arXiv:2608. 11519v1 Announce Type: new Abstract: Full self-attention is a strong token mixer for PDE surrogates on irregular domains, but its quadratic cost limits its use on high-resolution problems.
By Vedant Puri, Yongjie Jessica Zhang, Levent Burak Kara
arXiv:2608. 06776v1 Announce Type: new Abstract: A standard self-attention layer consists of two interacting circuits: the query-key circuit that governs attention allocation, and the output-value circuit that maps attended representations to predictions.
By Rahul Vashisht, Harish G. Ramaswamy
arXiv:2608. 16797v1 Announce Type: cross Abstract: Industrial recommenders rely on two model families that have evolved largely independently: feature-interaction models over multi-field user/item features, and sequential models over user-behavior histories.
By Rongcheng Lin, Yan Sun, Jamey Zhang, Guanglei Xiong, Ivan Ji, Xianjie Chen, Shujian Bu
arXiv:2606. 07703v1 Announce Type: cross Abstract: Long-context prefill remains expensive because full/GQA layers still score the historical sequence, even in hybrid models with local, sparse, linear, or recurrent components.
By Hongxing Wang, Harenome Razanajato, Zhen Zhang, Yujie Yuan, Hongsheng Liu
Elastic Threshold Attention (ETA) is a trainable attention mechanism that dynamically predicts contextual thresholds from query representations, enabling selective pruning of KV cache tokens during long‑context decoding. By multiplicatively suppressing sub‑threshold logits during training, ETA avoids representation collapse and eliminates localized attention sinks, allowing a 1.45B model to match dense attention performance at roughly 85% training sparsity and 38% active decode density. At inference, a custom Triton kernel achieves up to 2.5× faster decoding on sequences up to 512K tokens, and an offline calibration step can further reduce compute by 27% by freezing per‑head thresholds.
By Themistoklis Haris, Henry Li, Maryam Karimzadehgan
arXiv:2607. 22700v1 Announce Type: new Abstract: Post-click conversion rate (PCVR) prediction is central to industrial recommendation, but remains challenged by the structural mismatch between sparse, unordered multi-field features and long, domain-specific behavior histories.
By Wenan Wang, Qin Zhao, Zhixiang Lu