Counterpoint by Convolution · HackerPapers discussions

Counterpoint by Convolution — mentioned by koningrobot

Mon, 20 Oct 2025 19:38:26 GMT

It goes further back than that. In 2014, Li Yao et al (https://arxiv.org/abs/1409.0585) drew an equivalence between autoregressive (next token prediction, roughly) generative models and generative stochastic networks (denoising autoencoders, the predecessor to difussion models). They argued that the parallel sampling style correctly approximates sequential sampling. In my own work circa 2016 I used this approach in Counterpoint by Convolution (https://arxiv.org/abs/1903.07227), where we in turn argued that despite being an approximation, it leads to better results. Sadly being dressed up as…

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

Counterpoint by Convolution — mentioned by kastnerkyle

Thu, 12 May 2022 03:18:30 GMT

I've had pretty good luck recently with a mix of SUNDAE (https://arxiv.org/abs/2112.06749) and coconet (https://arxiv.org/abs/1903.07227) and/or Music Transformer based internal models recently for modeling very small datasets of polyphonic "midified" music. Research paper hopefully soon to come... Not sure what your pipeline looks like, but those papers might be worth putting on your radar. And as you mention, symbolic music datasets are both surprisingly small, surprisingly low quality, and generally a huge pain to work with. Cool stuff - I like the sax! For anyone unfamiliar with diffusion…

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