Lucid Dreaming for World Models: Learning to Doubt Imagination and Decide by TrustResearchSep 30, 2026
SQUARE: Structured Quantum Representation Adapters as Compact Quadratic Feature Maps for Frozen Language ModelsResearchSep 30, 2026
Trajectory Soup: Pushing the Compute-Scaling Frontier of LLM Mid-training via Diverse TrajectoriesResearchSep 30, 2026
Interpolated Policy Distillation: A Controllable Continuum Between Off-Policy and On-Policy DistillationResearchSep 30, 2026
EgoHumanoid-V2: Human-to-Humanoid Transfer of Coordinated Whole-Body Skills for Loco-ManipulationResearchSep 30, 2026
When to Adapt: Multi-Signal Domain Shift Detection for Efficient Training-Free Adaptation in Open-Vocabulary SegmentationResearchSep 30, 2026
ReSPO: Reshaped Sequence Policy Optimization for Gradient Starvation in Off-Policy LearningResearchSep 30, 2026
CogWAM: Aligning Semantic Cognition with World Action Modeling via Event-Driven InterfacesResearchSep 30, 2026
SOLO: Pretraining Billion-Parameter Language Models with Shared-Output Local LearningResearchSep 30, 2026