Alignment Research, Model Robustness, Adversarial Examples, Risk Assessment
MemeMind: A Large-Scale Multimodal Dataset with Chain-of-Thought Reasoning for Harmful Meme Detection
arxiv.org·14h
Machines of Faithful Obedience
lesswrong.com·20h
Toward Decision-Oriented Prognostics: An Integrated Estimate-Optimize Framework for Predictive Maintenance
arxiv.org·14h
RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1
arxiv.org·14h
How Leaders Can Fix Failing AI Ethics
pub.towardsai.net·4h
NTRL: Encounter Generation via Reinforcement Learning for Dynamic Difficulty Adjustment in Dungeons and Dragons
arxiv.org·14h
Unlocking Insights Addressing Alcohol Inference Mismatch through Database-Narrative Alignment
arxiv.org·14h
Loading...Loading more...