architecture · first seen 5 Oct 2026
Gated DeltaNet
Also: GDN, Gated Delta Networks
Linear-attention recurrent architecture using gated delta-rule updates for efficient sequence modeling.
Mentions per week
PapersCodeDiscussion
Rank 111 on 15 Nov 2026 · 9 mentions in 28 days · 9 independent groups · papers → code · first seen 6 weeks ago · acceleration +0.36
Earliest sources
- HLA-WM: Hybrid Linear Attention for Long-Horizon Video World ModelsPapers · 5 Oct 2026 · Zhuokun Chen, Feng Chen, Xi Lin, Xiyu Wu, Jiahao He, Jianfei Cai, Bohan Zhuang
- HLA: Expressive Hybrid Linear Attention via Chunk-Wise Dynamic MixingPapers · 5 Oct 2026 · Zhuokun Chen, Xi Lin, Xiyu Wu, Jiahao He, Jianfei Cai, Bohan Zhuang
- Dual-Stream Memory for Vision-Language-Action PoliciesPapers · 9 Oct 2026 · Yang Wang, Ping Liu, Ruiyu Wang, Xuhua Chen, Lingfeng Zhang, Tao Zhang
- GateSight: Recurrent Memory Anticipates Attention Memory for Query-Agnostic KV Eviction in Hybrid LLMsPapers · 10 Oct 2026 · Junjie Li, Jiong Lou, Jie Li
- LinMorph: Learning to Morph Weights for Efficient Video DiT LinearizationPapers · 13 Oct 2026 · Lingyi Long, Congyue Zhao, Xiaoou Li, Yanmin Qian, Tao Huang
- MemT-1.0: Towards Memory-Native EvolutionPapers · 19 Oct 2026 · Zhiyu Li, Zeyu Zhang, Linyun Liu, Yiwei Bu, Chenyang Xi, Xichong Zhang, Yi Yu, Y…
Latest sources
- The State Is Not the Bottleneck: A Paged-State Gated-DeltaNet Tile on a Tri-Mode Multicast Mesh, Bit-Exact from RTL to SiliconPapers · 13 Nov 2026 · Cong Xu, Ravi Sankar
- The Noise Floor of a Quantization Comparison: Engine, restart, batch and kernel drift, measured against 8-bit and 4-bit effects in two decision modelsPapers · 11 Nov 2026 · Aleks Blagojevich, Trevor Sunderland
- Systolic Linear Attention: Co-Designing Tile-Grouped Gated Delta Attention for TPUsPapers · 4 Nov 2026 · Gagik Amirkhanyan, Nuojin Cheng
- HybridSpec: Throughput-Aware Speculative Decoding for Hybrid GDN-MoE ModelsPapers · 2 Nov 2026 · Haiyu Wang, Sai Qian Zhang, Zechun Liu, Steven Li
- A Fine-Grained Hierarchy and Benchmark for State Tracking in Language ModelsPapers · 2 Nov 2026 · Jackson Petty, William Merrill, Ashish Sabharwal
- vixhal-baraiya/qwenGPUCode · 1 Nov 2026 · vixhal-baraiya · 121 stars
- FlyWheel: Attention Kernels Built for the TPUPapers · 1 Nov 2026 · Zishuo Bao, Zeshen Zhang, Linkun Chen, Yucheng Lu
- divagr18/qwenputerCode · 19 Oct 2026 · divagr18 · 826 stars
- MemT-1.0: Towards Memory-Native EvolutionPapers · 19 Oct 2026 · Zhiyu Li, Zeyu Zhang, Linyun Liu, Yiwei Bu, Chenyang Xi, Xichong Zhang, Yi Yu, Y…
- LinMorph: Learning to Morph Weights for Efficient Video DiT LinearizationPapers · 13 Oct 2026 · Lingyi Long, Congyue Zhao, Xiaoou Li, Yanmin Qian, Tao Huang
- GateSight: Recurrent Memory Anticipates Attention Memory for Query-Agnostic KV Eviction in Hybrid LLMsPapers · 10 Oct 2026 · Junjie Li, Jiong Lou, Jie Li
- Dual-Stream Memory for Vision-Language-Action PoliciesPapers · 9 Oct 2026 · Yang Wang, Ping Liu, Ruiyu Wang, Xuhua Chen, Lingfeng Zhang, Tao Zhang