A few “leaks” for you from the #Nvidia presentation I’m right now in Milan. Impressive stuff.

Ps: sorry for the shitty quality of the pics ♥️

Slides about CUDA-Q & Nvidia quantum 👇 (coming in 10 mins)

🤬Music vs. Face Recognition🤬

👉At their recent concerts, Massive Attack turned surveillance into art: crafting a haunting audiovisual show that exposes the dangers of facial recognition tech. Audiences were scanned with mock surveillance, confronting them with the intrusive power of #AI in real time

👉Review https://t.ly/VMrPC
👉News https://t.ly/aj1an

🔥SOTA Detection w/ DINOv3🔥

👉DEIMv2 is the evolution of DEIM framework while leveraging DINOv3. Various models, from an ultra-light version up to S, M, L, & X for a wide range of scenarios. Across these variants, DEIMv2 achieves SOTA. Repo Apache2.0💙

👉Review https://t.ly/P7jEH
👉Paper arxiv.org/pdf/2509.20787
👉Repo github.com/Intellindust-AI-Lab/DEIMv2
👉Project intellindust-ai-lab.github.io/projects/DEIMv2

🤖Real-time Interactive Video🤖

👉LONGLIVE by #Nvidia is a frame-level autoregressive framework for real-time & interactive long video generation. LONGLIVE accepts sequential user prompts and generates corresponding videos in real time. Repo under non-commercial license💙

👉Review https://t.ly/jJkdY
👉Paper arxiv.org/pdf/2509.22622
👉Project nvlabs.github.io/LongLive/
👉Repo github.com/NVlabs/LongLive
🤗huggingface.co/Efficient-Large-Model/LongLive-1.3B