[2209.15162] Linearly Mapping from Image to Text Space

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status Get status notifications via email or slack

[2209.15162] Linearly Mapping from Image to Text Space Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Computation and Language arXiv:2209.15162 (cs) [Submitted on 30 Sep 2022 ( v1 ), last revised 9 Mar 2023 (this version, v3)] Title: Linearly Mapping from Image to Text Space Authors: Jack Merullo , Louis Castricato , Carsten Eickhoff , Ellie Pavlick View a PDF of the paper titled Linearly Mapping from Image to Text Space, by Jack Merullo and 3 other authors View PDF Abstract: The

related reading

• [2512.19428] Attention Is Not What You Needarxiv.org
• [1409.3215] Sequence to Sequence Learning with Neural Networksarxiv.org
• The Geometry of Categorical and Hierarchical Concepts in Large Language Modelsarxiv.org
• [2406.11717] Refusal in Language Models Is Mediated by a Single Directionarxiv.org
• [2312.15159] Understanding the Potential of FPGA-Based Spatial Acceleration for Large Language Model Inferencearxiv.org
• [2309.01809] Are Emergent Abilities in Large Language Models just In-Context Learning?arxiv.org
• [2406.02061] Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Modelsarxiv.org
• Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Textarxiv.org
• [2312.03079] LooseControl: Lifting ControlNet for Generalized Depth Conditioningarxiv.org
• [2301.13823] Grounding Language Models to Images for Multimodal Generationarxiv.org
• Hyper-Connectionsarxiv.org
• [2305.18654] Faith and Fate: Limits of Transformers on Compositionalityarxiv.org