S. Yeung-Levy

Adult-trained human mesh recovery models can now handle kids, too, thanks to a new framework that enforces spatial consistency and leverages VLM-derived age and gender cues.

ELBO-based reinforcement learning, previously dismissed for visual generation, can actually outperform MDP-based methods for aligning denoising generative models with human preferences.

The medical imaging AI community is being held back by a fragmented data landscape, but a new metadata-driven fusion paradigm offers a path to unlocking the power of foundation models.

Unlock superhuman visual reasoning in multimodal models by simply giving them the ability to think step-by-step at test time.