Composite-Gradient Learning for Shared Control Authority Between Deep Reinforcement Learning and Model Predictive Control
Research
Research News
New papers, breakthroughs and academic AI research
SAM-on-the-Curve: Sharpness-Aware Mode Connectivity for Robust Weight-Space Interpolation
Research
Does Moral Reasoning Training Help or Hurt? Red-Teaming RL-Trained Ethical Agents with Persona Attacks
Research
MDN-Control: Mask-Depth-Noise Guided Region Control for Multi-Subject Video Editing
Research
Vision And Text Transformer For Predicting Answerability On Visual Question Answering
Research
Large Language Models Versus Physicians in Traditional Chinese Medicine: A Real-World Clinical Case Evaluation
Research
No Usable Linear "Capitulation Direction" in Two Small LLMs: A Validation Protocol for Activation-Steering Claims, and a Cross-Family Behavioral Study of Sycophancy Under Pushback
Research
The Free Inference Dimension: Complexity Measure for Zero-Collision Navigation under Hypothesis Mixtures
Research
The Limits of BPE Tokenization in Polish: Segmentation-Flexional Forms, Grammatical Anchoring, and First-Person Stability in Inflectional Language Models
Research
Making Political Text Scaling Comparable: Infrastructure and Hyperparameter Sensitivity for 17 Algorithms
Research
Counterfactual Reasoning for Robust Visual Question Answering
Research
MechReason: Benchmarking Multi-Image Multi-Hop Reasoning in Mechanical Engineering
Research