← authors · overview

• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
  2026
• The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models
  2026
• MiniCPM4: Ultra-Efficient LLMs on End Devices
  2025
• BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity
  2025
• MiniCPM4: Ultra-Efficient LLMs on End Devices
  2025
• BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity
  2025
• InfLLM-V2: Dense-Sparse Switchable Attention for Seamless Short-to-Long Adaptation
  2025
• Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models
  2022
• Predicting Emergent Abilities with Infinite Resolution Evaluation
  2023
• Mastering Text, Code and Math Simultaneously via Fusing Highly Specialized Language Models
  2024
• MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
  2024
• Ouroboros: Speculative Decoding with Large Model Enhanced Drafting
  2024
• MiniCPM-V: A GPT-4V Level MLLM on Your Phone
  2024
• Configurable Foundation Models: Building LLMs from a Modular Perspective
  2024