17 accepted papers
Speculative decoding is widely used in accelerating large language model (LLM) inference. In this work, we focus on the online draft model selection problem in speculative decoding. We design an algorithm that provably competes with the best draft model in hindsight for each query in terms of eithe…
Large Language Models (LLMs) have demonstrated exceptional performance in natural language processing tasks, yet their massive size makes serving them inefficient and costly. Semi-structured pruning has emerged as an effective method for model acceleration, but existing approaches are suboptimal bec…
Connectionist Temporal Classification (CTC) loss is commonly used in sequence learning applications. For example, in Automatic Speech Recognition (ASR) task, the training data consists of pairs of audio (input sequence) and text (output label),without temporal alignment information. Standard CTC com…
In this work, we propose DiffWave, a versatile diffusion probabilistic model for conditional and unconditional waveform generation. The model is non-autoregressive, and converts the white noise signal into structured waveform through a Markov chain with a constant number of steps at synthesis. It is…
There are so many models in the literature that it is difficult for practitioners to decide which combinations are likely to be effective for a new task. This paper attempts to address this question by capturing relationships among checkpoints published on the web. We model the space of tasks as a G…
Several approaches have been proposed in recent literature to alleviate the long-tail problem, mainly in object classification tasks. In this paper, we make the first large-scale study concerning the task of Long-Tail Visual Relationship Recognition (LTVRR). LTVRR aims at improving the learning of s…
The geometric properties of contextual embedding spaces for deep language models such as BERT and ERNIE, have attracted considerable attention in recent years. Investigations on the contextual embeddings demonstrate a strong anisotropic space such that most of the vectors fall within a narrow cone,…
Language models (LM) have been widely deployed in modern ASR systems. The LM is often trained by minimizing its perplexity on speech transcript. However, few studies try to discriminate a "gold" reference against inferior hypotheses. In this work, we propose a large margin language model (LMLM). LML…
Multi-layer multi-head self-attention mechanism is widely applied in modern neural language models. Attention redundancy has been observed among attention heads but has not been deeply studied in the literature. Using BERT-base model as an example, this paper provides a comprehensive study on attent…
Deep neural networks have proved very successful on archetypal tasks for which large training sets are available, but when the training data are scarce, their performance suffers from overfitting. Many existing methods of reducing overfitting are data-independent. Data-dependent regularizations are…
We propose a Topic Compositional Neural Language Model (TCNLM), a novel method designed to simultaneously capture both the global semantic meaning and the local word-ordering structure in a document. The TCNLM learns the global semantic coherence of a document via a neural topic model, and the proba…
High dimensional data is modeled using low-rank subspaces, and the probability of misclassification is expressed in terms of the principal angles between subspaces. The form taken by this expression motivates the design of a new feature extraction method that enlarges inter-class separation, while p…
The Poisson Factor Analysis (PFA) is applied to recover signals from a Poisson compressive sensing system. Motivated by the recently developed compressive X-ray imaging system, Coded Aperture Coherent Scatter Spectral Imaging (CACSSI) [1], we propose a new Bayesian reconstruction algorithm. The prop…
This paper proposes a framework for learning features that are robust to data variation, which is particularly important when only a limited number of trainingsamples are available. The framework makes it possible to tradeoff the discriminative value of learned features against the generalization er…
Many recent efforts have been devoted to designing sophisticated deep learning structures, obtaining revolutionary results on benchmark datasets. The success of these deep learning methods mostly relies on an enormous volume of labeled training samples to learn a huge number of parameters in a netw…
A novel multi-scale dictionary based Bayesian reconstruction algorithm is proposed for compressive X-ray imaging, which encodes the material's spectrum by Poisson measurements. Inspired by recently developed compressive X-ray imaging systems [1], this work aims to recover the material's spectrum fro…
This paper introduces a new ESPRIT-based algorithm to estimate the direction-of-arrival of an arbitrary degree polynomial-phase signal with a single acoustic vector-sensor. The proposed time-invariant ESPRIT algorithm is based on a matrix-pencil pair derived from the time-delayed data-sets collected…