming languages requires appreciation of the tradeoffs that exist between important language characteristics such as safety properties, expressive power, and succinctness. Unfortunately, such tradeoffs are little…

Programming Languages · Computer Science 2009-09-29 Todd L. Veldhuizen

To make safe transitions from autonomous to manual control, a vehicle must have a representation of the awareness of driver state; two metrics which quantify this state are the Observable Readiness Index and Takeover Time. In this work, we…

Computer Vision and Pattern Recognition · Computer Science 2023-01-20 Ross Greer , Nachiket Deo , Akshay Rangesh , Pujitha Gunaratne , Mohan Trivedi

The field of deep learning has witnessed significant breakthroughs, spanning various applications, and fundamentally transforming current software capabilities. However, alongside these advancements, there have been increasing concerns…

Machine Learning · Computer Science 2025-05-07 Nikita Ravi , Abhinav Goel , James C. Davis , George K. Thiruvathukal

Self-recognition is a crucial metacognitive capability for AI systems, relevant not only for psychological analysis but also for safety, particularly in evaluative scenarios. Motivated by contradictory interpretations of whether models…

Artificial Intelligence · Computer Science 2025-10-07 Xiaoyan Bai , Aryan Shrivastava , Ari Holtzman , Chenhao Tan

Attention mechanism is effective in both focusing the deep learning models on relevant features and interpreting them. However, attentions may be unreliable since the networks that generate them are often trained in a weakly-supervised…

Machine Learning · Statistics 2020-06-11 Jay Heo , Hae Beom Lee , Saehoon Kim , Juho Lee , Kwang Joon Kim , Eunho Yang , Sung Ju Hwang

The deployment of large language models (LLMs) in production environments has created an urgent need for observability systems that span the full stack -- from model internals to GPU kernels. Yet existing monitoring approaches address…

Software Engineering · Computer Science 2026-04-30 Twinkll Sisodia

Learning-based methods for inverse problems, adapting to the data's inherent structure, have become ubiquitous in the last decade. Besides empirical investigations of their often remarkable performance, an increasing number of works…

Numerical Analysis · Mathematics 2023-07-21 Clemens Arndt , Sören Dittmer , Nick Heilenkötter , Meira Iske , Tobias Kluth , Judith Nickel

Current agentic AI architectures are fundamentally incompatible with the security and epistemological requirements of high-stakes scientific workflows. The problem is not inadequate alignment or insufficient guardrails, it is architectural:…

Cryptography and Security · Computer Science 2026-02-11 Manish Bhattarai , Minh Vu

Self-attention is usually described as a flexible, content-adaptive way to mix a token with information from its past. We reinterpret causal self-attention transformers, the backbone of modern foundation models, within a probabilistic…

Machine Learning · Computer Science 2026-03-24 Deepak Agarwal , Dhyey Dharmendrakumar Mavani , Suyash Gupta , Karthik Sethuraman , Tejas Dharamsi

Classically, any structure for a signature $\Sigma$ may be completed to a model of a desired regular theory $T$ by means of the chase construction or small object argument. Moreover, this exhibits $\mathrm{Mod}(T)$ as weakly reflective in…

Logic · Mathematics 2026-04-14 Henrik Forssell , Peter LeFanu Lumsdaine
‹ Prev 1 8 9 10 Next ›