相关论文: F-StrIPE: Fast Structure-Informed Positional Encod…

Fine-grained sparsity promises higher parametric capacity without proportional per-token compute, but often suffers from training instability, load balancing, and communication overhead. We introduce STEM (Scaling Transformers with…

Many music theoretical constructs (such as scale types, modes, cadences, and chord types) are defined in terms of pitch intervals---relative distances between pitches. Therefore, when computer models are employed in music tasks, it can be…

A great number of deep learning based models have been recently proposed for automatic music composition. Among these models, the Transformer stands out as a prominent approach for generating expressive classical piano performance with a…

Inducing latent tree structures from sequential data is an emerging trend in the NLP research landscape today, largely popularized by recent methods such as Gumbel LSTM and Ordered Neurons (ON-LSTM). This paper proposes FASTTREES, a new…

Characterizing the express power of the Transformer architecture is critical to understanding its capacity limits and scaling law. Recent works provide the circuit complexity bounds to Transformer-like architecture. On the other hand,…

At present, neural network-based models, including transformers, struggle to generate memorable and readily comprehensible music from unified and repetitive musical material due to a lack of understanding of musical structure. Consequently,…

This paper presents a generative AI model for automated music composition with LSTM networks that takes a novel approach at encoding musical information which is based on movement in music rather than absolute pitch. Melodies are encoded as…

How can neural networks perform so well on compositional tasks even though they lack explicit compositional representations? We use a novel analysis technique called ROLE to show that recurrent neural networks perform well on such tasks by…

Most music source separation systems require large collections of isolated sources for training, which can be difficult to obtain. In this work, we use musical scores, which are comparatively easy to obtain, as a weak label for training a…

This technical report presents a new paradigm for full-song symbolic music generation. Existing symbolic models operate on note-attribute tokens and suffer from extremely long sequences, limited context length, and weak support for…

This paper proposes a novel Transformer-based model for music score infilling, to generate a music passage that fills in the gap between given past and future contexts. While existing infilling approaches can generate a passage that…

The fidelity with which neural networks can now generate content such as music presents a scientific opportunity: these systems appear to have learned implicit theories of such content's structure through statistical learning alone. This…

We address the problem of robot guided assembly tasks, by using a learning-based approach to identify contact model parameters for known and novel parts. First, a Variational Autoencoder (VAE) is used to extract geometric features of…

Electroencephalography (EEG) is a widely used non-invasive technique for measuring brain activity in brain-computer interface (BCI) applications. Supervised EEG decoding models often struggle to generalize across tasks, subjects, and…

Rotary Positional Embedding (RoPE) is a widely adopted technique for encoding position in language models, which, while effective, causes performance breakdown when input length exceeds training length. Prior analyses assert (rightly) that…

The attention module, which is a crucial component in Transformer, cannot scale efficiently to long sequences due to its quadratic complexity. Many works focus on approximating the dot-then-exponentiate softmax function in the original…

Artificial intelligence (AI) has revolutionized software engineering (SE) by enhancing software development efficiency. The advent of pre-trained models (PTMs) leveraging transfer learning has significantly advanced AI for SE. However,…

Since most of music has repetitive structures from motifs to phrases, repeating musical ideas can be a basic operation for music composition. The basic block that we focus on is conceptualized as loops which are essential ingredients of…

The success of large pretrained Transformers is closely tied to tokenizers, which convert raw input into discrete symbols. Extending these models to graph-structured data remains a significant challenge. In this work, we introduce a graph…

The development of effective explainability tools for Transformers is a crucial pursuit in deep learning research. One of the most promising approaches in this domain is Layer-wise Relevance Propagation (LRP), which propagates relevance…