Results for "contrastive vision-language"
Tool-Augmented Prompt
Intro
Enables external computation or lookup.
Exposure Bias
Intermediate
Differences between training and inference conditions.
Prompt Sensitivity
Intermediate
Small prompt changes cause large output changes.
Token Budgeting
Intermediate
Limiting inference usage.
Intent Recognition
Frontier
Inferring human goals from behavior.
E-Discovery
Intermediate
AI-assisted review of legal documents.
AI Hallucination
Intermediate
Fabrication of cases or statutes by LLMs.
Automated Hypothesis Generation
Advanced
AI proposing scientific hypotheses.
Self-Supervised Learning
Intermediate
Learning from data by constructing “pseudo-labels” (e.g., next-token prediction, masked modeling) without manual annotation.