CreativeAtmanityConfirmed
Story 16 of 17 in the Wednesday 4 November editionAtmanity introduces Atmee v2 and Causeur models for single-GPU live video avatars
Taking a single portrait and 15 seconds of reference audio, Causeur drives real-time listening and emotion while Atmee v2 renders full-frame avatars on one GPU.
Edited by Ashutosh Shrivastava
5 Nov 2026, 09:50 IST · 1 min read
AI research lab Atmanity unveiled its two-model live video agent stack on 4 November 2026, pairing the Causeur behaviour model for active listening, timing and personality with the Atmee v2 full-frame video foundation model to render interactive photorealistic or stylised face-and-body avatars in real time on a single GPU from one reference image and 15 seconds of audio; public weights and API pricing were not announced.
Sources
- PrimaryAtmanity official portal and model overviewatmanity.io
The rest of the day
Read the whole day
01CreativeOpenAI
OpenAI rolls out ChatGPT Images 2.6 with animated GIFs and two new API image models
Images 2.6 generates visuals 50% faster across ChatGPT and Codex while adding GPT-Image-2.6 Flare and Sunburst to the API with SVG export and markup-guided edits.
02ModelTencent
Tencent launches multimodal Hy4 model with native computer use and 3D engine training
Hy4 adds visual reasoning alongside CLI and GUI control, trained directly inside Blender, CAD, Unreal Engine, Unity and Godot environments.
03Open sourceMoonshot AI
Moonshot AI releases open-weight Kimi K3.1 Pro with 2.8T parameters and 1M context
Activating 104B parameters per token with native MXFP4 weights, the multimodal MoE model leads Opus 5.5 and GPT-6 Astra on SWE Marathon v1.1.
04ResearchOpenAI
OpenAI’s autonomous cyber pipeline uncovers and patches 948 Linux kernel root flaws
Powered by an upcoming cyber model, a five-stage VM validation and exploit pipeline generated working privilege-escalation exploits at $1,279 per distinct vulnerability.
Spotted an error? Email aiforsuccess.in+compass@gmail.com or tag @ai_for_success on X