Prompt-driven scene synthesis allows users to generate complete 3D environments from textual descriptions. Current text-to-scene methods often struggle with complex geometries and object transformations, and tend to show weak adherence to complex instructions. We address these limitations by introducing Reason-3D, a text-to-scene model powered by large reasoning models (LRMs). Reason-3D integrates object retrieval using captions covering physical, functional, and contextual attributes. Reason-3D then places the selected objects based on implicit and explicit layout constraints, and refines their positions with collision-aware spatial reasoning. Evaluated on instructions ranging from simple to complex indoor configurations, Reason-3D significantly outperforms previous methods in human-rated visual fidelity, adherence to constraints, and asset retrieval quality. Beyond its contribution to the field of text-to-scene generation, our work showcases the advanced spatial reasoning abilities of modern LRMs. Additionally, we release the codebase to further the research in object retrieval and placement with LRMs.

Recent advancements have brought generated music closer to human-created compositions, yet evaluating these models remains challenging. While human preference is the gold standard for assessing quality, translating these subjective judgments into objective metrics, particularly for text-audio alignment and music quality, has proven difficult. In this work, we generate 6k songs using 12 state-of-the-art models and conduct a survey of 15k pairwise audio comparisons with 2.5k human participants to evaluate the correlation between human preferences and widely used metrics. To the best of our knowledge, this work is the first to rank current state-of-the-art music generation models and metrics based on human preference. To further the field of subjective metric evaluation, we provide open access to our dataset of generated music and human evaluations.

Recent multimodal methods for lyrics alignment have relied on large datasets. Our approach introduces a box loss that directly incorporates timestamp information into the loss function, enabling precise alignment and competitive results even with limited training data. We also address the noise present in the public DALI dataset, conducting a thorough cleaning process to improve the quality of training data. Finally, we propose JamendoLyrics++, a substantial extension of the common JamendoLyrics evaluation dataset, offering improved genre diversity for better evaluation of lyrics alignment systems.

While neural vocoders have made significant progress in high-fidelity speech synthesis, their application on polyphonic music has remained underexplored. In this work, we propose DisCoder, a neural vocoder that leverages a generative adversarial encoder-decoder architecture informed by a neural audio codec to reconstruct high-fidelity 44.1 kHz audio from mel spectrograms. Our approach first transforms the mel spectrogram into a lower-dimensional representation aligned with the Descript Audio Codec (DAC) latent space before reconstructing it to an audio signal using a fine-tuned DAC decoder. DisCoder achieves state-of-the-art performance in music synthesis on several objective metrics and in a MUSHRA listening study. Our approach also shows competitive performance in speech synthesis, highlighting its potential as a universal vocoder.

We introduce DiscoDiff, a text-to-music generative model that utilizes two latent diffusion models to produce high-fidelity 44.1kHz music hierarchically. Our approach significantly enhances audio quality through a coarse-to-fine generation strategy, leveraging residual vector quantization from the Descript Audio Codec. We consolidate this coarse-to-fine design through an important observation that the audio latent representation can be split into a primary and secondary part, controlling music content and details accordingly. We validate the effectiveness of our approach and text-audio alignment through various objective metrics. Furthermore, we provide access to high-quality synthetic captions for the MTG-Jamendo and FMA datasets, as well as open-sourcing DiscoDiff’s codebase and model checkpoints.

We introduce BLAP, a model capable of generating high-quality captions for music. BLAP leverages a fine-tuned CLAP audio encoder and a pre-trained Flan-T5 large language model. To achieve effective cross-modal alignment between music and language, BLAP utilizes a Querying Transformer, allowing us to obtain state-of-the-art performance using 6x less data compared to previous models. This is a critical consideration given the scarcity of descriptive music data and the subjective nature of music interpretation. We provide qualitative examples demonstrating BLAP’s ability to produce realistic captions for music, and perform a quantitative evaluation on three datasets. BLAP achieves a relative improvement on FENSE compared to previous models of 3.5%, 6.5%, and 7.5% on the MusicCaps, Song Describer, and YouTube8m-MTC datasets, respectively. The codebase is available at https://github.com/ETH-DISCO/blap.

In this work, we introduce AutoSing, a novel framework designed to generate diverse and high-quality singing voices from provided lyrics and musical accompaniment. AutoSing extends an existing semantic token-based text-to-speech approach by incorporating musical accompaniment as an additional conditioning input. This enables AutoSing to synchronize its vocal output with the rhythm and melodic nuances of the accompaniment while adhering to the provided lyrics. Our contributions include a novel training scheme for autoregressive audio models applied to singing voice synthesis, as well as ablation studies to identify the best way to condition generation on musical accompaniment. We measure AutoSing’s performance with subjective listening tests, demonstrating its capability to generate coherent and creative singing voices. Furthermore, we open-source our codebase to foster further research in the field of singing voice synthesis.

