AI Briefing#vlm
The latest AI and developer news about #vlm, with the original source and a short summary.
The latest AI and developer news about #vlm, with the original source and a short summary.
ASCIITermDraw-Bench, which evaluates VLMs' ability to generate and edit text-based diagrams, has been released.
LG AI Research has proposed the EXAONE LMM architecture, which resolves data licensing issues in existing LMMs while improving efficiency.
LG AI Research has released EXAONE 4.5, a multimodal model that understands text and images simultaneously, as an open-weight model.
LG AI Research has unveiled EXAONE 4.5, an open-weight VLM that processes visual information and language simultaneously.
LensVLM is a framework designed to address recognition errors caused by resolution degradation when VLMs process images containing text.
RL-finetuned VLMs show improved visual reasoning performance, but exhibit vulnerability to textual perturbations.
Moondream explains how its Photon engine reduces GPU idle time and optimizes inference performance through pipelined decoding technology.
A 4B-scale Granite Vision 4.1 model specialized for document structure extraction has been added to llama.cpp.
KOLongDoc, a VLM benchmark for evaluating comprehension of long Korean public institution documents, has been released.
Stable-Layers fine-tunes an image layer decomposition model without paired data through reinforcement learning that leverages feedback from a VLM.
NVIDIA has unveiled LocateAnything, which applies Parallel Box Decoding (PBD) technology to revolutionize the grounding speed and accuracy of VLMs.
MUSINSA used **Geometric Prior** instead of a VLM to boost clothing detail shot generation speed by **25x**.
NuExtract3, a VLM based on Qwen3.5-4B specialized for document data extraction and Markdown conversion, has been released.
Numind has released NuExtract3, a VLM specialized in document structuring and OCR based on Qwen3.5-4B.
Numind has released NuExtract3, a 4B-scale open-weight VLM specialized for Markdown conversion and structured data extraction from documents.
**VSAS-Bench**, a new framework for evaluating the performance of real-time visual streaming assistant models, has been released.
An open-source tool called 'Bracket' has been released that uses VLM and statistical validation to find optimal fine-tuning settings for Diffusion models.
TurboOCR claims up to 1,200 img/s OCR using C++/CUDA and FP16 TensorRT.
A Windows OCR translator built with Rust/Slint, supporting Gemini and local models.
The Vision2Web benchmark has been released to evaluate the web development capabilities of multimodal coding agents in stages.
By having the VLM branch arm and gripper actions, it improves manipulation performance even in dynamic environments.
Word Shape Encoding significantly boosts Hebrew and Arabic PDF parsing quality.
NVIDIA has released Cosmos Reason 2, an open VLM with enhanced reasoning capabilities for physical AI.
A guide summarizing recent open-source OCR technology trends leveraging Vision Language Models (VLMs), along with model selection and usage methods.