Franck Dernoncourt

Ditch quadratic attention in your ViTs without sacrificing performance: ViT-AdaLA distills knowledge from pre-trained VFMs into linear attention architectures, achieving state-of-the-art results on classification and segmentation.

Multimodal agents can now plan more coherently and solve complex tasks thanks to a new anticipatory reasoning framework that forecasts short-horizon trajectories before acting.

LLMs can't keep up: even state-of-the-art models struggle to adapt to dynamically changing facts in continual knowledge streams, forgetting updates and getting distracted.

Forget direct prompt editing: this agentic planning framework, powered by offline RL and synthetic data, masters complex image styling by breaking it down into interpretable tool sequences.

Finally, AI can generate hour-long videos with consistent characters and backgrounds, thanks to a new framework that nails seamless transitions between shots.