Today we released JASCO 🥁🎵🪇! JASCO uses time-aligned conditions (e.g. drums, melody) as guiding controls for text-to-music generation. 📜Full Paper: 🔊Samples: @lonziks @itai_gat @FelixKreuk @adiyossLC Stay tuned for updates.

RT @hila_chefer: This work was done during my internship at @AIatMeta 🎉 Huge thanks to my amazing collaborators @urielsinger @amit_zhr @YK…

@lonziks @itai_gat @FelixKreuk @adiyossLC To play with the models and checkpoints you can run the Gradio app on your device and play with the checkpoints by running `python demos/jasco_app.py` from the audiocraft root dir 🥳

RT @OmriAvr: [1/7] 📜 I can finally share that our recent @NVIDIA project DiffUHaul --- A Training-Free Method for Object Dragging in Images…

RT @MichaelHassid: Which is better, running a 70B model once, or a 7B model 10 times? The answer might be surprising! Presenting our new @…

RT @FelixKreuk: Excited to share our latest work on discrete flow matching! A new framework that achieves SOTA non-autoregressive generatio…

RT @itai_gat: Excited to share Discrete Flow Matching! A discrete flow framework that yields state-of-the-art non-autoregressive modeling.…

RT @AIatMeta: We recently announced JASCO, a music-generation model with improved controllability using conditioning inputs like chords or…

RT @Amit_Roth: We present our #INTERSPEECH2024 paper "A Language Modeling Approach to Diacritic-Free Hebrew TTS" 🎙️. Model is fully open so…

RT @NeumanRoee: צריך לדאוג שכל ישראלי יראה את ה-3 דק האלה של יאיר לפיד

RT @MohammadSalaama: I am excited to share my first work: "Dataset Size Recovery from LoRA Weights". Ever wondered if you could find out ho…

RT @guy_yariv: 1/ Commonsense reasoning needs multimodal knowledge, yet current LLMs focus mostly on text, limiting their integration of cr…

RT @adiyossLC: Speech tokenizers are fundamental in building speech LMs. In a recent study we show the common tokenization method (a.k.a “s…

RT @MichaelHassid: New version for “Transformers are Multi-State RNNs” is now on arxiv: What’s new? Efficiency ana…

RT @AIatMeta: As part of our releases this week, Meta FAIR introduced JASCO. This model differs from other text-to-music approaches with im…

RT @ShovalMessica: 🚨I’m excited to share our #INTERSPEECH2024 paper "NAST: Noise Aware Speech Tokenization for Speech Language Models” 🥳 W/…

RT @ylecun: Lots of open source models released by Meta FAIR today: - Chameleon: experiment in vision-language model with early fusion. - L…

RT @RoniBerkowitz: Thrilled to share that my first article, a result of 2 years of ethnographic work at the President's Residence, has been…

RT @ArxivSound: ``NAST: Noise Aware Speech Tokenization for Speech Language Models,'' Shoval Messica, Yossi Adi,

@ArxivSound Check out examples on our sample page: 🔊😎🎵