arXiv Machine Learning August 4, 2026 By Guiqiu Liao, Matjaz Jogan, Daniel A. Hashimoto

Slot2Text: Object-Centric Visual Tokenization for Efficient and Spatially Traceable Surgical MLLMs

Read the original on arXiv Machine Learning →

arXiv:2608. 01473v1 Announce Type: cross Abstract: Multimodal large language models (MLLM) for surgical scene understanding typically inject hundreds of dense visual tokens into a language model, leading to costly inference and limited spatial traceability for generated answers.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

Hugging Face Trending Papers

Jun 24

SurgAtlas: A Large-Scale Surgical Video-Language Dataset with 2,391 Hours of Open and Minimally Invasive Surgery

We introduce SurgAtlas, the largest surgical video-language dataset to date, comprising 15,291 videos (2,391 hours) spanning 18 surgical specialties and over 5,000 procedure types, sourced entirely from publicly available YouTube content. SurgAtlas is also the first surgical video-language dataset to include open surgery at scale, with 6,182 open procedure videos alongside over 9,000 minimally invasive recordings, and the first to establish standardized benchmarks for open-surgery video understanding.

llms nlp multimodal benchmarks

arXiv AI

Aug 11

MedPixel: A Unified Pixel-Language Model for Medical Reasoning and Segmentation

arXiv:2608. 09818v1 Announce Type: cross Abstract: Reliable medical image understanding requires models to connect clinical language and visual reasoning with pixel-level grounding.

By Haoyu Yang, Meixing Shi, Zengjie Chen, Haoran Sun, Haitao Leng, Xiaoming Shi, Yuxiang Cai, Yankai Jiang

llms computer-vision fine-tuning multimodal benchmarks

arXiv AI

Aug 12

MedUP: Awakening Unified Understanding and Perception in Medical Vision-Language Models

arXiv:2608. 10635v1 Announce Type: cross Abstract: Medical Vision-Language Models (Med-VLMs) excel at verbalizing visual content, yet precise visual perception, segmentation, and grounding remain challenging.

By Yuan Wang, Hualiang Wang, Yixin Chen, Songtao Jiang, Shujian Gao, Jiaming Lin, Siming Fu, Jian Wu, Zuozhu Liu

llms agents computer-vision nlp multimodal safety

arXiv Machine Learning

Jul 1

Medical Image Spatial Grounding with Semantic Sampling

arXiv:2603. 14579v3 Announce Type: replace-cross Abstract: Vision language models (VLMs) have shown significant promise in visual grounding for images as well as videos.

By Andrew Seohwan Yu, Mohsen Hariri, Kunio Nakamura, Mingrui Yang, Xiaojuan Li, Vipin Chaudhary

llms computer-vision multimodal benchmarks

arXiv AI

Jul 7

IRIS: An Intelligent Vision-Language System for Ocular Surface Diseases via Topic Tree and Scene-Driven VQA Generation

arXiv:2607. 04344v1 Announce Type: cross Abstract: While Large Vision-Language Models (VLMs) demonstrate remarkable generic capabilities, their clinical reasoning in specialized domains like ocular surface diseases (OSDs) is severely hindered by a paucity of high-fidelity, multimodal instruction-tuning data.

By Hao Wei, Wenjin Qi, Dasen Dai, Minqing Zhang, Wu Yuan

llms multimodal benchmarks

arXiv AI

Aug 6

Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens

arXiv:2511. 19418v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) excel at reasoning in linguistic space but struggle with perceptual understanding that requires dense visual perception, e.

By Yiming Qin, Bomin Wei, Jiaxin Ge, Konstantinos Kallidromitis, Stephanie Fu, Trevor Darrell, XuDong Wang

llms computer-vision multimodal benchmarks safety

Related stories

SurgAtlas: A Large-Scale Surgical Video-Language Dataset with 2,391 Hours of Open and Minimally Invasive Surgery

MedPixel: A Unified Pixel-Language Model for Medical Reasoning and Segmentation

MedUP: Awakening Unified Understanding and Perception in Medical Vision-Language Models

Medical Image Spatial Grounding with Semantic Sampling

IRIS: An Intelligent Vision-Language System for Ocular Surface Diseases via Topic Tree and Scene-Driven VQA Generation

Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens