🧵 Excited to share our latest work: FUTURIST - A unified transformer architecture for multimodal semantic future prediction, is accepted to #CVPR2025 ! Here's how it works (1/n) 👇 Links to the arxiv and github below

New blog post: let's talk about latents! sander.ai/2025/04/15/lat…

EQ-VAE is accepted at #ICML2025 😁. Grateful to my co-authors for their guidance and collaboration! Ioannis Kakogeorgiou, Spyros Gidaris, Nikos Komodakis.

1/n Multi-token prediction boosts LLMs (DeepSeek-V3), tackling key limitations of the next-token setup: • Short-term focus • Struggles with long-range decisions • Weaker supervision Prior methods add complexity (extra layers) 🔑 Our fix? Register tokens—elegant and powerful

As I was saying: it's happening

I am at #CVPR2025 this week in Nashville! Presenting "Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers" on multi-modal semantic future prediction. Come discuss! Fri 13 Jun 10:30-12:30, poster #345 x.com/K_Sta8is/statu…

Can open-data models beat DINOv2? Today we release Franca, a fully open-sourced vision foundation model. Franca with ViT-G backbone matches (and often beats) proprietary models like SigLIPv2, CLIP, DINOv2 on various benchmarks setting a new standard for open-source research🧵