How can we get large model level multimodal reasoning for documents, charts and videos while running only a 3B class model in production? Baidu has added a new model to the ERNIE-4.5 open source family. ERNIE-4.5-VL-28B-A3B-Thinking is a vision language model that focuses on document, chart and video understanding with a small active parameter budget.…

Zhipu AI has open sourced the GLM-4.6V series as a pair of vision language models that treat images, video and tools as first class inputs for agents, not as afterthoughts bolted on top of text. Model lineup and context length The series has 2 models. GLM-4.6V is a 106B parameter foundation model for cloud and…

In this tutorial, we implement an advanced Optuna workflow that systematically explores pruning, multi-objective optimization, custom callbacks, and rich visualization. Through each snippet, we see how Optuna helps us shape smarter search spaces, speed up experiments, and extract insights that guide model improvement. We work with real datasets, design efficient search strategies, and analyze trial…

Black Forest Labs has released FLUX.2, its second generation image generation and editing system. FLUX.2 targets real world creative workflows such as marketing assets, product photography, design layouts, and complex infographics, with editing support up to 4 megapixels and strong control over layout, logos, and typography. FLUX.2 product family and FLUX.2 [dev] The FLUX.2…

How do you reliably find, segment and track every instance of any concept across large image and video collections using simple prompts? Meta AI Team has just released Meta Segment Anything Model 3, or SAM 3, an open-sourced unified foundation model for promptable segmentation in images and videos that operates directly on visual concepts instead…

Computer-use agents have been limited to primitives. They click, they type, they scroll. Long action chains amplify grounding errors and waste steps. Apple Researchers introduce UltraCUA, a foundation model that builds an hybrid action space that lets an agent interleave low level GUI actions with high level programmatic tool calls. The model chooses the cheaper…

Can we render long texts as images and use a VLM to achieve 3–4× token compression, preserving accuracy while scaling a 128K context toward 1M-token workloads? A team of researchers from Zhipu AI release Glyph, an AI framework for scaling the context length through visual-text compression. It renders long textual sequences into images and processes…

A team of Salesforce AI researchers introduced WALT (Web Agents that Learn Tools), a framework that reverse-engineers latent website functionality into reusable invocable tools. It reframes browser automation around callable tools rather than long chains of clicks. Agents then call operations such as search, filter, sort, post_comment, and create_listing. This reduces dependence on large language…

A team of researchers from Meta Reality Labs and Carnegie Mellon University has introduced MapAnything, an end-to-end transformer architecture that directly regresses factored metric 3D scene geometry from images and optional sensor inputs. Released under Apache 2.0 with full training and benchmarking code, MapAnything advances beyond specialist pipelines by supporting over 12 distinct 3D vision…

IBM has released Granite-Docling-258M, an open-source (Apache-2.0) vision-language model designed specifically for end-to-end document conversion. The model targets layout-faithful extraction—tables, code, equations, lists, captions, and reading order—emitting a structured, machine-readable representation rather than lossy Markdown. It is available on Hugging Face with a live demo and MLX build for Apple Silicon. What’s new compared to…