Related papers: Time-Shifted Token Scheduling for Symbolic Music G…

We propose Composition Sampling, a simple but effective method to generate diverse outputs for conditional generation of higher quality compared to previous stochastic decoding strategies. It builds on recently proposed plan-based neural…

We present Text2midi-InferAlign, a novel technique for improving symbolic music generation at inference time. Our method leverages text-to-audio alignment and music structural alignment rewards during inference to encourage the generated…

The goal of this paper is to accelerate codec-based speech synthesis systems with minimum sacrifice to speech quality. We propose an enhanced inference method that allows for flexible trade-offs between speed and quality during inference…

The implementation difficulties of combining distribution matching (DM) and dematching (invDM) for probabilistic shaping (PS) with soft-decision forward error correction (FEC) coding can be relaxed by reverse concatenation, for which the…

Despite progress in controllable symbolic music generation, data scarcity remains a challenge for certain control modalities. Composer-style music generation is a prime example, as only a few pieces per composer are available, limiting the…

We propose task-adaptive tokenization as a way to adapt the generation pipeline to the specifics of a downstream task and enhance long-form generation in mental health. Inspired by insights from cognitive science, our task-adaptive…

Transformer-based models have shown strong performance in time-series forecasting by leveraging self-attention to model long-range temporal dependencies. However, their effectiveness depends critically on the quality and structure of input…

While music remains a challenging domain for generative models like Transformers, recent progress has been made by exploiting suitable musically-informed priors. One technique to leverage information about musical structure in Transformers…

Music generation models can produce high-fidelity coherent accompaniment given complete audio input, but are limited to editing and loop-based workflows. We study real-time audio-to-audio accompaniment: as a model hears an input audio…

Several real-world scenarios, such as remote control and sensing, are comprised of action and observation delays. The presence of delays degrades the performance of reinforcement learning (RL) algorithms, often to such an extent that…

Effective token compression remains a critical challenge for scaling models to handle increasingly complex and diverse datasets. A novel mechanism based on contextual reinforcement is introduced, dynamically adjusting token importance…

In this paper, we explore the tokenized representation of musical scores using the Transformer model to automatically generate musical scores. Thus far, sequence models have yielded fruitful results with note-level (MIDI-equivalent)…

We introduce new differentially private (DP) mechanisms for gradient-based machine learning (ML) with multiple passes (epochs) over a dataset, substantially improving the achievable privacy-utility-computation tradeoffs. We formalize the…

In deep learning research, many melody extraction models rely on redesigning neural network architectures to improve performance. In this paper, we propose an input feature modification and a training objective modification based on two…

Deep learning models generalize well to in-distribution data but struggle to generalize compositionally, i.e., to combine a set of learned primitives to solve more complex tasks. In sequence-to-sequence (seq2seq) learning, transformers are…

This work addresses the general problem of control synthesis for continuous-space, discrete-time stochastic systems with probabilistic guarantees via finite abstractions. While established methods exist, they often trade off accuracy for…

Tokenization is a key component of autoregressive (AR) generative models, converting raw data into more manageable units for modeling. Commonly, tokens describe local information, such as regions of pixels in images or word pieces in text,…

Recent progress in natural language processing has been adapted to the symbolic music modality. Language models, such as Transformers, have been used with symbolic music for a variety of tasks among which music generation, modeling or…

Self-supervised learning has been actively studied in time series domain recently, especially for masked reconstruction. Most of these methods follow the "Pre-training + Fine-tuning" paradigm in which a new decoder replaces the pre-trained…

Learning time-evolving objects such as multivariate time series and dynamic networks requires the development of novel knowledge representation mechanisms and neural network architectures, which allow for capturing implicit time-dependent…