Tag
This paper proposes LDT-Coord, a lightweight digital-twin coordination framework for heterogeneous LLM embodied agents over computing power networks, achieving a task success rate comparable to conventional methods while reducing communication overhead by over 70×.
KTransformers is a framework that optimizes inference and fine-tuning of large Mixture-of-Experts models by dynamically placing only active experts on the GPU while keeping the rest in CPU memory, enabling large models like DeepSeek-V3 to run on limited consumer GPU memory.
OmniRetrieval is a framework that unifies retrieval across heterogeneous knowledge sources (text, tables, graphs) by dispatching native queries to appropriate execution engines, outperforming single-source baselines on a benchmark of 13 datasets and 309 knowledge bases.