Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1612.00197/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTLearning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses — mentioned by ollinhttps://news.ycombinator.com/item?id=49136548urn:hackerpapers:mention:1612.00197:49136548Sat, 01 Aug 2026 17:37:03 GMT<p>This paper shows a nice integration of older winner-take-all ideas for learning K-modal generative models (see e.g. https://arxiv.org/abs/1612.00197, https://arxiv.org/abs/2211.14286) into modern diffusion/flow pipelines. As-implemented, I think it has some downsides: 1. K-1 extra forward passes during training 2. Inaccurate sampling behavior (will sample all K modes with equal likelihood, rather than sampling them proportionally) However, I think both of these downsides can be mitigated by adjusting the implementation a bit more (you can have the model predict K modes jointly in one forward…</p><p><a href="https://hackerpaper.kaipfister.de/p/1612.00197/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CV