Tag
Jina-ocr-v1 is a multimodal vision language model designed for advanced document intelligence, reading text from images in multiple languages.
The paper presents PANORAMA, a vision-language model for panoptic grounded captioning that uses mask proposal selection to ground captions with pixel-level masks, and introduces the PanoCaps benchmark for evaluation.
ModaLens is a paired image-swap audit that measures how report availability reduces image sensitivity in medical vision-language models, demonstrated using MedGemma-27B on the MIMIC-CXR dataset.
This academic paper proposes an AI-based system that uses thermal video footage to estimate combustion efficiency in flare stacks, integrated into a graphical user interface with high uptime and low maintenance.
A 2B vision-language model distilled from a tool-using agent achieves first-place performance on long egocentric video question answering by pruning its multilingual embedding table to meet parameter limits, reaching 89% accuracy of the larger pipeline with only 1.1% of parameters.
Alibaba Qwen has released an open-source 4B parameter vision-language model for autonomous driving on Hugging Face, featuring 3D detection, occupancy prediction, and BEV capabilities while preserving strong VL abilities.
Show-Harness is a method that enables vision-language models to control robots through discrete semantic actions, allowing zero-shot deployment and efficient fine-tuning across different robots and GUIs.
DeepSeek-V4-Flash-Vision-Exp is a vision-language model that processes images and generates text, with over 313k downloads, useful for tasks like image description and visual question answering.
TANGO is a vision-language-action framework for humanoid robots to navigate cluttered environments using simulated training data, demonstrating state-of-the-art performance and zero-shot real-world deployment.
CARDEA is an AI model designed to provide auditable reasoning for coronary angiography interpretation using Chain-of-Box to indicate image regions, enhancing trust in clinical practice.
A shared app for exploring and understanding vision language model evaluations, referencing a thread analyzing popular vision benchmarks.
Jina-OCR-v1 is an efficient end-to-end document parsing model that uses speculative decoding and dense verifiable rewards to achieve high accuracy and speed on low-budget GPUs, scoring 91.14 on OmniDocBench v1.6 and 83.4 on olmOCR-Bench.
A coding agent guided by vision-language models generates editable layered designs by synthesizing visual assets and refining HTML/CSS layouts, enabling post-editing with precise control.
WorldReward introduces a vision-language reward model for camera-conditioned world models that unifies action-consistency and visual-quality evaluation through chunk decomposition and preference aggregation, outperforming existing methods like GPT-5.5 on benchmarks.
An announcement that open-source resources, including code, RL environment, and dataset, will be released for using reinforcement learning on a 4B parameter vision-language model to excel at GeoGuesser, enabling full reproduction.
SCAFFOLD is a large-scale dataset of computer science research figures paired with captions, context, QA, and Chain-of-Thought traces, aimed at improving vision-language model understanding of diagrams in CS papers.
This research paper introduces a parametric multimodal user memory system that improves AI agents' ability to recall users by integrating perceptual data like voice and appearance, using vision-language models and dedicated encoders to surpass text-based methods.
SimLoss uses embedding-space contrastive supervision to enable single-pass fine-grained image captioning that matches multi-stage quality at much lower latency, with variants like SimLoss FFT achieving high precision.
FoldingAgent is an agentic framework that uses vision-language models and specialized tools to infer parametric origami folding programs from demonstration videos via sequential reasoning and physical verification.
Cohere introduces Parse, a cost-effective vision language model for processing large volumes of enterprise documents into structured data, offering high performance and scalability for use cases like RAG and document indexing.