SPARC: Subspace-Aware Prompt Adaptation for Robust Continual Learning in LLMs

Ähnliche Einträge

• Learning Conformal Abstention Policies for Adaptive Risk Management in Large Language and Vision-Language Models
  von: Tayebati, Sina, et al.
  Veröffentlicht: (2025)
• EigenShield: Causal Subspace Filtering via Random Matrix Theory for Adversarially Robust Vision-Language Models
  von: Darabi, Nastaran, et al.
  Veröffentlicht: (2025)
• TRACER: Trajectory Risk Aggregation for Critical Episodes in Agentic Reasoning
  von: Tayebati, Sina, et al.
  Veröffentlicht: (2026)
• EigenTrack: Spectral Activation Feature Tracking for Hallucination and Out-of-Distribution Detection in LLMs and VLMs
  von: Ettori, Davide, et al.
  Veröffentlicht: (2025)
• VLM Judges Can Rank but Cannot Score: Task-Dependent Uncertainty in Multimodal Evaluation
  von: Kumar, Divake, et al.
  Veröffentlicht: (2026)