AI.info
Wenbo Su
Explore Wenbo Su on AI.info.
- Expert Divergence Learning for MoE-based Language Models
- CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling
- COMI: Coarse-to-fine Context Compression via Marginal Information Gain
- Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization
- MeSH: Memory-as-State-Highways for Recursive Transformers