Open ultrasound foundation model for robust segmentation and clinical measurement across heterogeneous settings
Research
Research News
New papers, breakthroughs and academic AI research
LLM-as-an-Improver: Turning Verification into Better Candidates
Research
Position: It is Time to Virtualize Foundation Models with a Self-evolving Operating System Layer
Research
Safety Beyond the Interface: Detecting Harm via Latent States in Large Language Models
Research
The syntax and semantics of goals
Research
QVAC Genesis III: A Large-Scale, High-Quality Open Synthetic STEM Corpus for Efficient Language Model Pre-Training
Research
MAGS: Multi-agent Auto-formalization Guarantees Safety for Agentic Outputs
Research
Compositional Reasoning in Language Models under Reinforcement Learning Post-Training
Research
Regularized Emphatic Temporal-Difference Learning: Stability under Constant Stepsizes
Research
SCOUT: Sim-to-Real Text-Based Person Retrieval by Embedding-Space Prediction over Frozen Video Features
Research
Inference-Time Nash Alignment
Research
From Rollout to Reset: A Graph-Based Harness for Autonomous Long-Horizon Manipulation Evaluation
Research