technique
Concept-Constrained Prompt Learning
techniqueactiveprovisional
concept-constrained-prompt-learning-f84187ff·1 events·first seen 4h agoAliases: Concept-Constrained Prompt Learning
Co-occurring entities
More like this (12)
On the Limits of Prompt-Conditioned Language Models as General-Purpose Learnersembodiment-aware prompt conditioningConstrained Reinforcement Learningchain-of-thought promptingMulti-Task Bayesian In-Context LearningObserve-and-Act Adaptive Context SelectionReinforcement Learning Elicits Contextual Learning of Unseen Language Translationfew-shot promptingknowledge graph promptingGoal-Conditioned Reinforcement LearningUniIntervene: Agentic Intervention for Efficient Real-World Reinforcement LearningCross-Event Prompt Fusion
Recent events (1)
Concept-Constrained Prompt Learning (CCPL) improves CLIP few-shot generalization via concept regularization
Researchers propose Concept-Constrained Prompt Learning (CCPL), a lightweight regularization framework for few-shot CLIP adaptation that anchors learnable class prompts to frozen concept-level text prototypes. The method uses cosine consistency objectives in text space and concept dropout to reduce overfitting to base classes, improving base-to-new generalization. Experiments show gains on DTD (+0.6 HM) and EuroSAT (+2.9 HM) over CoOp, with near-neutral results on OxfordPets, suggesting effectiveness is tied to how well concept prototypes align with dataset semantics.