https://hackerpaper.kaipfister.de/p/2410.17434/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=41939444urn:hackerpapers:mention:2410.17434:41939444Thu, 24 Oct 2024 20:31:39 GMT<p>VideoLLM from Meta! LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding Paper: https://huggingface.co/papers/2410.17434 Code: https://github.com/Vision-CAIR/LongVU Project (Demo): https://vision-cair.github.io/LongVU We propose LongVU, a video LLM with a spatiotemporal adaptive compression mechanism designed for real-world hour-long video understanding. LongVU adaptively reduces the number of video tokens by leveraging (1) DINOv2 feature similarity across frames, (2) Cross-modal text-frame similarity, and (3) temporal frame similarity. 1. High quality on…</p><p><a href="https://hackerpaper.kaipfister.de/p/2410.17434/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CVhttps://news.ycombinator.com/item?id=41939443urn:hackerpapers:submission:2410.17434:41939443Thu, 24 Oct 2024 20:31:39 GMT<p>LongVU – New Video LLM from Meta</p><p></p><p>2 points; 1 discussion reply on HN. <a href="https://hackerpaper.kaipfister.de/p/2410.17434/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CV