Total 38 · Clear filters
Runway published GWM Worlds 2 on 3 September 2026, a research preview that turns high-fidelity video and audio generation into a real-time interactive world model steered by text actions and camera motion.
On 8 July 2026 Mistral AI introduced Robostral Navigate, an 8-billion-parameter model that steers robots from camera images and spoken-style instructions, trained entirely in simulation and scoring 76.6% on a standard navigation benchmark.
On 9 April 2026 LG AI Research released EXAONE 4.5, its first open-weight multimodal model: a 33B vision-language system aimed at document understanding, with a 256K context window and the earlier EXAONE licence.
On 11 March 2026 Reka released Reka Edge, a 7-billion-parameter vision-language model built for physical AI on devices rather than in the cloud, with a 3.5-bit quantization format and comparisons against Qwen3.5 9B, Cosmos Reason2 8B and Gemini 3 Pro.
On 11 December 2025 Ai2 released Molmo 2, an open-weights family of vision-language models that adds pointing, tracking and grounded question answering in video, in 8B, 4B and 7B versions.
On 19 November 2025 Meta released SAM 3, which detects, segments and tracks objects from text or visual prompts, and SAM 3D, which reconstructs 3D objects and human bodies from a single image. Both were released as open models.
In November 2025 Baidu released ERNIE-4.5-VL-28B-A3B-Thinking, an open-weight vision-language model that reasons with images — zooming into details and calling image search mid-thought — and reports a ChartQA score above Gemini 2.5 Pro and GPT-5.
On 20 October 2025 DeepSeek released DeepSeek-OCR under the MIT License. The model showed that rendering text as images can reduce the number of vision tokens needed for OCR, with decoding precision of about 97 percent at compression under 10x.
ByteDance Seed posted the UI-TARS-2 technical report on 2 September 2025 and released it on GitHub on 4 September. It was trained with multi-turn reinforcement learning.
In September 2025 Alibaba released Qwen3-VL, a vision-language model family under Apache 2.0 whose flagship handles hours-long video, operates PC and mobile interfaces and does 3D grounding.
GLM-4.5V is a vision-language model released by Zhipu on 11 August 2025, built on GLM-4.5-Air and published under the MIT License; Zhipu reported state-of-the-art results among similarly sized models on 42 vision-language benchmarks.
On 31 July 2025 Cohere released Command A Vision, a 112-billion-parameter vision-language model built on Command A. Its open weights were posted under a non-commercial licence.
Kimi-VL is Moonshot AI's open-source vision-language model, released in April 2025. It is a mixture-of-experts model that activates 3B of its 16B parameters, published in Instruct and Thinking versions, with a refreshed Thinking model following in June.
On 6 March 2025 Mistral AI launched Mistral OCR, a document-understanding API that it said processes up to 2,000 pages per minute, handles thousands of scripts and languages, and scored above GPT-4o on its benchmark.
On 4 March 2025 Cohere's research lab released Aya Vision in 8B and 32B open-weight sizes. The models understand images and text across 23 languages and carry a non-commercial licence.
In January 2025 Alibaba released Qwen2.5-VL in four sizes. The model works as a visual agent, follows videos longer than an hour and returns structured coordinates and document data.
On 13 December 2024 DeepSeek released the DeepSeek-VL2 vision-language models, a mixture-of-experts series in three sizes, with dynamic tiling for high-resolution images.
On 18 November 2024 Mistral AI released Pixtral Large, a 124-billion-parameter open-weight multimodal model built on Mistral Large 2, alongside Mistral Large 24.11 and a Le Chat update adding search, Canvas, image generation and agents.
On 25 September 2024 Ai2 released Molmo, a family of open vision-language models ranging from MolmoE-1B to Molmo-72B that can point at things in images; Ai2 said Molmo-72B ranked just behind GPT-4o in human preference.
On 25 September 2024 Meta released Llama 3.2, which added image understanding to the Llama family with 11B and 90B vision models and added small 1B and 3B text models for phones and other edge devices.
On 17 September 2024 Mistral AI released Pixtral 12B, an open-weight model pairing a 400M vision encoder with a 12B decoder and scoring 52.5% on MMMU and 90.7 on DocVQA.
