Related papers: Training-Free Spectral Fingerprints of Voice Proce…

The introduction of pre-trained transformer-based contextualized word embeddings has led to considerable improvements in the accuracy of graph-based parsers for frameworks such as Universal Dependencies (UD). However, previous works differ…

We explore deep autoregressive Transformer models in language modeling for speech recognition. We focus on two aspects. First, we revisit Transformer model configurations specifically for language modeling. We show that well configured…

As large language models are deployed as autonomous agents with tool execution privileges, a critical assumption underpins their security architecture: that model errors are detectable at runtime. We present empirical evidence that this…

Machine learning methods are emerging as a universal paradigm for constructing correlative structure-property relationships in materials science based on multimodal characterization. However, this necessitates development of methods for…

The rapid progress seen in terms of large-scale generative AI is largely based on the attention mechanism. It is conversely non-trivial to conceive small-scale applications for which attention-based architectures outperform traditional…

Transformer architectures, and their attention mechanisms in particular, form the foundation of modern large language models. While transformer models are widely believed to operate in high-dimensional hidden spaces, we show that attention…

Language models based on the Transformer architecture achieve excellent results in many language-related tasks, such as text classification or sentiment analysis. However, despite the architecture of these models being well-defined, little…

Thanks to the latest deep learning algorithms, silent speech interfaces (SSI) are now able to synthesize intelligible speech from articulatory movement data under certain conditions. However, the resulting models are rather…

Transformers achieve state-of-the-art accuracy and robustness across many tasks, but an understanding of their inductive biases and how those biases differ from other neural network architectures remains elusive. In this work, we identify…

Transformers resist surgical control. Ablating an attention head identified as critical for capitalization produces minimal behavioral change because distributed redundancy compensates for damage. This Hydra effect renders interpretability…

Transformers have achieved promising results on a variety of tasks. However, the quadratic complexity in self-attention computation has limited the applications, especially in low-resource settings and mobile or edge devices. Existing works…

Cross-attention is the primary interface through which text conditions latent diffusion models, yet its step-wise multi-resolution dynamics remain under-characterized, limiting principled training-free control. We cast diffusion…

Semantic associations such as the link between "bird" and "flew" are foundational for language modeling as they enable models to go beyond memorization and instead generalize and generate coherent text. Understanding how these associations…

The Radio frequency (RF) fingerprinting technique makes highly secure device authentication possible for future networks by exploiting hardware imperfections introduced during manufacturing. Although this technique has received considerable…

Understanding the underlying relationship between tongue and oropharyngeal muscle deformation seen in tagged-MRI and intelligible speech plays an important role in advancing speech motor control theories and treatment of speech…

Transformers face quadratic complexity and memory issues with long sequences, prompting the adoption of linear attention mechanisms using fixed-size hidden states. However, linear models often suffer from limited recall performance, leading…

Anomalies in multivariate time series often arise from temporal context and cross-channel coordination rather than isolated outliers. We present Pi-Transformer (Prior-Informed Transformer), a transformer with two attention pathways:…

The field of natural language processing has reached breakthroughs with the advent of transformers. They have remained state-of-the-art since then, and there also has been much research in analyzing, interpreting, and evaluating the…

This paper reveals that large language models (LLMs), despite being trained solely on textual data, are surprisingly strong encoders for purely visual tasks in the absence of language. Even more intriguingly, this can be achieved by a…

Architectural obfuscation - e.g., permuting hidden-state tensors, linearly transforming embedding tables, or remapping tokens - has recently gained traction as a lightweight substitute for heavyweight cryptography in privacy-preserving…