English
Related papers

Related papers: Progressive Inference: Explaining Decoder-Only Seq…

200 papers

Computer vision can be understood as the ability to perform inference on image data. Breakthroughs in computer vision technology are often marked by advances in inference techniques. This thesis proposes novel inference schemes and…

Computer Vision and Pattern Recognition · Computer Science 2017-09-04 Varun Jampani

Standard Transformers have a fixed computational depth, fundamentally limiting their ability to generalize to tasks requiring variable-depth reasoning, such as multi-hop graph traversal or nested logic. We propose a depth-recurrent…

Machine Learning · Computer Science 2026-03-24 Hung-Hsuan Chen

Catching and attributing code change-induced performance regressions in production is hard; predicting them beforehand, even harder. A primer on automatically learning to predict performance regressions in software, this article gives an…

Software Engineering · Computer Science 2023-05-23 Moritz Beller , Hongyu Li , Vivek Nair , Vijayaraghavan Murali , Imad Ahmad , Jürgen Cito , Drew Carlson , Ari Aye , Wes Dyer

Recommendation model interpretation aims to reveal the relationships between inputs, model internal representations and outputs to enhance the transparency, interpretability, and trustworthiness of recommendation systems. However, the…

Information Retrieval · Computer Science 2026-01-27 Jiayin Wang , Xiaoyu Zhang , Weizhi Ma , Zhiqiang Guo , Min Zhang

Previous multi-task dense prediction studies developed complex pipelines such as multi-modal distillations in multiple stages or searching for task relational contexts for each task. The core insight beyond these methods is to maximize the…

Computer Vision and Pattern Recognition · Computer Science 2023-04-10 Yangyang Xu , Xiangtai Li , Haobo Yuan , Yibo Yang , Lefei Zhang

Approximating complex probability densities is a core problem in modern statistics. In this paper, we introduce the concept of Variational Inference (VI), a popular method in machine learning that uses optimization techniques to estimate…

Machine Learning · Computer Science 2021-11-23 Ankush Ganguly , Samuel W. F. Earp

To tackle interpretability in deep learning, we present a novel framework to jointly learn a predictive model and its associated interpretation model. The interpreter provides both local and global interpretability about the predictive…

Machine Learning · Computer Science 2022-02-24 Jayneel Parekh , Pavlo Mozharovskyi , Florence d'Alché-Buc

We propose selective debiasing -- an inference-time safety mechanism designed to enhance the overall model quality in terms of prediction performance and fairness, especially in scenarios where retraining the model is impractical. The…

Computation and Language · Computer Science 2025-03-12 Gleb Kuzmin , Neemesh Yadav , Ivan Smirnov , Timothy Baldwin , Artem Shelmanov

Convolutional neural networks typically encode an input image into a series of intermediate features with decreasing resolutions. While this structure is suited to classification tasks, it does not perform well for tasks requiring…

Computer Vision and Pattern Recognition · Computer Science 2020-06-18 Xianzhi Du , Tsung-Yi Lin , Pengchong Jin , Golnaz Ghiasi , Mingxing Tan , Yin Cui , Quoc V. Le , Xiaodan Song

Despite strong empirical performance for image classification, deep neural networks are often regarded as ``black boxes'' and they are difficult to interpret. On the other hand, sparse convolutional models, which assume that a signal can be…

Computer Vision and Pattern Recognition · Computer Science 2022-10-25 Xili Dai , Mingyang Li , Pengyuan Zhai , Shengbang Tong , Xingjian Gao , Shao-Lun Huang , Zhihui Zhu , Chong You , Yi Ma

Interpreting the internal activations of neural networks can produce more faithful explanations of their behavior, but is difficult due to the complex structure of activation space. Existing approaches to scalable interpretability use…

Artificial Intelligence · Computer Science 2025-12-18 Vincent Huang , Dami Choi , Daniel D. Johnson , Sarah Schwettmann , Jacob Steinhardt

Generative Large Language Models (LLMs) based on the Transformer architecture have recently emerged as a dominant foundation model for a wide range of Natural Language Processing tasks. Nevertheless, their application in real-time scenarios…

Computation and Language · Computer Science 2024-01-04 Coleman Hooper , Sehoon Kim , Hiva Mohammadzadeh , Hasan Genc , Kurt Keutzer , Amir Gholami , Sophia Shao

Attention-based models, such as Transformer, excel across various tasks but lack a comprehensive theoretical understanding, especially regarding token-wise sparsity and internal linear representations. To address this gap, we introduce the…

Machine Learning · Statistics 2025-02-27 Pierre Marion , Raphaël Berthier , Gérard Biau , Claire Boyer

Transformer-based CLIP models are widely used for text-image probing and feature extraction, making it relevant to understand the internal mechanisms behind their predictions. While recent works show that Sparse Autoencoders (SAEs) yield…

Machine Learning · Computer Science 2025-05-27 Maximilian Dreyer , Lorenz Hufe , Jim Berend , Thomas Wiegand , Sebastian Lapuschkin , Wojciech Samek

Identifying the parameters of a non-linear model that best explain observed data is a core task across scientific fields. When such models rely on complex simulators, evaluating the likelihood is typically intractable, making traditional…

This paper investigates a phenomenon where query-based object detectors mispredict at the last decoding stage while predicting correctly at an intermediate stage. We review the training process and attribute the overlooked phenomenon to two…

Computer Vision and Pattern Recognition · Computer Science 2023-03-23 Fangyi Chen , Han Zhang , Kai Hu , Yu-kai Huang , Chenchen Zhu , Marios Savvides

We propose a novel approach to perform approximate Bayesian inference in complex models such as Bayesian neural networks. The approach is more scalable to large data than Markov Chain Monte Carlo, it embraces more expressive models than…

Machine Learning · Statistics 2022-09-07 Joel Janek Dabrowski , Daniel Edward Pagendam

Segments that span contiguous parts of inputs, such as phonemes in speech, named entities in sentences, actions in videos, occur frequently in sequence prediction problems. Segmental models, a class of models that explicitly hypothesizes…

Computation and Language · Computer Science 2018-06-14 Hao Tang

Predictive coding is an influential model of cortical neural activity. It proposes that perceptual beliefs are furnished by sequentially minimising "prediction errors" - the differences between predicted and observed data. Implicit in this…

Neurons and Cognition · Quantitative Biology 2022-04-07 Alexander Tschantz , Beren Millidge , Anil K Seth , Christopher L Buckley

We present a new approach to automatic amortized inference in universal probabilistic programs which improves performance compared to current methods. Our approach is a variation of inference compilation (IC) which leverages deep neural…

Machine Learning · Computer Science 2019-10-29 William Harvey , Andreas Munk , Atılım Güneş Baydin , Alexander Bergholm , Frank Wood