MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies (2024 · 269 citations)
Training very large language models is expensive, which makes experiments hard to afford, and the resulting models are difficult to run on phones or laptops.
ERNIE-ViLG: Unified Generative Pre-training for Bidirectional Vision-Language Generation (2021 · 33 citations)
Image captioning and text-to-image synthesis are two directions of the same mapping between vision and language, yet they have usually been handled by separate, task-specific architectures.
MiniCPM-SALA: Hybridizing Sparse and Linear Attention for Efficient Long-Context Modeling (2026 · 2 citations)
Full attention in Transformers is costly for very long inputs. Compute grows quadratically with length, and the KV-Cache can reach tens or hundreds of gigabytes at million-token scale. Sparse attention cuts computation but still keeps the whole cache. Linear attention is cheap but compresses context lossily and loses…

Co-authors here

12 of 21 co-authors with a page, the most papers together first.

Cited by

Papers of our library cite their works 276 times (of the 149,439 papers whose bibliographies we read); 68 citing papers with a page here →.

Updated 31 October 2026