LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2304.15010/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTLLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model — mentioned by aspenmayerhttps://news.ycombinator.com/item?id=39417798urn:hackerpapers:mention:2304.15010:39417798Sun, 18 Feb 2024 10:12:08 GMT<p>A fine suggestion. For you and others: https://arxiv.org/abs/2304.15010 also available at: https://doi.org/10.48550/arXiv.2304.15010</p><p><a href="https://hackerpaper.kaipfister.de/p/2304.15010/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CVLLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model — mentioned by benobhttps://news.ycombinator.com/item?id=39417240urn:hackerpapers:mention:2304.15010:39417240Sun, 18 Feb 2024 08:28:00 GMT<p>This reminds me of bias tuning, a LoRA competitor. One can get decent adapters by only finetuning a vector added to each linear layer activations. I think I saw it first while reading [1] but there are other instances. [1] https://arxiv.org/pdf/2304.15010.pdf</p><p><a href="https://hackerpaper.kaipfister.de/p/2304.15010/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CV