Loading activity…
@hanlin_hl
PhD @UNC | MS @Columbia | Research Intern @AIatMeta| Working on generative models, multimodal learning, and LLMs
AI
WEDGE's creators say it identifies where each agent struggles and generates learnable environments targeting those weaknesses.
AI
Its creators say the benchmark pairs simple goals with challenging physics to test both models beyond simple robot-control tasks.
AI
The announcement says learnable “canvas tokens” carry multimodal models’ visual plans into diffusion models through a lightweight connector.
