← authors · overview

• Pangu Pro MoE: Mixture of Grouped Experts for Efficient Sparsity
  2025 · 1 citations
• FocuSFT: Bilevel Optimization for Dilution-Aware Long-Context Fine-Tuning
  2026
• Behavioral Fingerprinting of Large Language Models
  2025
• CMoE: Fast Carving of Mixture-of-Experts for Efficient LLM Inference
  2025
• CMoE: Fast Carving of Mixture-of-Experts for Efficient LLM Inference
  2025
• Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models
  2025
• PreMoe: Lightening MoEs on Constrained Memory by Expert Pruning and Retrieval
  2025
• Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs
  2025
• L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models
  2025
• Faster and Better LLMs via Latency-Aware Test-Time Scaling
  2025
• A Simple Linear Patch Revives Layer-Pruned Large Language Models
  2025
• FlatQuant: Flatness Matters for LLM Quantization
  2024