Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free · HackerPapers discussions

Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free — mentioned by RandyOrion

Sun, 07 Dec 2025 03:05:41 GMT

For arXiv papers, I prefer HTML format much more than PDF format. Compared to PDF format, HTML format is much more accessible because of browsers. Basically I can reuse my browser extensions to do anything I like without hassle, like translation, note taking, sending texts to LLMs, and so on. For now, arXiv offers two HTML services: the default one in https://arxiv.org/html/xxxx.xxxxx , and the alternative one in https://ar5iv.labs.arxiv.org/html/xxxx.xxxxx , here 'x' is a placeholder for a number or digit. The most glaring problem of the default HTML service is the coverage of papers.…

Paper and discussion history. A mention is not an endorsement.

Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free — HN submission

Sun, 30 Nov 2025 16:35:18 GMT

Gated Attention for Large Language Models

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free — mentioned by yorwba

Fri, 12 Sep 2025 09:12:55 GMT

Also, Gated Attention: https://arxiv.org/abs/2505.06708

Paper and discussion history. A mention is not an endorsement.