English
Related papers

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

200 papers

Transformers have demonstrated remarkable capabilities in multi-step reasoning tasks. However, understandings of the underlying mechanisms by which they acquire these abilities through training remain limited, particularly from a…

Machine Learning · Computer Science 2025-12-09 Tong Yang , Yu Huang , Yingbin Liang , Yuejie Chi

Living organisms process information without any central control unit and without any ruling clock. We have been studying a novel computational strategy that uses a geometrically arranged excitable field, i.e., "field computation." As an…

Pattern Formation and Solitons · Physics 2009-11-10 Hiroki Nagahara , Takatoshi Ichino , Kenichi Yoshikawa

Circuit analysis of any certain model behavior is a central task in mechanistic interpretability. We introduce our circuit discovery pipeline with Sparse Autoencoders (SAEs) and a variant called Transcoders. With these two modules inserted…

Machine Learning · Computer Science 2024-07-23 Xuyang Ge , Fukang Zhu , Wentao Shu , Junxuan Wang , Zhengfu He , Xipeng Qiu

Transformers are effective at inferring the latent task from context via two inference modes: recognizing a task seen during training, and adapting to a novel one. Recent interpretability studies have identified from middle-layer…

Machine Learning · Computer Science 2026-05-06 Hao Yan , Haolin Yang , Yiqiao Zhong

Many real-world problems can be naturally described by mathematical formulas. The task of finding formulas from a set of observed inputs and outputs is called symbolic regression. Recently, neural networks have been applied to symbolic…

Machine Learning · Computer Science 2022-10-24 Martin Vastl , Jonáš Kulhánek , Jiří Kubalík , Erik Derner , Robert Babuška

A reliable language model should be able to signal, prior to generation, when a query falls outside its knowledge. We investigate whether representation geometry can provide such a pre-generation signal by measuring the deviation of hidden…

Computation and Language · Computer Science 2026-05-06 Yucheng Du

Mechanistic interpretability has transformed the analysis of transformer circuits by decomposing model behavior into competing algorithms, identifying phase transitions during training, and deriving closed-form predictions for when and why…

Machine Learning · Computer Science 2026-03-19 Alma Lago

Transformers have become the foundational architecture for a broad spectrum of sequence modeling applications, underpinning state-of-the-art systems in natural language processing, vision, and beyond. However, their theoretical limitations…

Computation and Language · Computer Science 2026-02-13 Michelle Yuan , Weiyi Sun , Amir H. Rezaeian , Jyotika Singh , Sandip Ghoshal , Yao-Ting Wang , Miguel Ballesteros , Yassine Benajiba

As transformers are equivariant to the permutation of input tokens, encoding the positional information of tokens is necessary for many tasks. However, since existing positional encoding schemes have been initially designed for NLP tasks,…

Computer Vision and Pattern Recognition · Computer Science 2024-06-10 Takeru Miyato , Bernhard Jaeger , Max Welling , Andreas Geiger

Transformer language models contain localized reasoning circuits, contiguous layer blocks that improve reasoning when duplicated at inference time. Finding these circuits currently requires brute-force sweeps costing 25 GPU hours per model.…

Artificial Intelligence · Computer Science 2026-04-02 Rajkiran Panuganti

Tensor networks and circuits are widely used data structures to represent pseudo-Boolean functions. These two formalisms have been studied primarily in separate communities, and this paper aims to establish equivalences between them. We…

Transformer-based language models exhibit complex and distributed behavior, yet their internal computations remain poorly understood. Existing mechanistic interpretability methods typically treat attention heads and multilayer perceptron…

Machine Learning · Computer Science 2025-11-26 Areeb Ahmad , Abhinav Joshi , Ashutosh Modi

Single-cell foundation models such as scGPT learn high-dimensional gene representations, but what biological knowledge these representations encode remains unclear. We systematically decode the geometric structure of scGPT internal…

Genomics · Quantitative Biology 2026-02-27 Ihor Kendiukhov

We study whether next-token prediction can yield world models that truly support planning, in a controlled symbolic setting where propositional STRIPS action models are learned from action traces alone and correctness can be evaluated…

Artificial Intelligence · Computer Science 2026-05-26 Carlos Núñez-Molina , Vicenç Gómez , Hector Geffner

We introduce a convolutional neural network that operates directly on graphs. These networks allow end-to-end learning of prediction pipelines whose inputs are graphs of arbitrary size and shape. The architecture we present generalizes…

In transformer architectures, position encoding primarily provides a sense of sequence for input tokens. While the original transformer paper's method has shown satisfactory results in general language processing tasks, there have been new…

Computation and Language · Computer Science 2024-03-26 Eren Unlu

Transformers were originally proposed as a sequence-to-sequence model for text but have become vital for a wide range of modalities, including images, audio, video, and undirected graphs. However, transformers for directed graphs are a…

Machine Learning · Computer Science 2023-09-01 Simon Geisler , Yujia Li , Daniel Mankowitz , Ali Taylan Cemgil , Stephan Günnemann , Cosmin Paduraru

A central idea in understanding brains and building artificial intelligence is that structure determines function. Yet, how the brain's complex structure arises from a limited set of genetic instructions remains a key question. The ultra…

Neurons and Cognition · Quantitative Biology 2026-01-28 Xingyu Liu , Yubin Li , Guozhang Chen

Neural networks have in recent years shown promise for helping software engineers write programs and even formally verify them. While semantic information plays a crucial part in these processes, it remains unclear to what degree popular…

Machine Learning · Computer Science 2023-06-27 Shizhuo Dylan Zhang , Curt Tigges , Stella Biderman , Maxim Raginsky , Talia Ringer

The cerebrovascular tree is a complex anatomical structure that plays a crucial role in the brain irrigation. A precise identification of the bifurcations in the vascular network is essential for understanding various cerebral pathologies.…

Image and Video Processing · Electrical Eng. & Systems 2023-08-25 Ibtissam Essadik , Anass Nouri , Raja Touahni , Florent Autrusseau