Image created with gemini-3.1-flash-image-preview with claude-sonnet-4-5. Image prompt: Vintage 1990s screen-printed t-shirt graphic on worn mustard-yellow cotton fabric, single deep red ink print showing a smiling cartoon video store clerk behind counter with shelves of VHS tapes, hand-drawn BE KIND REWIND sign, bold text VIDEO in large retro letters across top, simple cartoon outlines, slightly imperfect printed registration, aged fabric texture with minor stains, humorous nostalgic charm
98ms time to first token (faster than human visual reaction time), built for agentic workflows. 65% faster throughput compared to leading 8B models. Reka Edge is a 7B VLM built for latency-sensitive apps: real-time video analysis, agentic workflows, on-device deployment
https://x.com/RekaAILabs/status/2032132996422082619
Track4World: Feedforward World‑centric Dense 3D Tracking of All Pixels”” TL;DR: feed‑forward model that predicts pixel‑level 2D and 3D dense flows for holistic world‑centric 3D tracking from monocular video, outperforming prior flow and tracking baselines.
https://x.com/Almorgand/status/2031060671064891647
Your videos can go further now. We’re introducing new Video API capabilities, powered by Sora 2: • Custom characters and objects • 16:9 and 9:16 exports • Clips up to 20 seconds • Video continuation to extend scenes • Batch jobs for video generation
https://x.com/OpenAIDevs/status/2032142448970121468
Mode Seeking meets Mean Seeking for Fast Long Video Generation https://primecai.github.io/mmm/
Mode Seeking meets Mean Seeking for Fast Long Video Generation”” TL;DR: combines global flow-matching (mean-seeking) and local distribution-matching (mode-seeking) objectives to generate minute-long coherent videos with fast inference and strong local realism.
https://x.com/Almorgand/status/2029982050653012208
if you know 3d tools, you’re gonna love this video 10/10 no notes – blender is now the king; houdini is the only challenger
https://x.com/bilawalsidhu/status/2029385972467601862
ID-LoRA: Identity-Driven Audio-Video Personalization https://id-lora.github.io/
Meet Reka Edge – Our next-generation vision language model for physical AI. Uses 3x fewer input tokens and achieves 65% faster throughput compared to leading 8B models. Image understanding, video analysis, object detection, and tool use. Built for Action. Fast enough for
https://x.com/RekaAILabs/status/2031781818349834628
Leave a Reply