Songlin Yang

Songlin Yang has 2 papers in our library, in 2023–2025, most of them on Efficient models & compression; often with Enzhe Lu, Fanqing Meng, Jiaxi Hu.

2 papers in our library · 2023–2025

The profile is the library's match of the name; two people with one name are not always told apart.

Fields, topics and concepts

Of its works in our library, with the number of works on each.

The most cited first (OpenAlex and our library).

Hierarchically Gated Recurrent Neural Network for Sequence Modeling (2023 · 73 citations)
Transformers scale quadratically with sequence length. RNNs run in linear time but are traditionally slow to train and weak at capturing distant context. The authors propose HGRN (Hierarchically Gated Recurrent Neural Network), a stack of layers that pairs an HGRU token mixer with a GLU channel mixer. HGRU uses…
Kimi Linear: An Expressive, Efficient Attention Architecture (2025 · 51 citations)
Softmax attention becomes a bottleneck for agentic and RL-heavy LLM workloads. Its cost grows quadratically with sequence length, and its KV cache keeps expanding during long decoding. Earlier linear-attention and hybrid designs saved compute but usually lost quality or were only tested at small scale. The Kimi Team…

10 co-authors with a page, the most papers together first.

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 87 times (of the 149,439 papers whose bibliographies we read); 26 citing papers with a page here →.

Updated 3 November 2026