English
Related papers

Related papers: Explaining the Explainer: Understanding the Inner …

200 papers

Large language models (LLMs) demonstrate surprising capabilities, but we do not understand how they are implemented. One hypothesis suggests that these capabilities are primarily executed by small subnetworks within the LLM, known as…

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

Many promising approaches to symbolic regression have been presented in recent years, yet progress in the field continues to suffer from a lack of uniform, robust, and transparent benchmarking standards. In this paper, we address this…

Neural and Evolutionary Computing · Computer Science 2021-08-02 William La Cava , Patryk Orzechowski , Bogdan Burlacu , Fabrício Olivetti de França , Marco Virgolin , Ying Jin , Michael Kommenda , Jason H. Moore

We frame the task of predicting a semantic labeling as a sparse reconstruction procedure that applies a target-specific learned transfer function to a generic deep sparse code representation of an image. This strategy partitions training…

Computer Vision and Pattern Recognition · Computer Science 2014-10-17 Michael Maire , Stella X. Yu , Pietro Perona

Recent self-supervised learning (SSL) methods have shown impressive results in learning visual representations from unlabeled images. This paper aims to improve their performance further by utilizing the architectural advantages of the…

Computer Vision and Pattern Recognition · Computer Science 2022-07-20 Sukmin Yun , Hankook Lee , Jaehyung Kim , Jinwoo Shin

Vision-language models (VLMs) are powerful but remain opaque black boxes. We introduce the first framework for transparent circuit tracing in VLMs to systematically analyze multimodal reasoning. By utilizing transcoders, attribution graphs,…

Computer Vision and Pattern Recognition · Computer Science 2026-02-25 Jingcheng Yang , Tianhu Xiong , Shengyi Qian , Klara Nahrstedt , Mingyuan Wu

Mechanistic interpretability aims to reverse-engineer large language models (LLMs) into human-understandable computational circuits. However, the complexity of pretrained models often obscures the minimal mechanisms required for specific…

Computation and Language · Computer Science 2025-10-30 Rabin Adhikari

Decoder-only transformers lead to a step-change in capability of large language models. However, opinions are mixed as to whether they are really planning or reasoning. A path to making progress in this direction is to study the model's…

Machine Learning · Computer Science 2025-02-14 Andrew Cohen , Andrey Gromov , Kaiyu Yang , Yuandong Tian

The reconstruction of particle tracks from hits in tracking detectors is a computationally intensive task due to the large combinatorics of detector signals. Recent efforts have proven that ML techniques can be successfully applied to the…

High Energy Physics - Experiment · Physics 2024-11-19 Nathalie Soybelman , Carlo Schiavi , Francesco A. Di Bello , Eilam Gross

Regression analysis is used for prediction and to understand the effect of independent variables on dependent variables. Symbolic regression (SR) automates the search for non-linear regression models, delivering a set of hypotheses that…

Machine Learning · Computer Science 2025-04-09 Fabricio Olivetti de Franca , Gabriel Kronberger

Mechanistic interpretability often uses activation patching, causal tracing, path patching, and steering directions to reveal behaviorally meaningful directions in Transformer activation space. This paper develops a field-theoretic…

Machine Learning · Computer Science 2026-05-26 David N. Olivieri , Antonio F. Pérez Rodríguez

Symbolic regression is a machine learning method with the goal to produce interpretable results. Unlike other machine learning methods such as, e.g. random forests or neural networks, which are opaque, symbolic regression aims to model and…

Machine Learning · Computer Science 2024-06-07 Yousef A. Radwan , Gabriel Kronberger , Stephan Winkler

Understanding and predicting the activity of oxide perovskite catalysts for the oxygen evolution reaction (OER) requires descriptors that are both accurate and physically interpretable. While symbolic regression (SR) offers a path to…

Data Analysis, Statistics and Probability · Physics 2025-07-17 Yeming Xian , Xiaoming Wang , Yanfa Yan

Counting serves as a simple but powerful test of a Large Vision-Language Model's (LVLM's) reasoning; it forces the model to identify each individual object and then add them all up. In this study, we investigate how LVLMs implement counting…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Liwei Che , Zhiyu Xue , Yihao Quan , Benlin Liu , Zeru Shi , Michelle Hurst , Jacob Feldman , Ruixiang Tang , Ranjay Krishna , Vladimir Pavlovic

Circuit discovery has gradually become one of the prominent methods for mechanistic interpretability, and research on circuit completeness has also garnered increasing attention. Methods of circuit discovery that do not guarantee…

Machine Learning · Computer Science 2025-09-26 Hang Chen , Jiaying Zhu , Xinyu Yang , Wenya Wang

In this paper we propose the Ray-Patch querying, a novel model to efficiently query transformers to decode implicit representations into target views. Our Ray-Patch decoding reduces the computational footprint and increases inference speed…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 T. Berriel Martins , Javier Civera

Modern task-oriented semantic parsing approaches typically use seq2seq transformers to map textual utterances to semantic frames comprised of intents and slots. While these models are empirically strong, their specific strengths and…

Computation and Language · Computer Science 2021-05-31 Shrey Desai , Ahmed Aly

Recent studies suggest that large language models (LLMs) possess the capability to solve graph reasoning tasks. Notably, even when graph structures are embedded within textual descriptions, LLMs can still effectively answer related…

Computation and Language · Computer Science 2025-10-21 Xinnan Dai , Kai Yang , Jay Revolinsky , Kai Guo , Aoran Wang , Bohang Zhang , Jiliang Tang

To improve the explainability of leading Transformer networks used in NLP, it is important to tease apart genuine symbolic rules from merely associative input-output patterns. However, we identify several inconsistencies in how…

Machine Learning · Computer Science 2023-03-02 Tommi Gröndahl , Yujia Guo , N. Asokan

The speed and accuracy with which robots are able to interpret natural language is fundamental to realizing effective human-robot interaction. A great deal of attention has been paid to developing models and approximate inference algorithms…

Robotics · Computer Science 2019-03-25 Siddharth Patki , Andrea F. Daniele , Matthew R. Walter , Thomas M. Howard
‹ Prev 1 4 5 6 7 8 10 Next ›