Got a "too familiar" tune from your generative model? Try checking for musical version matching (MVM)!. But MVM works with full tracks, and your tune is just a segment. Well, in our latest work we tackle precisely this issue, and achieve SOTA results even on full tracks!. 1/4

Just embrace luck. You submit and some random people will either like it or not. Then finished, either resubmit somewhere else or leave it on ArXiv. Time will judge you and them. Let it flow.

Generate videos in just a few seconds. Try Grok Imagine, free for a limited time.

The answer to an overcomplicated hyper-cumbersome disfunctional peer-review system is not adding things to it, but removing them.

RT @zhaisf: Unlike an RNN, one attention block alone cannot model anything interesting. And it’s the stacking of it that does wonders. Unde….

RT @HubertSiuzdak: Cool work and a nice read. But why we rebranded masked language models to diffusion language models 😭.

RT @docmilanfar: some of the most hyped use cases of Al aren’t use cases at all - they're parlor tricks that serve no purpose.

RT @kenneth0stanley: Those who intuit something is lacking in LLMs struggle to pinpoint the gap beyond inadequate metaphors like “stochasti….

RT @HannesStaerk: Tomorrow we discuss diffusion models for sampling unnormalized densities "Adjoint Sampling: Highly Scalable Diffusion Sam….

RT @dlbcnai: Call for presenters is out ! This year, we replace the orals by spotlight + posters. We will also have more invited talks. ht….

RT @hungchiayu123: 🚨 New model alert! Meet 🎵JAM🎵: our tiny AI song generator that turns your lyrics into songs with precise word-level timi….

RT @drscotthawley: .@elonmusk apparently missed my talk to @xianityplus in 2018.

RT @docmilanfar: MIT has a long tradition of hacks. One of the best was in 1985 when Ted Larkin, a freshman, returned to his dorm room one….

RT @CVC_UAB: 🔈 Keynote Session with Joan Serrà (@SonyAI_global ) on 'Supervised contrastive learning from weakly-labeled audio segments for….

RT @jaseweston: 🌿Introducing MetaCLIP 2 🌿.📝: code, model: After four years of advancements….

RT @ArxivSound: Nao Tokui, Tom Baker, "Latent Granular Resynthesis using Neural Audio Codecs,"

RT @chrisdonahuey: Excited to share our beta release of Music Arena, a live evaluation platform for state-of-the-art AI music generation mo….

RT @makingAGI: 🚀Introducing Hierarchical Reasoning Model🧠🤖. Inspired by brain's hierarchical processing, HRM delivers unprecedented reasoni….

RT @s_scardapane: *Diffusion Models are Evolutionary Algorithms*.by @YanboZhang3 @drmichaellevin et al. They develop novel evolutionary al….

RT @cloneofsimo: Very nice blogpost on RoPE variants by @jerryx314

RT @2prime_PKU: Anyone knows adam?

RT @rasbt: From GPT to MoE: I reviewed & compared the main LLMs of 2025 in terms of their architectural design from DeepSeek-V3 to Kimi 2.….