A Proof-of-Concept Study of Weakly Supervised Labeling of Fine-Grained EEG Components for Artifact Attenuation
Research
Research News
New papers, breakthroughs and academic AI research
Multi-Label Topic Assignment via LLM Distillation: A Comparative Analysis of Generative vs. Discriminative Student Models
Research
On-Policy Distillation Teaches New Skills but Not New Knowledge
Research
TAP: Efficient Long-Horizon Agent Pruning via Trajectory-Anchored Recovery
Research
Tucker Bottleneck Attention for Multi-Dimensional Sequence Modeling
Research
Breaking Adversarial Transferability in Fine-Tuned Speech Recognition
Research
Rubric Spans are Label Representations: Joint LLM Encoding for Short Answer Scoring
Research
A Scoping Review and Experimental Study on Reinforcement Learning from Human Feedback for Human-Robot Collaboration
Research
A Tale of Two Error Categories: Exploring Concealed Trade-Offs in the Errors of Automated Judges in Evaluation of Uncertainty Quantifiers
Research
Defensive Sufficiency in a Stackelberg Model of AI Security
Research
FedRSPO+: A Heterogeneity-aware Algorithm for Decision-focused Federated Learning
Research
Relevance Is Not Sufficiency: What Actually Closes the Evidence Gap in Long-Term Memory QA
Research