AtMan: Understanding Transformer Predictions Through Memory Efficient
Attention Manipulation

v1v2v3v4v5 (latest)

AtMan: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation

19 January 2023

Bjorn Deiseroth

Samuel Weinbach

Kristian Kersting

ArXiv (abs)PDF HTML

Papers citing "AtMan: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation"

16 / 16 papers shown

Title
JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit Zeqing He Peng Kuang Zhixuan Chu Huiyu Xu Rui Zheng Kui Ren Chun Chen 114 7 0 17 Nov 2024
Token Merging: Your ViT But Faster Daniel Bolya Cheng-Yang Fu Xiaoliang Dai Peizhao Zhang Christoph Feichtenhofer Judy Hoffman MoMe 128 470 0 17 Oct 2022
GIT: A Generative Image-to-text Transformer for Vision and Language Jianfeng Wang Zhengyuan Yang Xiaowei Hu Linjie Li Kevin Qinghong Lin Zhe Gan Zicheng Liu Ce Liu Lijuan Wang VLM 139 560 0 27 May 2022
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation Junnan Li Dongxu Li Caiming Xiong Guosheng Lin MLLM BDL VLM CLIP 555 4,413 0 28 Jan 2022
MAGMA -- Multimodal Augmentation of Generative Models through Adapter-based Finetuning C. Eichenberg Sid Black Samuel Weinbach Letitia Parcalabescu Anette Frank MLLM VLM 63 100 0 09 Dec 2021
Transformer Interpretability Beyond Attention Visualization Hila Chefer Shir Gur Lior Wolf 139 673 0 17 Dec 2020
A Survey on the Explainability of Supervised Machine Learning Nadia Burkart Marco F. Huber FaML XAI 60 778 0 16 Nov 2020
Captum: A unified and generic model interpretability library for PyTorch Narine Kokhlikyan Vivek Miglani Miguel Martin Edward Wang B. Alsallakh ... Alexander Melnikov Natalia Kliushkina Carlos Araya Siqi Yan Orion Reblitz-Richardson FAtt 152 849 0 16 Sep 2020
End-to-End Object Detection with Transformers Nicolas Carion Francisco Massa Gabriel Synnaeve Nicolas Usunier Alexander Kirillov Sergey Zagoruyko ViT 3DV PINN 454 13,130 0 26 May 2020
Quantifying Attention Flow in Transformers Samira Abnar Willem H. Zuidema 169 803 0 02 May 2020
Learning Important Features Through Propagating Activation Differences Avanti Shrikumar Peyton Greenside A. Kundaje FAtt 203 3,884 0 10 Apr 2017
Understanding Black-box Predictions via Influence Functions Pang Wei Koh Percy Liang TDI 219 2,910 0 14 Mar 2017
Axiomatic Attribution for Deep Networks Mukund Sundararajan Ankur Taly Qiqi Yan OOD FAtt 193 6,027 0 04 Mar 2017
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization Ramprasaath R. Selvaraju Michael Cogswell Abhishek Das Ramakrishna Vedantam Devi Parikh Dhruv Batra FAtt 335 20,110 0 07 Oct 2016
SQuAD: 100,000+ Questions for Machine Comprehension of Text Pranav Rajpurkar Jian Zhang Konstantin Lopyrev Percy Liang RALM 316 8,177 0 16 Jun 2016
"Why Should I Trust You?": Explaining the Predictions of Any Classifier Marco Tulio Ribeiro Sameer Singh Carlos Guestrin FAtt FaML 1.2K 17,071 0 16 Feb 2016

We use cookies and other tracking technologies to improve your browsing experience on our website, to show you personalized content and targeted ads, to analyze our website traffic, and to understand where our visitors are coming from. See our policy.