Activation-Informed Pareto-Guided Low-Rank Compression for Efficient LLM/VLM

Documenti analoghi

• Saten: Sparse Augmented Tensor Networks for Post-Training Compression of Large Language Models
  di: Solgi, Ryan, et al.
  Pubblicazione: (2025)
• SharpZO: Hybrid Sharpness-Aware Vision Language Model Prompt Tuning via Forward-Only Passes
  di: Yang, Yifan, et al.
  Pubblicazione: (2025)
• FLAT-LLM: Fine-grained Low-rank Activation Space Transformation for Large Language Model Compression
  di: Tian, Jiayi, et al.
  Pubblicazione: (2025)
• RankGuide: Tensor-Rank-Guided Routing and Steering for Efficient Reasoning
  di: Tian, Jiayi, et al.
  Pubblicazione: (2026)
• INTERLACE: Interleaved Layer Pruning and Efficient Adaptation in Large Vision-Language Models
  di: Madinei, Parsa, et al.
  Pubblicazione: (2025)