Lucid Dreaming for World Models: Learning to Doubt Imagination and Decide by Trust
Research
Research News
New papers, breakthroughs and academic AI research
Follow the Entities: A Corpus Map for Agentic Search
Research
SQUARE: Structured Quantum Representation Adapters as Compact Quadratic Feature Maps for Frozen Language Models
Research
Trajectory Soup: Pushing the Compute-Scaling Frontier of LLM Mid-training via Diverse Trajectories
Research
Interpolated Policy Distillation: A Controllable Continuum Between Off-Policy and On-Policy Distillation
Research
EgoHumanoid-V2: Human-to-Humanoid Transfer of Coordinated Whole-Body Skills for Loco-Manipulation
Research
When to Adapt: Multi-Signal Domain Shift Detection for Efficient Training-Free Adaptation in Open-Vocabulary Segmentation
Research
Procedural Core: A Compact Recurrent Initialization for Vision Transformers
Research
ReSPO: Reshaped Sequence Policy Optimization for Gradient Starvation in Off-Policy Learning
Research
CogWAM: Aligning Semantic Cognition with World Action Modeling via Event-Driven Interfaces
Research
SOLO: Pretraining Billion-Parameter Language Models with Shared-Output Local Learning
Research
PhysWAM: Physically Consistent World Action Model for Autonomous Driving
Research