Related papers: Better Intermediates Improve CTC Inference

Connectionist Temporal Classification (CTC) based end-to-end speech recognition system usually need to incorporate an external language model by using WFST-based decoding in order to achieve promising results. This is more essential to…

Inference acceleration of large language models (LLMs) has been put forward in many application scenarios and speculative decoding has shown its advantage in addressing inference acceleration. Speculative decoding usually introduces a draft…

Although connectionist temporal classification (CTC) has the label context independence assumption, it can still implicitly learn a context-dependent internal language model (ILM) due to modern powerful encoders. In this work, we…

Neural predictive models have achieved remarkable performance improvements in various natural language processing tasks. However, most neural predictive models suffer from the lack of explainability of predictions, limiting their practical…

Diffusion models have demonstrated strong performance in time series forecasting, yet often suffer from semantic misalignment between generated trajectories and conditioning covariates, especially under complex or multimodal conditions. To…

Semi-supervised learning is an important and active topic of research in pattern recognition. For classification using linear discriminant analysis specifically, several semi-supervised variants have been proposed. Using any one of these…

Test-Time Scaling (TTS) enhances the reasoning capabilities of large language models by allocating additional inference compute to explore the solution space. However, existing parallel TTS methods typically keep branches isolated during…

We study the model selection problem in conditional average treatment effect (CATE) prediction. Unlike previous works on this topic, we focus on preserving the rank order of the performance of candidate CATE predictors to enable accurate…

Generating natural language explanations for recommendations has become increasingly important in recommender systems. Traditional approaches typically treat user reviews as ground truth for explanations and focus on improving review…

While reliable data-driven decision-making hinges on high-quality labeled data, the acquisition of quality labels often involves laborious human annotations or slow and expensive scientific measurements. Machine learning is becoming an…

Developing a unified multilingual model has long been a pursuit for machine translation. However, existing approaches suffer from performance degradation -- a single multilingual model is inferior to separately trained bilingual ones on…

The goal of optimization-based meta-learning is to find a single initialization shared across a distribution of tasks to speed up the process of learning new tasks. Conditional meta-learning seeks task-specific initialization to better…

An improved inference method for densely connected systems is presented. The approach is based on passing condensed messages between variables, representing macroscopic averages of microscopic messages. We extend previous work that showed…

In modern data analysis, it is common to use machine learning methods to predict outcomes on unlabeled datasets and then use these pseudo-outcomes in subsequent statistical inference. Inference in this setting is often called…

The presence of intermediate confounders, also called recanting witnesses, is a fundamental challenge to the investigation of causal mechanisms in mediation analysis, preventing the identification of natural path-specific effects. Proposed…

Predicting the chemical properties of compounds is crucial in discovering novel materials and drugs with specific desired characteristics. Recent significant advances in machine learning technologies have enabled automatic predictive…

We introduce a linguistically enhanced combination of pre-training methods for transformers. The pre-training objectives include POS-tagging, synset prediction based on semantic knowledge graphs, and parent prediction based on dependency…

Translate-test is a popular technique to improve the performance of multilingual language models. This approach works by translating the input into English using an external machine translation system, and running inference over the…

The paper describes the refinement algorithm for the Calculus of (Co)Inductive Constructions (CIC) implemented in the interactive theorem prover Matita. The refinement algorithm is in charge of giving a meaning to the terms, types and proof…

The inferential model (IM) framework provides valid prior-free probabilistic inference by focusing on predicting unobserved auxiliary variables. But, efficient IM-based inference can be challenging when the auxiliary variable is of higher…