Recent progress in speech processing has highlighted that high-quality performance across languages requires substantial training data for each individual language. While existing multilingual datasets cover many languages, they often contain insufficient data for each language, leading to models trained on these datasets to exhibit poor performance on most supported languages. Our work addresses this challenge by introducing a scalable pipeline for constructing speech datasets from parliamentary recordings. The proposed pipeline includes robust components for media retrieval and a two-stage alignment algorithm designed to handle non-verbatim transcripts and long-form audio. Applying this pipeline to recordings from 22 European parliaments, we extract over 61k hours of aligned speech segments, achieving substantial per-language coverage with 19 languages exceeding 1k hours and 22 languages exceeding 500 hours of high-quality speech data. We obtain an average 41.8\% reduction in word error rates over baselines when finetuning an existing ASR model on our dataset, demonstrating the usefulness of our approach.

Generative models have made significant progress in synthesizing high-fidelity audio from short textual descriptions. However, editing existing audio using natural language has remained largely underexplored. Current approaches either require the complete description of the edited audio or are constrained to predefined edit instructions that lack flexibility. In this work, we introduce SAO-Instruct, a model based on Stable Audio Open capable of editing audio clips using any free-form natural language instruction. To train our model, we create a dataset of audio editing triplets (input audio, edit instruction, output audio) using Prompt-to-Prompt, DDPM inversion, and a manual editing pipeline. Although partially trained on synthetic data, our model generalizes well to real in-the-wild audio clips and unseen edit instructions. We demonstrate that SAO-Instruct achieves competitive performance on objective metrics and outperforms other audio editing approaches in a subjective listening study. To encourage future research, we release our code and model weights.

Reinforcement learning (RL) has gained popularity in the realm of recommender systems due to its ability to optimize long-term rewards and guide users in discovering relevant content. However, the successful implementation of RL in recommender systems is challenging because of several factors, including the limited availability of online data for training on-policy methods. This scarcity requires expensive human interaction for online model training. Furthermore, the development of effective evaluation frameworks that accurately reflect the quality of models remains a fundamental challenge in recommender systems. To address these challenges, we propose a comprehensive framework for synthetic environments that simulate human behavior by harnessing the capabilities of large language models (LLMs). We complement our framework with in-depth ablation studies and demonstrate its effectiveness with experiments on movie and book recommendations. Using LLMs as synthetic users, this work introduces a modular and novel framework to train RL-based recommender systems. The software, including the RL environment, is publicly available on https://github.com/SUBER-Team/SUBER.

Algorithmic reasoning is a fundamental cognitive ability that plays a pivotal role in problem-solving and decision-making processes. Reinforcement Learning (RL) has demonstrated remarkable proficiency in tasks such as motor control, handling perceptual input, and managing stochastic environments. These advancements have been enabled in part by the availability of benchmarks. In this work we introduce PUZZLES, a benchmark based on Simon Tatham's Portable Puzzle Collection, aimed at fostering progress in algorithmic and logical reasoning in RL. PUZZLES contains 40 diverse logic puzzles of adjustable sizes and varying levels of complexity, providing detailed information on the strengths and generalization capabilities of RL agents. Furthermore, we evaluate various RL algorithms on PUZZLES, providing baseline comparisons and demonstrating the potential for future research. All the software, including the environment, is available at this https url.

Image datasets serve as the foundation for machine learning models in computer vision, significantly influencing model capabilities, performance, and biases alongside architectural considerations. Therefore, understanding the composition and distribution of these datasets has become increasingly crucial. To address the need for intuitive exploration of these datasets, we propose AEye, an extensible and scalable visualization tool tailored to image datasets. AEye utilizes a contrastively trained model to embed images into semantically meaningful high-dimensional representations, facilitating data clustering and organization. To visualize the high-dimensional representations, we project them onto a two-dimensional plane and arrange images in layers so users can seamlessly navigate and explore them interactively. AEye facilitates semantic search functionalities for both text and image queries, enabling users to search for content. We open-source the codebase for AEye, and provide a simple configuration to add datasets.

Music datasets play a crucial role in advancing research in machine learning for music. However, existing music datasets suffer from limited size, accessibility, and lack of audio resources. To address these shortcomings, we present DISCO-10M, a novel and extensive music dataset that surpasses the largest previously available music dataset by an order of magnitude. To ensure high-quality data, we implement a multi-stage filtering process. This process incorporates similarities based on textual descriptions and audio embeddings. Moreover, we provide precomputed CLAP embeddings alongside DISCO-10M, facilitating direct application on various downstream tasks. These embeddings enable efficient exploration of machine learning applications on the provided data. With DISCO-10M, we aim to democratize and facilitate new research to help advance the development of novel machine learning models for music: https://huggingface.co/DISCOX