English
Related papers

Related papers: Engineering Verifiable Modularity in Transformers …

200 papers

Vision-Language-Action (VLA) models have demonstrated strong potential for predicting semantic actions in navigation tasks, demonstrating the ability to reason over complex linguistic instructions and visual contexts. However, they are…

Attention layers are widely used in natural language processing (NLP) and are beginning to influence computer vision architectures. Training very large transformer models allowed significant improvement in both fields, but once trained,…

Machine Learning · Computer Science 2021-05-21 Jean-Baptiste Cordonnier , Andreas Loukas , Martin Jaggi

We conduct a systematic study of the approximation properties of Transformer for sequence modeling with long, sparse and complicated memory. We investigate the mechanisms through which different components of Transformer, such as the…

Machine Learning · Computer Science 2024-10-31 Mingze Wang , Weinan E

Existing hallucination detection methods for large language models (LLMs) rely on external verification at inference time, requiring gold answers, retrieval systems, or auxiliary judge models. We ask whether this external supervision can…

Artificial Intelligence · Computer Science 2026-04-09 Shoaib Sadiq Salehmohamed , Jinal Prashant Thakkar , Hansika Aredla , Shaik Mohammed Omar , Shalmali Ayachit

Large vision-language models (LVLMs) have made substantial progress in integrating large language models (LLMs) with visual inputs, enabling advanced multimodal reasoning. Despite their success, a persistent challenge is hallucination-where…

Computation and Language · Computer Science 2025-06-11 Jinghan He , Kuan Zhu , Haiyun Guo , Junfeng Fang , Zhenglin Hua , Yuheng Jia , Ming Tang , Tat-Seng Chua , Jinqiao Wang

Mechanistic interpretability seeks to reverse engineer a trained neural network by identifying the minimal subset of internal components. We perform a mechanistic interpretability analysis of the Particle Transformer architecture, trained…

High Energy Physics - Phenomenology · Physics 2026-05-12 Saurabh Rai , Sanmay Ganguly

While the Transformer architecture dominates many fields, its quadratic self-attention complexity hinders its use in large-scale applications. Linear attention offers an efficient alternative, but its direct application often degrades…

Computer Vision and Pattern Recognition · Computer Science 2026-01-15 Kewei Zhang , Ye Huang , Yufan Deng , Jincheng Yu , Junsong Chen , Huan Ling , Enze Xie , Daquan Zhou

Image inpainting is an ill-posed problem to recover missing or damaged image content based on incomplete images with masks. Previous works usually predict the auxiliary structures (e.g., edges, segmentation and contours) to help fill…

Computer Vision and Pattern Recognition · Computer Science 2022-08-26 Yongsheng Yu , Dawei Du , Libo Zhang , Tiejian Luo

Attention mechanisms are ubiquitous components in neural architectures applied to natural language processing. In addition to yielding gains in predictive accuracy, attention weights are often claimed to confer interpretability, purportedly…

Computation and Language · Computer Science 2020-04-08 Danish Pruthi , Mansi Gupta , Bhuwan Dhingra , Graham Neubig , Zachary C. Lipton

Transformers are widely used in natural language processing, where they consistently achieve state-of-the-art performance. This is mainly due to their attention-based architecture, which allows them to model rich linguistic relations…

Computation and Language · Computer Science 2022-11-29 Nikolaos Mylonas , Ioannis Mollas , Grigorios Tsoumakas

The Vision Transformer (ViT) has made significant advancements in computer vision, utilizing self-attention mechanisms to achieve state-of-the-art performance across various tasks, including image classification, object detection, and…

Computer Vision and Pattern Recognition · Computer Science 2025-04-29 Sehyeong Jo , Gangjae Jang , Haesol Park

The quadratic computational cost of the self-attention mechanism is a primary challenge in scaling Transformer models. While attention sparsity is widely studied as a technique to improve computational efficiency, it is almost universally…

Computation and Language · Computer Science 2025-08-11 Sagar Gandhi , Vishal Gandhi

Transformer-based models have become state-of-the-art tools in various machine learning tasks, including time series classification, yet their complexity makes understanding their internal decision-making challenging. Existing…

Machine Learning · Computer Science 2025-11-27 Matīss Kalnāre , Sofoklis Kitharidis , Thomas Bäck , Niki van Stein

Transformers allow attention between all pairs of tokens, but there is reason to believe that most of these connections - and their quadratic time and memory - may not be necessary. But which ones? We evaluate the impact of sparsification…

Computation and Language · Computer Science 2022-10-11 Siddhartha Brahma , Polina Zablotskaia , David Mimno

Although attention mechanisms have become fundamental components of deep learning models, they are vulnerable to perturbations, which may degrade the prediction performance and model interpretability. Adversarial training (AT) for attention…

Computation and Language · Computer Science 2022-12-27 Shunsuke Kitada , Hitoshi Iyatomi

As machine learning models are increasingly deployed in safety-critical domains, visual explanation techniques have become essential tools for supporting transparency. In this work, we reveal a new class of attacks that compromise model…

Computer Vision and Pattern Recognition · Computer Science 2025-11-19 Farhin Farhad Riya , Shahinul Hoque , Jinyuan Stella Sun , Olivera Kotevska

Mechanistic interpretability improves the safety, reliability, and robustness of large AI models. This study examined individual attention heads in vision transformers (ViTs) fine tuned on distorted 2D spectrogram images containing non…

Machine Learning · Computer Science 2025-03-25 Nooshin Bahador

Modular exponentiation is crucial to number theory and cryptography, yet remains largely unexplored from a mechanistic interpretability standpoint. We train a 4-layer encoder-decoder Transformer model to perform this operation and…

Machine Learning · Computer Science 2025-10-24 David Demitri Africa , Sara M. Kapoor , Theo Simon Sorg , Challenger Mishra

Transformer-based models have been widely adopted for sentiment analysis tasks due to their exceptional ability to capture contextual information. However, these methods often exhibit suboptimal accuracy in certain scenarios. By analyzing…

Artificial Intelligence · Computer Science 2025-12-25 Yawei Liu

Multimodal large language models (MLLMs) have achieved remarkable progress in video understanding.However, hallucination, where the model generates plausible yet incorrect outputs, persists as a significant and under-addressed challenge in…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Jianfeng Cai , Wengang Zhou , Zongmeng Zhang , Jiale Hong , Nianji Zhan , Houqiang Li