Ge Liu
4 papers · Latest:
A-CODE: Fully Atomic Protein Co-Design with Unified Multimodal Diffusion
A-CODE is a fully atomic, unified multimodal diffusion model for protein co-design, achieving superior designability and outperforming existing methods.
Thought-Retriever: Don't Just Retrieve Raw Data, Retrieve Thoughts for Memory-Augmented Agentic Systems
Thought-Retriever enables LLMs to overcome context limits by retrieving and organizing past intermediate responses ('thoughts') for self-evolving long-term memory.
LangFlow: Continuous Diffusion Rivals Discrete in Language Modeling
LangFlow introduces the first continuous diffusion language model that rivals discrete counterparts, closing a significant performance gap in language modeling.
Batched Contextual Reinforcement: A Task-Scaling Law for Efficient Reasoning
Batched Contextual Reinforcement (BCR) trains LLMs to solve multiple problems concurrently, significantly reducing token usage while maintaining or improving reasoning accuracy.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.