Bailin Wang, Yue Zhang, Freda Shi, Songlin Yang, Wei Bi, Leyang Cui, Ruijie Zhu, Yiqiao Wang, Bolun Wang, Peng Zhou, Guohong Fu
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Linear attention Transformers and their gated variants, celebrated for enabling parallel training and efficient recurrent inference, still fall short in recall-intensive tasks compared to traditional Transformers and demand significant resources for training from scratch. This paper introduces Gated Slot Attention (GSA), which enhances Attention with Bounded-memory-Control (ABC [63]) by incorporating a gating mechanism inspired by Gated Linear Attention (GLA [96]). Essentially, GSA comprises a two-layer GLA linked via softmax, utilizing context-aware memory reading and adaptive forgetting to improve memory capacity while maintaining compact recurrent state size. This design greatly enhances both training and inference efficiency through GLA's hardware-efficient training algorithm and reduced state size. Additionally, retaining the softmax operation is particularly beneficial in "finetuning pretrained Transformers to RNNs" (T2R [41]) settings, reducing the need for extensive training from scratch. Extensive experiments confirm GSA's superior performance in scenarios requiring in-context recall and in T2R settings.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2409.07146")
get_code_for_paper("2409.07146")
have("2409.07146")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2409.07146.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2409.07146)
Connect an agent — have() is free.