English
Related papers

Related papers: InterpBench: Semi-Synthetic Transformers for Evalu…

200 papers

Given the ever-increasing computational costs of modern machine learning models, we need to find new ways to reuse such expert models and thus tap into the resources that have been invested in their creation. Recent work suggests that the…

Computer Vision and Pattern Recognition · Computer Science 2020-11-11 Robin Rombach , Patrick Esser , Björn Ommer

Since early machine learning models, metrics such as accuracy and precision have been the de facto way to evaluate and compare trained models. However, a single metric number doesn't fully capture the similarities and differences between…

Computer Vision and Pattern Recognition · Computer Science 2022-08-02 Ahmad Mustapha , Wael Khreich , Wes Masri

Transformer neural networks can exhibit a surprising capacity for in-context learning (ICL) despite not being explicitly trained for it. Prior work has provided a deeper understanding of how ICL emerges in transformers, e.g. through the…

Machine Learning · Computer Science 2023-12-13 Aaditya K. Singh , Stephanie C. Y. Chan , Ted Moskovitz , Erin Grant , Andrew M. Saxe , Felix Hill

Understanding when and how linguistic knowledge emerges during language model training remains a central challenge for interpretability. Most existing tools are post hoc, rely on scalar metrics, or require nontrivial integration effort,…

Computation and Language · Computer Science 2025-07-08 Nura Aljaafari , Danilo S. Carvalho , André Freitas

In recent years, Artificial Intelligence has become a powerful partner for complex tasks such as data analysis, prediction, and problem-solving, yet its lack of transparency raises concerns about its reliability. In sensitive domains such…

Machine Learning · Computer Science 2026-03-10 Jesús Sánchez Ochoa , Enrique Tomás Martínez Beltrán , Alberto Huertas Celdrán

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

Transferability estimation identifies the best pre-trained models for downstream tasks without incurring the high computational cost of full fine-tuning. This capability facilitates deployment and advances the pre-training and fine-tuning…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Yaoyan Zheng , Huiqun Wang , Nan Zhou , Di Huang

We introduce a simple post-training method that makes transformer attention sparse without sacrificing performance. Applying a flexible sparsity regularisation under a constrained-loss objective, we show on models up to 7B parameters that…

Machine Learning · Computer Science 2026-05-26 Florent Draye , Anson Lei , Hsiao-Ru Pan , Ingmar Posner , Bernhard Schölkopf

Today's deep learning systems deliver high performance based on end-to-end training. While they deliver strong performance, these systems are hard to interpret. To address this issue, we propose Semantic Bottleneck Networks (SBN): deep…

Computer Vision and Pattern Recognition · Computer Science 2019-07-30 Max Losch , Mario Fritz , Bernt Schiele

We present IMTLab, an open-source end-to-end interactive machine translation (IMT) system platform that enables researchers to quickly build IMT systems with state-of-the-art models, perform an end-to-end evaluation, and diagnose the…

Computation and Language · Computer Science 2023-10-18 Xu Huang , Zhirui Zhang , Ruize Gao , Yichao Du , Lemao Liu , Gouping Huang , Shuming Shi , Jiajun Chen , Shujian Huang

Symbol detection is a fundamental and challenging problem in modern communication systems, e.g., multiuser multiple-input multiple-output (MIMO) setting. Iterative Soft Interference Cancellation (SIC) is a state-of-the-art method for this…

Machine Learning · Computer Science 2022-08-18 Hung T. Nguyen , Steven Bottone , Kwang Taik Kim , Mung Chiang , H. Vincent Poor

We show how to "compile" human-readable programs into standard decoder-only transformer models. Our compiler, Tracr, generates models with known structure. This structure can be used to design experiments. For example, we use it to study…

Machine Learning · Computer Science 2023-11-06 David Lindner , János Kramár , Sebastian Farquhar , Matthew Rahtz , Thomas McGrath , Vladimir Mikulik

Deep neural networks have usually to be compressed and accelerated for their usage in low-power, e.g. mobile, devices. Recently, massively-parallel hardware accelerators were developed that offer high throughput and low latency at low power…

Machine Learning · Computer Science 2021-08-04 Thomas Pfeil

Transformers have revolutionized machine learning, yet their inner workings remain opaque to many. We present Transformer Explainer, an interactive visualization tool designed for non-experts to learn about Transformers through the GPT-2…

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

Computer Vision and Pattern Recognition · Computer Science 2020-04-29 Patrick Esser , Robin Rombach , Björn Ommer

The interpretability of machine learning, particularly for deep neural networks, is crucial for decision making in real-world applications. One approach is replacing the un-interpretable machine learning model with a surrogate model, which…

Machine Learning · Statistics 2020-07-22 Keiichi Kisamori , Keisuke Yamazaki , Yuto Komori , Hiroshi Tokieda

There have been several post-hoc explanation approaches developed to explain pre-trained black-box neural networks. However, there is still a gap in research efforts toward designing neural networks that are inherently explainable. In this…

Computer Vision and Pattern Recognition · Computer Science 2022-07-01 Subash Khanal , Benjamin Brodie , Xin Xing , Ai-Ling Lin , Nathan Jacobs

We explore the interplay of quantum computing and machine learning to advance experimental protocols for observing measurement-induced phase transitions (MIPT) in quantum devices. In particular, we focus on trapped ion monitored circuits…

Quantum Physics · Physics 2025-11-07 Yangrui Hu , Yi Hong Teoh , William Witczak-Krempa , Roger G. Melko

A non-parametric interpretable texture synthesis method, called the NITES method, is proposed in this work. Although automatic synthesis of visually pleasant texture can be achieved by deep neural networks nowadays, the associated…

Computer Vision and Pattern Recognition · Computer Science 2020-09-04 Xuejing Lei , Ganning Zhao , C. -C. Jay Kuo

Visual transformers have achieved remarkable performance in image classification tasks, but this performance gain has come at the cost of interpretability. One of the main obstacles to the interpretation of transformers is the…

Computer Vision and Pattern Recognition · Computer Science 2025-04-25 Guillaume Jeanneret , Loïc Simon , Frédéric Jurie