Related papers: Associative-State Universal Transformers: Sparse R…

Robust Subspace Recovery (RoSuRe) algorithm was recently introduced as a principled and numerically efficient algorithm that unfolds underlying Unions of Subspaces (UoS) structure, present in the data. The union of Subspaces (UoS) is…

Large language models (LLMs) have demonstrated promising performance in both automatic speech recognition (ASR) and text-to-speech (TTS) systems, gradually becoming the mainstream approach. However, most current approaches address these…

This paper introduces the concept of abstracted model reduction: a framework to improve the tractability of structure-preserving methods for the complexity reduction of interconnected system models. To effectively reduce high-order,…

Transformer-based models have advanced the field of question answering, but multi-hop reasoning, where answers require combining evidence across multiple passages, remains difficult. This paper presents a comprehensive evaluation of…

Automatic speech recognition (ASR) systems developed in recent years have shown promising results with self-attention models (e.g., Transformer and Conformer), which are replacing conventional recurrent neural networks. Meanwhile, a…

Large language model (LLM) based listwise reranking has emerged as the dominant paradigm for achieving state-of-the-art ranking effectiveness in information retrieval. However, its reliance on feeding full passage texts into the LLM…

Transformers excel at in-context retrieval but suffer from quadratic complexity with sequence length, while State Space Models (SSMs) offer efficient linear-time processing but have limited retrieval capabilities. We investigate whether…

Ensemble learning remains a cornerstone of machine learning, with stacking used to integrate predictions from multiple base learners through a meta-model. However, deep stacking remains uncommon due to feature redundancy, complexity, and…

Large-scale vision-language pre-trained models have shown promising transferability to various downstream tasks. As the size of these foundation models and the number of downstream tasks grow, the standard full fine-tuning paradigm becomes…

Current unified multimodal models typically rely on discrete visual tokenizers to bridge the modality gap. However, discretization inevitably discards fine-grained semantic information, leading to suboptimal performance in visual…

Large language models deliver strong generative performance but at the cost of massive parameter counts, memory use, and decoding latency. Prior work has shown that pruning and structured sparsity can preserve accuracy under substantial…

We study learned memory tokens as a computational scratchpad for a single-block Universal Transformer with Adaptive Computation Time (ACT) on Sudoku-Extreme, a combinatorial reasoning benchmark. Memory tokens are empirically necessary: no…

Generative audio modeling has largely been fragmented into specialized tasks, text-to-speech (TTS), text-to-music (TTM), and text-to-audio (TTA), each operating under heterogeneous control paradigms. Unifying these modalities remains a…

Transformers encode structure in sequences via an expanding contextual history. However, their purely feedforward architecture fundamentally limits dynamic state tracking. State tracking -- the iterative updating of latent variables…

The punctuation restoration task aims to correctly punctuate the output transcriptions of automatic speech recognition systems. Previous punctuation models, either using text only or demanding the corresponding audio, tend to be constrained…

The unified streaming and non-streaming two-pass (U2) end-to-end model for speech recognition has shown great performance in terms of streaming capability, accuracy, real-time factor (RTF), and latency. In this paper, we present U2++, an…

UniSpeech has achieved superior performance in cross-lingual automatic speech recognition (ASR) by explicitly aligning latent representations to phoneme units using multi-task self-supervised learning. While the learned representations…

Suffix Array (SA) is a cardinal data structure in many pattern matching applications, including data compression, plagiarism detection and sequence alignment. However, as the volumes of data increase abruptly, the construction of SA is not…

We propose a novel high-fidelity expressive speech synthesis model, UniTTS, that learns and controls overlapping style attributes avoiding interference. UniTTS represents multiple style attributes in a single unified embedding space by the…

Persistent homology is a leading tool in topological data analysis (TDA). Many problems in TDA can be solved via homological -- and indeed, linear -- algebra. However, matrices in this domain are typically large, with rows and columns…