← authors · overview

• A Graph Neural Network for the Era of Large Atomistic Models
  2025 · 21 citations
• Roadmap on Advancements of the FHI-aims Software Package
  2025 · 14 citations
• Vib2Mol: from vibrational spectra to molecular structures-a unified deep learning framework
  2025 · 2 citations
• LightAgent: Production-level Open-source Agentic AI Framework
  2025
• Speed Always Wins: A Survey on Efficient Architectures for Large Language Models
  2025
• Iterative Value Function Optimization for Guided Decoding
  2025
• Linear-MoE: Linear Sequence Modeling Meets Mixture-of-Experts
  2025
• Linear-MoE: Linear Sequence Modeling Meets Mixture-of-Experts
  2025
• Speed Always Wins: A Survey on Efficient Architectures for Large Language Models
  2025
• Evolutionary Guided Decoding: Iterative Value Refinement for LLMs
  2025
• Probing Language Models for Pre-training Data Detection
  2024
• LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training
  2024
• ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLM
  2024
• NesTools: A Dataset for Evaluating Nested Tool Learning Abilities of Large Language Models
  2024