English
Related papers

Related papers: Architecture Determines Observability of Transform…

200 papers

Deep learning has achieved great success in computer vision, but remains vulnerable to adversarial attacks. Adversarial training is the leading defense designed to improve model robustness. However, its effect on the transferability of…

Computer Vision and Pattern Recognition · Computer Science 2025-12-15 Mohamed Awad , Mahmoud Akrm , Walid Gomaa

Trusting machine learning algorithms requires having confidence in their outputs. Confidence is typically interpreted in terms of model reliability, where a model is reliable if it produces a high proportion of correct outputs. However,…

Machine Learning · Computer Science 2023-11-01 Jonathan Vandenburgh

Recent work has shown that LLMs can sometimes detect when steering vectors are injected into their residual stream and identify the injected concept -- a phenomenon termed "introspective awareness." We investigate the mechanisms underlying…

Machine Learning · Computer Science 2026-05-18 Uzay Macar , Li Yang , Atticus Wang , Peter Wallich , Emmanuel Ameisen , Jack Lindsey

Mechanistic interpretability aims to understand how neural networks generalize beyond their training data by reverse-engineering their internal structures. We introduce patterning as the dual problem: given a desired form of generalization,…

Machine Learning · Computer Science 2026-01-21 George Wang , Daniel Murfet

Robustness is often regarded as a critical future challenge for real-world applications, where stability is essential. However, as models often learn tasks in a similar order, we hypothesize that easier tasks will be easier regardless of…

Machine Learning · Computer Science 2026-02-04 Shir Ashury-Tahan , Ariel Gera , Elron Bandel , Michal Shmueli-Scheuer , Leshem Choshen

A robot's ability to provide descriptions of its decisions and beliefs promotes effective collaboration with humans. Providing such transparency is particularly challenging in integrated robot systems that include knowledge-based reasoning…

Artificial Intelligence · Computer Science 2020-10-22 Tiago Mota , Mohan Sridharan

When a system commits to a hypothesis, much of the evidential structure behind that commitment is lost to compression. Standard accounts assume that selected content and scalar confidence suffice for downstream control. This paper argues…

Artificial Intelligence · Computer Science 2026-04-21 Mark Walsh

Deploying reinforcement learning in safety critical domains, from autonomous vehicles to medical decision support, is constrained by failures arising when systems encounter unfamiliar conditions. We argue that the fundamental bottleneck is…

Systems and Control · Electrical Eng. & Systems 2026-05-27 Chayan Banerjee , Ethan Goan

Instruction-following language models are trained to be helpful and safe, yet their safety behavior can deteriorate under benign fine-tuning and worsen under adversarial updates. Existing defenses often offer limited protection or force a…

Computation and Language · Computer Science 2026-05-12 Jyotin Goel , Souvik Maji , Pratik Mazumder

Recently, transformers have become incredibly popular in computer vision and vision-language tasks. This notable rise in their usage can be primarily attributed to the capabilities offered by attention mechanisms and the outstanding ability…

Computer Vision and Pattern Recognition · Computer Science 2023-12-08 Mayank Vatsa , Anubhooti Jain , Richa Singh

Chain-of-thought (CoT) outputs let us read a model's step-by-step reasoning. Since any long, serial reasoning process must pass through this textual trace, the quality of the CoT is a direct window into what the model is thinking. This…

Machine Learning · Computer Science 2025-12-02 Austin Meek , Eitan Sprejer , Iván Arcuschin , Austin J. Brockmeier , Steven Basart

Transformers are crucial across many AI fields, such as large language models, computer vision, and reinforcement learning. This prominence stems from the architecture's perceived universality and scalability compared to alternatives. This…

Machine Learning · Computer Science 2025-12-23 Amirreza Abbasi , Mohsen Hooshmand

Large language models now write software, draft legal documents, and produce clinical notes, yet fundamental limits, from Turing and Arrow to the No Free Lunch theorems, shape what computation can do. This thesis turns such impossibility…

Artificial Intelligence · Computer Science 2026-05-25 Dongxin Guo

The most important architectural problem in AI is not the size of the model but the absence of a layer that carries forward what the model has come to understand. Sessions end. Context windows fill. Memory APIs return flat facts that the…

Artificial Intelligence · Computer Science 2026-04-21 Samuel Sameer Tanguturi

In this work, we consider error detection via simulation for reversible circuit architectures. We rigorously prove that reversibility augments the performance of this simple error detection protocol to a considerable degree. A single…

Hardware Architecture · Computer Science 2023-01-11 Lukas Burgholzer , Robert Wille , Richard Kueng

Mechanistic interpretability work attempts to reverse engineer the learned algorithms present inside neural networks. One focus of this work has been to discover 'circuits' -- subgraphs of the full model that explain behaviour on specific…

Machine Learning · Computer Science 2024-07-12 Joseph Miller , Bilal Chughtai , William Saunders

AI coding agents select frameworks, scaffold infrastructure, and wire integrations, often in seconds. These are architectural decisions, yet almost no one reviews them as such. We identify five mechanisms by which agents make implicit…

Software Engineering · Computer Science 2026-04-08 Phongsakon Mark Konrad , Tim Lukas Adam , Riccardo Terrenzi , Serkan Ayvaz

Transformers have recently been utilized to perform object detection and tracking in the context of autonomous driving. One unique characteristic of these models is that attention weights are computed in each forward pass, giving insights…

Computer Vision and Pattern Recognition · Computer Science 2022-10-27 Felicia Ruppel , Florian Faion , Claudius Gläser , Klaus Dietmayer

PGD adversarial training, the standard robustness method, can reduce Jacobian Frobenius norm yet worsen clean-input geometry (e.g., TDI 1.336 vs. ERM 1.093). We show this is not an implementation artifact but a theorem-level consequence of…

Machine Learning · Computer Science 2026-04-28 Vishal Rajput

Robustness is a basic property of any control system. In the context of linear output regulation, it was proved that embedding an internal model of the exogenous signals is necessary and sufficient to achieve tracking of the desired…

Systems and Control · Electrical Eng. & Systems 2021-04-23 Michelangelo Bin , Daniele Astolfi , Lorenzo Marconi