English
Related papers

Related papers: Circuit Fingerprints: How Answer Tokens Encode The…

200 papers

We present a handcrafted neural network that, without training, solves the seemingly difficult problem of encoding an arbitrary set of integers into a single numerical variable, and then recovering the original elements. While using only…

Neural and Evolutionary Computing · Computer Science 2025-06-17 Assaf Marron

We show that deep neural networks, including transformers and RNNs, pretrained as usual on next-token prediction, intrinsically discover and represent beliefs over 'quantum' and 'post-quantum' low-dimensional generative models of their…

Machine Learning · Computer Science 2025-07-15 Paul M. Riechers , Thomas J. Elliott , Adam S. Shai

A fundamental question in interpretability research is to what extent neural networks, particularly language models, implement reusable functions through subnetworks that can be composed to perform more complex tasks. Recent advances in…

Machine Learning · Computer Science 2025-06-24 Philipp Mondorf , Sondre Wold , Barbara Plank

Transformers have exhibited exceptional capabilities in sequence modeling tasks, leveraging self-attention and in-context learning. Critical to this success are induction heads, attention circuits that enable copying tokens based on their…

Machine Learning · Computer Science 2025-09-11 Francesco D'Angelo , Francesco Croce , Nicolas Flammarion

Steering vectors offer a training-free mechanism for controlling reasoning behaviors in large language models, but constructing effective vectors requires identifying genuine behavioral signals in the model's hidden states. For behaviors…

Computation and Language · Computer Science 2026-04-03 Haomin Zhuang , Hojun Yoo , Xiaonan Luo , Kehan Guo , Xiangliang Zhang

Understanding the learning process and the embedded computation in transformers is becoming a central goal for the development of interpretable AI. In the present study, we introduce a hierarchical filtering procedure for data models of…

Machine Learning · Computer Science 2025-06-11 Jerome Garnier-Brun , Marc Mézard , Emanuele Moscato , Luca Saglietti

Leveraging topos theory a semantics can be given to sequential circuits where time-sensitive gates, such as unit delay, are treated uniformly with combinational gates. Both kinds of gates are functions in a particular topos: the topos of…

Logic in Computer Science · Computer Science 2018-07-20 Arnaud Spiwack

Diagrams matter. Unfortunately, the deep learning community has no standard method for diagramming architectures. The current combination of linear algebra notation and ad-hoc diagrams fails to offer the necessary precision to understand…

Machine Learning · Computer Science 2024-02-09 Vincent Abbott

We show that standard Transformers without graph-specific modifications can lead to promising results in graph learning both in theory and practice. Given a graph, we simply treat all nodes and edges as independent tokens, augment them with…

Machine Learning · Computer Science 2022-10-25 Jinwoo Kim , Tien Dat Nguyen , Seonwoo Min , Sungjun Cho , Moontae Lee , Honglak Lee , Seunghoon Hong

We investigate the relationship between the geometry of token embeddings and their role in the next token prediction within transformer models. An important aspect of this connection uses the notion of empirical measure, which encodes the…

Computation and Language · Computer Science 2025-01-22 Karthik Viswanathan , Yuri Gardinazzi , Giada Panerai , Alberto Cazzaniga , Matteo Biagetti

In this paper, I introduce the retrieval problem, a simple yet common reasoning task that can be solved only by transformers with a minimum number of layers, which grows logarithmically with the input size. I empirically show that large…

Machine Learning · Computer Science 2025-10-29 Tiberiu Musat

Transformers are being used extensively across several sequence modeling tasks. Significant research effort has been devoted to experimentally probe the inner workings of Transformers. However, our conceptual and theoretical understanding…

Machine Learning · Computer Science 2020-10-13 Satwik Bhattamishra , Arkil Patel , Navin Goyal

Humans exhibit remarkable compositional reasoning by integrating knowledge from various sources. For example, if someone learns ( B = f(A) ) from one source and ( C = g(B) ) from another, they can deduce ( C=g(B)=g(f(A)) ) even without…

Artificial Intelligence · Computer Science 2025-10-14 Yutong Yin , Zhaoran Wang

We introduce a novel framework for learning vector representations of tree-structured geometric data focusing on 3D vascular networks. Our approach employs two sequentially trained Transformer-based autoencoders. In the first stage, the…

Image and Video Processing · Electrical Eng. & Systems 2025-06-16 James Batten , Michiel Schaap , Matthew Sinclair , Ying Bai , Ben Glocker

In decoder-only (causal) transformers, the computation graph created by causal masking routes information through both direct-path attention and indirect paths formed by intermediate tokens. We denote these indirect paths between token…

Machine Learning · Computer Science 2026-01-22 Hunjae Lee , Corey Clark

Developing and fielding complex systems requires proof that they are reliably correct with respect to their design and operating requirements. Especially for autonomous systems which exhibit unanticipated emergent behavior, fully…

Software Engineering · Computer Science 2024-02-28 Matthew Litton , Doron Drusinsky , James Bret Michael

Graph Neural Networks (GNN) can capture the geometric properties of neural representations in EEG data. Here we utilise those to study how reinforcement-based motor learning affects neural activity patterns during motor planning, leveraging…

Machine Learning · Computer Science 2024-11-01 Federico Nardi , Jinpei Han , Shlomi Haar , A. Aldo Faisal

VQC can be understood through the lens of Fourier analysis. It is already well-known that the function space represented by any circuit architecture can be described through a truncated Fourier sum. We show that the spectrum available to…

Machine Learning · Computer Science 2024-11-08 Marco Wiedmann , Maniraman Periyasamy , Daniel D. Scherer

Accurate 3D lane segment detection and topology reasoning are critical for structured online map construction in autonomous driving. Recent transformer-based approaches formulate this task as query-based set prediction, yet largely inherit…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Danny Abraham , Nikhil Kamalkumar Advani , Arun Das , Nikil Dutt

Finger vein recognition has drawn increasing attention as one of the most popular and promising biometrics due to its high distinguishes ability, security and non-invasive procedure. The main idea of traditional schemes is to directly…

Computer Vision and Pattern Recognition · Computer Science 2021-01-22 Zhongxia Zhang , Mingwen Wang