Related papers: Align-Consistency: Improving Non-autoregressive an…

Many value-based deep reinforcement learning algorithms rely on target networks - lagged copies of the online network - to stabilize training. While effective, this mechanism introduces a fundamental stability-recency tradeoff: slower…

The recurrent neural network transducer (RNN-T) objective plays a major role in building today's best automatic speech recognition (ASR) systems for production. Similarly to the connectionist temporal classification (CTC) objective, the…

Multi-objective preference alignment in language models often encounters a challenging trade-off: optimizing for one human preference (e.g., helpfulness) frequently compromises others (e.g., harmlessness) due to the inherent conflicts…

The Abstraction and Reasoning Corpus (ARC) is designed to assess generalization beyond pattern matching, requiring models to infer symbolic rules from very few examples. In this work, we present a transformer-based system that advances ARC…

We present a simple and efficient auxiliary loss function for automatic speech recognition (ASR) based on the connectionist temporal classification (CTC) objective. The proposed objective, an intermediate CTC loss, is attached to an…

Reinforcement Learning from AI Feedback (RLAIF) relies on LLM judges as preference measurement instruments, yet these instruments are fundamentally limited by random measurement errors -- stochastic fluctuations that manifest as preference…

End-to-end Automatic Speech Recognition (ASR) systems based on neural networks have seen large improvements in recent years. The availability of large scale hand-labeled datasets and sufficient computing resources made it possible to train…

Signal Temporal Logic (STL) inference seeks to extract human-interpretable rules from time-series data, but existing methods lack formal confidence guarantees for the inferred rules. Conformal prediction (CP) is a technique that can provide…

We propose Attentive Regularization (AR), a method to constrain the activation maps of kernels in Convolutional Neural Networks (CNNs) to specific regions of interest (ROIs). Each kernel learns a location of specialization along with its…

Autoregressive sequence models achieve state-of-the-art performance in domains like machine translation. However, due to the autoregressive factorization nature, these models suffer from heavy latency during inference. Recently,…

As Large Language Models (LLMs) expand in capability and application scope, their trustworthiness becomes critical. A vital risk is intrinsic deception, wherein models strategically mislead users to achieve their own objectives. Existing…

Continual learning (CL) over non-stationary data streams remains one of the long-standing challenges in deep neural networks (DNNs) as they are prone to catastrophic forgetting. CL models can benefit from self-supervised pre-training as it…

Contrastive representation learning (CRL) underpins many modern foundation models. Despite recent theoretical progress, existing analyses suffer from several key limitations: (i) the statistical consistency of CRL remains poorly understood;…

Scores from traditional confidence classifiers (CCs) in automatic speech recognition (ASR) systems lack universal interpretation and vary with updates to the underlying confidence or acoustic models (AMs). In this work, we build…

Asynchronous and parallel implementation of standard reinforcement learning (RL) algorithms is a key enabler of the tremendous success of modern RL. Among many asynchronous RL algorithms, arguably the most popular and effective one is the…

We present a novel semi-supervised learning framework that intelligently leverages the consistency regularization between the model's predictions from two strongly-augmented views of an image, weighted by a confidence of pseudo-label,…

Uncertainty quantification is necessary for developers, physicians, and regulatory agencies to build trust in machine learning predictors and improve patient care. Beyond measuring uncertainty, it is crucial to express it in clinically…

Retinex-based low-light image enhancement benefits from separating reflectance and illumination, yet recent generative approaches often rely on iterative sampling and are difficult to deploy under strict latency budgets. Consistency models…

Accurate sentiment analysis of texts is crucial for a variety of applications, such as understanding customer feedback, monitoring market trends, and detecting public sentiment. However, manually annotating large sentiment corpora for…

End-to-end (E2E) automatic speech recognition (ASR) systems have revolutionized the field by integrating all components into a single neural network, with attention-based encoder-decoder models achieving state-of-the-art performance.…