Hybrid language models interleave linear-attention layers with a small number of softmax-attention layers. Prior work largely attributes in-context retrieval to softmax attention, treating linear attention primarily as a mechanism for compressing past context. We revisit this division of labor and show that linear atte...
Single-molecule fluorescence techniques have revolutionized our ability to probe biomolecular dynamics by resolving molecular heterogeneity and transient states inaccessible to ensemble measurements. However, conventional analysis pipelines remain constrained by several factors that compromise both reproducibility and...
Shu-Qi Zhou, Wen-Qi Zeng, Yuan Yao et al.· Nature Communications· 0 citations
ThunderGNN is a hardware-aware acceleration system designed to reconcile graph irregularity with Tensor Core rigidity and significantly outperforms state-of-the-art systems, achieving geometric mean speedups of 1.89× over DGL and 2.59× over PyG.
Yuang Chen, Si-Yi Teng, Wen-Qi Zeng et al.· Proceedings of the VLDB Endo...· 0 citations
This work identifies a structural connection between speculative decoding (SD) and length prediction: latent representations produced by the draft decoder in advanced frameworks (e.g., EAGLE-3) encode signals that are predictive of generation length.
Wei-Huang Wen, Ying-Ying Liu, Yi-Chuan Liu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.