Related papers: Stutter-Solver: End-to-end Multi-lingual Dysfluenc…

Diffusion large language models (dLLMs) offer capabilities beyond those of autoregressive (AR) LLMs, such as parallel decoding and random-order generation. However, realizing these benefits in practice is non-trivial, as dLLMs inherently…

Disfluent speech has been previously addressed from two main perspectives: the clinical perspective focusing on diagnostic, and the Natural Language Processing (NLP) perspective aiming at modeling these events and detect them for downstream…

The paper studies an implementation methodology for partial and disjunctive stable models where partiality and disjunctions are unfolded from a logic program so that an implementation of stable models for normal (disjunction-free) programs…

Text style transfer aims to alter the style of a sentence while preserving its content. Due to the lack of parallel corpora, most recent work focuses on unsupervised methods and often uses cycle construction to train models. Since cycle…

Recently, forecasting the crowd flows has become an important research topic, and plentiful technologies have achieved good performances. As we all know, the flow at a citywide level is in a mixed state with several basic patterns (e.g.,…

Recently, a few open-vocabulary methods have been proposed by employing a unified architecture to tackle generic segmentation and detection tasks. However, their performance still lags behind the task-specific models due to the conflict…

A major focus of recent research in spoken language understanding (SLU) has been on the end-to-end approach where a single model can predict intents directly from speech inputs without intermediate transcripts. However, this approach…

Flowcharts are typically presented as images, driving the trend of using vision-language models (VLMs) for end-to-end flowchart understanding. However, two key challenges arise: (i) Limited controllability--users have minimal influence over…

Diffusion Multi-modal Large Language Models (dMLLMs) have recently emerged as a novel architecture unifying image generation and understanding. However, developing effective and efficient Test-Time Scaling (TTS) methods to unlock their full…

Multiple human tracking is a fundamental problem for scene understanding. Although both accuracy and speed are required in real-world applications, recent tracking methods based on deep learning have focused on accuracy and require…

Many approaches have recently been proposed to detect irregular scene text and achieved promising results. However, their localization results may not well satisfy the following text recognition part mainly because of two reasons: 1)…

Distributed inference serves as a promising approach to enabling the inference of large language models (LLMs) at the network edge. It distributes the inference process to multiple devices to ensure that the LLMs can fit into the device…

Conventional spoken language understanding (SLU) consist of two stages, the first stage maps speech to text by automatic speech recognition (ASR), and the second stage maps text to intent by natural language understanding (NLU). End-to-end…

Spoken Language Understanding (SLU) models are a core component of voice assistants (VA), such as Alexa, Bixby, and Google Assistant. In this paper, we introduce a pipeline designed to extend SLU systems to new languages, utilizing Large…

End-to-end spoken language understanding (SLU) remains elusive even with current large pretrained language models on text and speech, especially in multilingual cases. Machine translation has been established as a powerful pretraining…

Multi-turn instruction following capability constitutes a core competency of large language models (LLMs) in real-world applications. Existing evaluation benchmarks predominantly focus on fine-grained constraint satisfaction and…

We study the problem of self-supervised 3D scene flow estimation from real large-scale raw point cloud sequences, which is crucial to various tasks like trajectory prediction or instance segmentation. In the absence of ground truth scene…

In an emergency room (ER) setting, stroke triage or screening is a common challenge. A quick CT is usually done instead of MRI due to MRI's slow throughput and high cost. Clinical tests are commonly referred to during the process, but the…

Deep learning is increasingly becoming a promising pathway to improving the accuracy of sub-grid scale (SGS) turbulence closure models for large eddy simulations (LES). We leverage the concept of differentiable turbulence, whereby an…

Unsupervised pixel-level video understanding remains challenging in real-world scenarios, where motion blur, occlusion, and fast object dynamics often cause temporal drift and flickering pseudo-labels.We propose VVitCutLER, an unsupervised…