Domain-Specific Pruning of Large Mixture-of-Experts Models with Few-shot Demonstrations

Ähnliche Einträge

• ForesightKV: Optimizing KV Cache Eviction for Reasoning Models by Learning Long-Term Contribution
  von: Dong, Zican, et al.
  Veröffentlicht: (2026)
• How Efficient Are Diffusion Language Models? A Critical Examination of Efficiency Evaluation Practices
  von: Peng, Han, et al.
  Veröffentlicht: (2025)
• LongReD: Mitigating Short-Text Degradation of Long-Context Large Language Models via Restoration Distillation
  von: Dong, Zican, et al.
  Veröffentlicht: (2025)
• Exploring Context Window of Large Language Models via Decomposed Positional Vectors
  von: Dong, Zican, et al.
  Veröffentlicht: (2024)
• Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models
  von: Lu, Xudong, et al.
  Veröffentlicht: (2024)