The Evidence Ladder for Reinforcement Learning in Healthcare: From Retrospective Policies to Trusted Interventions
Research
Research News
New papers, breakthroughs and academic AI research
Efficient Reasoning Exploration via State-Conditioned Latent Steering with Progress Guidance
Research
Time-Incremental Continued Pretraining of LLMs: Knowledge Updates Without Catastrophic Forgetting
Research
A$^2$Safe: Counterfactual Evidence-Aligned Adaptive Agent Collaboration for Safe and Effective Visual Question Answering
Research
Measuring the Assistant's Harmlessness Preferences on the User Turn
Research
Patch-to-Global: Random Patch Diffusion for Globally Consistent Megapixel Artifact Inpainting in Whole Slide Images
Research
HaikuS2S: A Cascaded System For Responding In Verse
Research
Positive Pair Geometry Matters: Optimal Transport for Contrastive Learning of Visual Representations
Research
XYEval: Agents say yes to bad advice
Research
Tool-Augmented On-Policy Distillation for LLM Domain Adaptation in Sequence-Based Omics Tasks
Research
Predicting Out-of-Distribution Generalization of Neural Operators via Observable Spectral Error Decomposition
Research
1% of Tokens Can Be Enough: On Gradient Estimation in On-Policy Distillation
Research