Classifying Dominant Temporal Orientation without Pretrained Text Embeddings: A Novel Morphosyntactic Inventory Vector Approach
Research
Research News
New papers, breakthroughs and academic AI research
Instruct, Not Answer: Using Instruction Privileges in On-Policy Context Distillation
Research
What Can a Leaderboard Certify? Compositional Controllability for Fair Evaluation and Training of Biomedical Literature-Review Agents
Research
Agentic Video Understanding: A Survey
Research
RAO-Nav: Probing Omni-Language Models for Zero-shot Semantic Audio-Visual Navigation
Research
Witness: Discovery, Deciphering, and Epiphany in Interactive Puzzle Environments
Research
Certifying Interventional Agreement Among Observationally Equivalent Causal Models
Research
Typed Decision Models: An Early Evidence Audit and Evaluation Checklist
Research
Generalization and Memorization along the Learning Trajectory of Neural Language Models: A Geometric Account of Categorization
Research
KinyaMed: Seeds, Not Rows -- What a Corpus Requirement Written in the Wrong Unit Fails to Constrain
Research
A bilingual AI audiologist built through rubric-guided playbook induction outperforms human audiologists in a blinded evaluation of simulated cases
Research
Clarify the User or Verify the World? Uncertainty Routing for Proactive Agents
Research