
@_cobalamini
iAccount based inGermany
About this account
- Account based in
- Germany
- Connected via
- Web
Account-level information from X, not a live location or the device used for a specific post.
Simon retweeted
๐ซ Large Language Continuous Diffusion Models
Presenting Sigma, the first large-scale (3B/8B) continuous diffusion LM (dLM) trained with likelihood.
๐ Comparable with discrete dLMs and AR on math and coding
๐๏ธ Enables meaningful study of inference-time interventions
Jointly led with Wei Guo (@WeiGuo01), Jean-Marie Lemercier (@jm_lemercier), Simon Welker (@_cobalamin)
Team: @YongganFu @mmkamani7 Sajad Norouzi @julberner @tomasgeffner @karsten_kreis @YongxinChen1 @MoleiTaoMath @jwthickstun @PavloMolchanov Ante Jukic @ArashVahdat @MardaniMorteza
Simon retweeted
Can the Bluetooth commitee get their heads out of their asses and invent a revolutionary(!) protocol that lets us do this and also not downgrade to callcenter quality audio when using the microphone? It's 2025 and Bluetooth still sucks ass.
Simon retweeted
Simon Welker, Tal Peer, Timo Gerkmann, "Real-Time Streaming Mel Vocoding with Generative Flow Matching," arxiv.org/abs/2509.15085
Simon retweeted
Imagine if, in the 1890s, Eastman Kodak had created an entire research team devoted to figuring out if film cameras actually did steal your soul.
Simon retweeted
Most modernization attempts accompany a sense of delusional disrespect for existing systems and profound arrogance that the people who came before them were incompetent/ignorant. This lack of humility combined with a cacophonous fetish for making things *appear* modern/sexy, it's a recipe for civilizational regression. False confidence to undertake modernization comes from technological progressโi.e., "We have faster computers and bigger screens now, and they didn't. We can design things better!"โwhich becomes apparent as the new systems they design are bloated, slow and utterly dysfunctionalโindicting their thesis for change.
Simon retweeted
FlowDec
An neural full-band audio codec for general audio sampled at 48 kHz with 7.5 kps or 4.5 kbps.
github.com/facebookresearch/โฆ
Simon retweeted
๐ Join Our Team! We have exciting open positions:
๐ Postdoc: Data Science & AI for Speech & Audio
๐ PhD/Postdoc: AI-based Speech & Audio
๐ PhD: Diffusion Models for Speech Processing
๐ 3 PhD positions for Imaging & Speech
๐ inf.uni-hamburg.de/en/inst/aโฆ
Simon retweeted
Best Student Paper Award at IWAENC 2024 with @moliner_eloi for our joint work on Unsupervised Speech Dereverberation using Diffusion Models!!
Thanks to @_cobalamin @sp_uhh @AaltoAkuLab for the great work!
More publications on the topic: inf.uni-hamburg.de/en/inst/aโฆ
Simon retweeted
Smashing my PC when it looked like the AoE II medium AI was beating me was not an act of frustration. It was actually an example of Extraplanar Warfare, the approach to military theory I've been developing. You attack the enemy in metaphysical modalities to which he has no access
Simon retweeted
BUDDy: Single-Channel Blind Unsupervised Dereverberation with Diffusion Models
We present a fully unsupervised method for blind speech dereverberation using a diffusion prior and a parametric subband filter
Paper ๐ arxiv.org/abs/2405.04272
Audio/Code ๐ uhh.de/sp-inf-buddy
Simon retweeted
๐ฃ๐ต๐ ๐ฝ๐ผ๐๐ถ๐๐ถ๐ผ๐ป โ๐๐ถ๐ณ๐ณ๐๐๐ถ๐ผ๐ป-๐๐ฎ๐๐ฒ๐ฑ ๐๐ฒ๐ฒ๐ฝ ๐๐ฒ๐ป๐ฒ๐ฟ๐ฎ๐๐ถ๐๐ฒ ๐ ๐ผ๐ฑ๐ฒ๐น๐ ๐ณ๐ผ๐ฟ ๐ฆ๐ฝ๐ฒ๐ฒ๐ฐ๐ต ๐ฆ๐ถ๐ด๐ป๐ฎ๐น ๐ฃ๐ฟ๐ผ๐ฐ๐ฒ๐๐๐ถ๐ป๐ดโ. Join us in pushing the state-of-the-art in this exciting field.
Details and on how to apply:
inf.uni-hamburg.de/en/inst/aโฆ
Simon retweeted
We just opened a PhD or Postdoc position on AI-based speech and audio signal processing.
Please see our webpage for details and on how to apply
inf.uni-hamburg.de/en/inst/aโฆ
Simon retweeted
We offer an exciting #PhDposition on deep multi-microphone speech enhancement. Please find details on our webpages
inf.uni-hamburg.de/en/inst/aโฆ


























