CORTEXA
← Browse
arxivcs.CVcs.AIcs.LG2026-07-03

RADIO1D: Elastic Representations for Condensed Vision Modeling

Greg Heinrich, Mike Ranzinger, Collin McCarthy, Natan Bagrov, Eugene Khvedchenya, Bryan Catanzaro, Jan Kautz, Andrew Tao, Pavlo Molchanov

This paper challenges the assumption that vision-language models (VLMs) require fixed patch-based 2D vision features. Analyzing fine-tuned vision encoders, we find that representations become increasingly abstract and less spatially coherent during VLM training. Notably, models trained with image-text alignment (such as SigLIP2) develop a small number of specialized tokens that effectively summarize global image content. Building on this, we introduce RADIO1D, which compresses images into a compact, variable-length 1D token sequence using multi-teacher knowledge distillation and an autoencoder design. The resulting representations exhibit strong hierarchical summarization, enabling accurate scene understanding - even with a single token - and support improved composition-aware image retrieval. In VLMs, RADIO1D provides flexible accuracy-efficiency tradeoffs through adjustable token counts, delivering competitive performance on diverse multimodal benchmarks with lower computational overhead and better accuracy.

View free PDFSource page

Related papers

arxivcs.CVcs.AIcs.LG2026-07-08

LoCA: Spatially-Aware Low-Rank Convolutional Adaptation of Vision Foundation Models

Sojung An, Junha Lee, Sujeong You, Nam Ik Cho, Donghyun Kim

Pre-trained Vision Foundation Models (VFMs) provide strong visual representations for diverse downstream tasks. The key challenge of VFM adaptation stems from the prohibitive costs of full fine-tuning and catastrophic forgetting. To address this, Low-Rank Adaptation (LoRA) has em…

View free PDFSource page
arxivcs.CVcs.AIcs.CLcs.LGcs.MM2026-07-01

ESC: Emotional Self-Correction for Reliable Vision-Language Models

Tien-Huy Nguyen, Minh-Nhat Nguyen, Nguyen Nhat Huy, Hung Viet Nguyen, Huy Nguyen Minh Nhat, Thanh-Huy Nguyen, et al.

Vision-language models (VLMs) have achieved strong performance across diverse multimodal tasks, yet they remain vulnerable to unreliable reasoning. Existing self-correction methods mitigate these issues but typically rely on post-training or carefully engineered feedback, incurri…

View free PDFSource page
arxivcs.CVcs.AIcs.LGeess.IV2026-07-17

Ask Twice, Look Twice: Prompt Echoing Resolves the Question-First Paradox in Vision-Language Models

Rakshanda Hassan Abhinandan, John Galeotti, Deva Ramanan, Gautam Rajendrakumar Gare

Where should the question go in a vision-language model (VLM) prompt: before the image or after it? Intuition says before: knowing what is asked should tell the model where to look. Yet across visual question answering benchmarks, question-first prompting consistently underperfor…

View free PDFSource page
arxivcs.CVcs.AIcs.LGcs.MM2026-06-28

ScAle: Attention Head Scaling as a Minimal Adapter for Spatial Reasoning in Vision Language Models

Rahul Chowdhury, Timothy A Rupprecht, Xuan Shen, Pu Zhao, Yanzhi Wang

Spatial reasoning remains a persistent challenge for many vision language models (VLMs), and improving it typically requires fine-tuning with substantial additional parameters. Our preliminary analysis reveals that rescaling activations in selected transformer layers-without modi…

View free PDFSource page
arxivcs.CVcs.AIcs.LG2026-07-08

Vision Foundation Models in Radiology: A Scoping Review of Data, Methodology, Evaluation and Clinical Translation

Alejandro Vergara-Richart, Xavier Rafael-Palou, Almudena Fuster-Matanzo, Ignacio Iborra Roncales, Ángel Alberich-Bayarri, Ana Jiménez-Pastor

Vision foundation models (VFMs) are increasingly being developed for radiological imaging, yet their definition, development and evaluation remain heterogeneous. We conducted a PRISMAScR scoping review of peer-reviewed studies published between January 2017 and March 2026 describ…

View free PDFSource page
arxivcs.CVcs.AIcs.LG2026-07-06

Multiplayer Interactive World Models with Representation Autoencoders

Anthony Hu, Václav Volhejn, Adrien Ramanana Rahary, Chris Mulder, Aditya Makkar, Alyx Liao, et al.

We introduce the first multiplayer world model for highly dynamic environments governed by complex physical interactions. Whereas single-player world models treat the other agents as part of the environment, ours conditions on the action streams of multiple agents, learning to at…

View free PDFSource page