Computationally efficient safe exploration in reinforcement learning
Research
Research News
New papers, breakthroughs and academic AI research
From Concept Alignment to Causal Grounding: An Intervention Test of Chain-of-Thought Faithfulness
Research
Directing large language models to follow the letter or spirit of the law
Research
OmniEdu: Open Foundation Models for Learning and Teaching
Research
Chronologic: Measuring Language Models' Ability to Represent the Past
Research
Low resource cross-modal alignment using HGNN to enhance speech representation
Research
SoK: Formal Methods for Fact-Checking and Information Integrity
Research
Collapse, Not Complexity: Failure-Conditioned Decomposition Repair for End-to-End Document Parsing
Research
Interpretable Multi-Hypersphere Deep Anomaly Detection for Open-set Supervised Anomaly Detection
Research
MolSC: Leveraging Substituent Contributions to Enhance Fine-grained Molecular Understanding in LLMs
Research
Robot World Models Are Not Invariant to How the Actions Are Written
Research
PairDropGS: Paired Dropout-Induced Consistency Regularization for Sparse-View Gaussian Splatting
Research