#Open source

Skywork AI releases open-source Matrix-Game 4.0 for real-time gaming on one RTX 5090

Skywork AI released Matrix-Game 4.0, an open-source game world model that reportedly runs at 480p and 60 FPS on one RTX 5090, with input response under 0.15 seconds and peak VRAM usage of approximately 18.5GiB. A game engine maintains state and executes rules, while a video model generates visuals from structural frames and dynamic captions. Model weights and code are available through https://huggingface.co/Skywork/Matrix-Game-4.0 and https://github.com/SkyworkAI/Matrix-Game.

The same story is shown in the picks as 《Kunlun Tech releases and open-sources Matrix-Game 4.0 for single-GPU real-time gameplay》

vLLM Semantic Router team ships Decision 2.0 for single-pass routing and classification

Great work from the vLLM Semantic Router team on Decision 2.0. Multiple questions about one input, answered in a single forward pass with per-option probabilities. Useful for routing and classification. Quoted post by @XunzhuoLiu: In every size. Decision 2.0: six open decision models, 0.6B to 27B. On the #Jev Decision Index 0.3, each one tops the same-size open models we lined it up against. #Trending collections on Hugging Face 🤗 Decision 2.0: https://huggingface.co/collections/vllm-sr/decision-20 Vela 2.0: https://huggingface.co/collections/vllm-sr/vela-20

TII launches Falcon-ASR, a 1.6B-parameter Arabic speech recognition model focused on Emirati dialects

Abu Dhabi's Technology Innovation Institute (TII) released Falcon-ASR, a 1.6B-parameter speech recognition model focused on Arabic and Emirati dialects, with support for English, French, Spanish, and Portuguese as well. Its average WER across six Arabic test sets is 20.92%, 2.25 percentage points below the best public result of 23.17% in the leaderboard snapshot used. In an internal Emirati dialect evaluation, it achieved a 22.73% WER and 10.19% CER, outperforming Qwen3-Omni.

Perplexity releases pplx-embed-v2-late multimodal embedding models

Perplexity is releasing pplx-embed-v2-late, described as two late-interaction embedding models that retrieve text, images, and pages through a shared embedding space for cross-modal querying. The company says both models reach frontier performance and are publicly available on Hugging Face, with a blog post at perplexity.ai/hub/blog/multimodal-embeddings-beyond-a-single-vector.

EmbeddingGemma 2 adopts the Apache 2.0 license

EmbeddingGemma 2 uses the Apache 2.0 license. Simon Willison argues that embedding models should not be locked into proprietary hosted services. They often require computing and storing thousands or millions of vectors; if a provider discontinues a model, users may have to pay to recompute them. He would rather pay for a hosted version while retaining the option to run open weights or switch providers if the service shuts down.

Falcon-Emirati-7B: teaching LLMs the Emirati dialect, culture, and feel for language

Falcon-Emirati-7B is a specialized model for Emirati dialects built on Falcon-H1-Arabic. It aims to understand and generate Emirati Arabic like a native speaker. It uses the Falcon-H1 hybrid architecture, running Mamba alongside Transformer attention. The base model family comes in 3B, 7B, and 34B sizes, with a context window of up to 256K tokens.

NASA and IBM release open-source lunar foundation model based on 17 years of LRO observations

NASA and IBM Research, together with several academic institutions, released the NASA-IBM Lunar Foundation Model, which they describe as one of the first open-source foundation models for lunar science.

Ai2 open-sources AstaBrief 8B, a scientific report-generation model

Ai2 open-sourced AstaBrief 8B, a model that turns research questions and retrieved literature excerpts into reports with citations. It was trained from Qwen3-8B using SFT and DPO and is now available as Asta's Fast mode.

Liquid AI releases LFM2.5-VL-DSpark draft model to accelerate LFM2.5-VL-3B inference

Liquid AI has released the experimental DSpark draft model for its LFM2.5-VL-3B vision-language model. Speculative decoding speeds inference without changing output quality: up to 3.13× on-device and 2.66× on an H100, with end-to-end speedups of up to 2.62× and 2.27×, respectively.

Hugging Face releases NeoMME, 260M and 800M multimodal multilingual encoders

Hugging Face has introduced the NeoMME family of multimodal multilingual encoders in 260M and 800M sizes. A single bidirectional Transformer directly processes text tokens and raw image patches, without a separate vision tower or causal language model.

Microsoft releases GigaPath-Flash and GigaTIME-Flash, efficient pathology foundation models for population-scale discovery

Microsoft has released GigaPath-Flash and GigaTIME-Flash, using a 22M-parameter ViT-S backbone distilled from the billion-parameter GigaPath encoder to sharply reduce the compute requirements of pathology foundation models. Both are open-source under Apache 2.0.

Hugging Face OlmoEarth Studio adds custom embedding export

Hugging Face's OlmoEarth Studio can now compute and export embeddings; its code and model weights are public. Through the UI or API, users can select a region, time range, encoder variant (Nano: 128 dimensions and 1.4M parameters; Tiny: 192 dimensions and 6.2M parameters; Base: 768 dimensions and 89M parameters), resolution, and imagery source, then export an int8 Cloud-Optimized GeoTIFF.