MINER: Mining Multimodal Internal Representation for Efficient Retrieval

Documenti analoghi

• LLM Safety From Within: Detecting Harmful Content with Internal Representations
  di: Jiao, Difan, et al.
  Pubblicazione: (2026)
• QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents
  di: Yuan, Ye, et al.
  Pubblicazione: (2026)
• CARE: Privacy-Compliant Agentic Reasoning with Evidence Discordance
  di: Liu, Haochen, et al.
  Pubblicazione: (2026)
• SPIN: Sparsifying and Integrating Internal Neurons in Large Language Models for Text Classification
  di: Jiao, Difan, et al.
  Pubblicazione: (2023)
• MINER: Mining the Underlying Pattern of Modality-Specific Neurons in Multimodal Large Language Models
  di: Huang, Kaichen, et al.
  Pubblicazione: (2024)