Search “Video”

English translation is being prepared.

English translation is being prepared.

Viggle AI Releases JST-2 Physics-Native World Foundation Model

Viggle AI has released JST-2, calling it the world's first full-stack physics-native world foundation model. Rather than learning in pixel or video space, the model builds its entire model stack in 3D space from first principles, can generate 3D scenes in seconds and extend them in real time, and can also create characters with their own motions through the same general architecture.

English translation is being prepared.

English translation is being prepared.

Elorian Releases Its First Model Glimpse, Using a Visual Draft Space for Image Reasoning

Elorian has released its first model, Glimpse, opening the API as a research preview, with a waitlist for the chat interface. During reasoning, the model can crop image regions, extract video frames, or run code to measure and compare what it sees, which Elorian calls a visual draft space. Glimpse is priced at $0.60 per million input tokens and $3 per million output tokens, and according to Elorian's evaluations it surpasses GPT-6 Astra on scientific chart reasoning and short video description. The company says the model was trained on several hundred GPUs, a scale notably smaller than the frontier systems it benchmarks against, and it initially targets enterprises with large amounts of video, such as robotics, research laboratories, and media and creative firms.

Meta Releases 816B Open-Source Model Muse Spark Open, Partnering with Apple for Local Execution

Meta has released the open-weight model Muse Spark Open, which uses a MoE architecture with 256 experts, activates about 42B parameters per token, has a context window of 1 million tokens, and supports text, image, video, and audio input but outputs text only. Meta has partnered with Apple to run the approximately 530 GByte four-bit quantized version on two interconnected Mac Studio M5 Ultra machines, distributing computation via the MLX framework and Thunderbolt 5, achieving about 25 output tokens/second at an 8192-token context. Artificial Analysis tests show that it scores 39 on the Intelligence Index, making it the strongest American open-weight model currently available, but it trails MiMo-V2.6-Pro's 46 points and GLM-5.3's 45 points, and ranks last in four Agent tests. The model weights are available on Hugging Face in two versions: 16-bit at approximately 1.6 TByte and four-bit at approximately 530 GByte, with API pricing at $1.25 per million input tokens and $4.25 per million output tokens.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

Meta releases open-source model Muse Spark Open, supporting 1M context and multimodal input

Meta releases open-source model Muse Spark Open, with weights released the same day. Muse-Spark-Open-816B-A42B supports text, image, video and audio input, with a context window of 1M. Unsloth provides a Dynamic 2-bit GGUF quantized version that can run on Mac Studio, along with a GGUF download address and usage guide.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

NVIDIA Nemotron 3.5 Super VL Launches on OpenRouter

NVIDIA Nemotron 3.5 Super VL is now available on OpenRouter. It is an open-source 120B-A12B multimodal model designed for long-running agents that need to observe, reason, and act across text, images, documents, GUIs, and video, with support for a 1M context. The model uses a Hybrid Mamba-Transformer MoE architecture and supports multi-token prediction to speed up output, targeting scenarios such as document intelligence, web research, customer service, and video understanding.

English translation is being prepared.

English translation is being prepared.