Adaptive Latent Capacity for World Models
ALeWM learns compact latent prefixes for JEPA world models and beats fixed-width LeWM.
Stories per day · 30 days
2 RSS
5 stories, newest first · one card per story
Stories tagged #latent-representation
Beyond Compression: Training Latent Representations for Stable Long-Horizon Rollout in Neural Surrogate Solvers
Research on improving long-horizon rollout stability in neural surrogate solvers, reducing error by 40% while matching full-resolution models on physics benchmarks.
Workspace Models: Lightweight Robotic Memory via Saliency-Driven Supervision
Researchers propose workspace tokens, a lightweight latent robot memory distilled from train-time VLM saliency queries, improving policy performance without in-loop VLM calls.
Learning Foresight without Explicit Trajectories for 3D Diffusion Policies
Movement Trend Guidance adds latent foresight to 3D diffusion policies, improving DP3 across RoboTwin2.0, LIBERO-40, and real-robot tasks with only 3.52% more parameters.
AlayaVista: Streaming World Modeling from Panoramic States to Perspective Video
AlayaVista is a camera-controllable streaming video world model that decouples panoramic scene evolution from perspective synthesis, trained on a 1,318-hour 4K dataset.