Rethinking Layer Redundancy: Calibration Matters More Than Search in LLM Depth Pruning

Documenti analoghi

• Locality-Aware Redundancy Pruning for LLM Depth Compression
  di: Yun, Vincent-Daniel, et al.
  Pubblicazione: (2026)
• MedCLM: Learning to Localize and Reason via a CoT-Curriculum in Medical Vision-Language Models
  di: Kim, Soo Yong, et al.
  Pubblicazione: (2025)
• Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs
  di: Yun, Vincent-Daniel, et al.
  Pubblicazione: (2026)
• Generating Plausible Distractors for Multiple-Choice Questions via Student Choice Prediction
  di: Lee, Yooseop, et al.
  Pubblicazione: (2025)
• Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance
  di: Park, Dongmin, et al.
  Pubblicazione: (2024)