FDE-Gym: The Last Mile of AI Delivery

New research challenges the superposition theory of polysemanticity, suggesting neural networks are more interpretable than previously believed through recursive generalization patterns.

Researchers propose MirrorMoE to address the exploration dilemma in modern Mixture-of-Experts architectures between fine-grained segmentation and shared experts.

Researchers introduce T2-z, a method for test-time optimization of environment latents in robotic world models that improves prediction accuracy and action success rates across simulations and real-world tasks.

Researchers introduce OmniVerifier-C1, a decomposed graded verifier that provides continuous scoring instead of binary judgments for multimodal verification tasks.

GeoState introduces a view-decoupled geometry representation for 3D world modeling that separates scene dynamics from camera motion, outperforming prior models on Waymo and generalizing to KITTI/nuScenes.