Related papers: PrismSSL: One Interface, Many Modalities; A Single…

We introduce PyKaldi2 speech recognition toolkit implemented based on Kaldi and PyTorch. While similar toolkits are available built on top of the two, a key feature of PyKaldi2 is sequence training with criteria such as MMI, sMBR and MPE.…

We here present SIMLR (Single-cell Interpretation via Multi-kernel LeaRning), an open-source tool that implements a novel framework to learn a sample-to-sample similarity measure from expression data observed for heterogenous samples. SIMLR…

We introduce PyTorchVideo, an open-source deep-learning library that provides a rich set of modular, efficient, and reproducible components for a variety of video understanding tasks, including classification, detection, self-supervised…

Due to limited supervised training data, large language models (LLMs) are typically pre-trained via a self-supervised "predict the next word" objective on a vast amount of unstructured text data. To make the resulting model useful to users,…

Simulation is a foundational tool for the analysis and testing of cyber-physical systems (CPS), underpinning activities such as algorithm development, runtime monitoring, and system verification. As CPS grow in complexity and scale,…

Semi-supervised Learning (SSL) has been proven vulnerable to out-of-distribution (OOD) samples in realistic large-scale unsupervised datasets due to over-confident pseudo-labeling OODs as in-distribution (ID). A key underlying problem is…

Self-supervised learning (SSL) methods targeting scene images have seen a rapid growth recently, and they mostly rely on either a dedicated dense matching mechanism or a costly unsupervised object discovery module. This paper shows that…

Multimodal large language models (MLLMs) achieve strong performance by jointly processing inputs from multiple modalities, such as vision, audio, and language. However, building such models or extending them to new modalities often requires…

Self-supervised learning (SSL) is a machine learning approach where the data itself provides supervision, eliminating the need for external labels. The model is forced to learn about the data structure or context by solving a pretext task.…

Recently, we see a new type of interfaces for programmers based on web technology. For example, JSFiddle, IPython Notebook and R-studio. Web technology enables cloud-based solutions, embedding in tutorial web pages, atractive rendering of…

Group conversations over videoconferencing are a complex social behavior. However, the subjective moments of negative experience, where the conversation loses fluidity or enjoyment remain understudied. These moments are infrequent in…

Three-dimensional (3D) point cloud analysis has become central to applications ranging from autonomous driving and robotics to forestry and ecological monitoring. Although numerous deep learning methods have been proposed for point cloud…

Although large-scale self-supervised learning (SSL) models like WavLM have achieved state-of-the-art performance in speech processing, their significant size impedes deployment on resource-constrained devices. While structured pruning is a…

Self-Supervised Learning (SSL) models have been successfully applied in various deep learning-based speech tasks, particularly those with a limited amount of data. However, the quality of SSL representations depends highly on the…

Reinforcement learning (RL) with verifiable rewards (RLVR) has demonstrated the great potential of enhancing the reasoning abilities in multimodal large language models (MLLMs). However, the reliance on language-centric priors and expensive…

Multi-party learning is an indispensable technique for improving the learning performance via integrating data from multiple parties. Unfortunately, directly integrating multi-party data would not meet the privacy preserving requirements.…

Self-supervised pre-trained audio networks have seen widespread adoption in real-world systems, particularly in multi-modal large language models. These networks are often employed in a frozen state, under the assumption that the SSL…

Sign Language Recognition (SLR) is a fast-growing field that aims to fill the communication gaps between the hearing-impaired and people without hearing loss. Existing solutions for Persian Sign Language (PSL) are limited to word-level…

In this work, we introduce a novel problem setup termed as Heterogeneous Semi-Supervised Learning (HSSL), which presents unique challenges by bridging the semi-supervised learning (SSL) task and the unsupervised domain adaptation (UDA)…

Hardware generation languages (HGLs) increase hardware design productivity by creating parameterized modules and test benches. Unfortunately, existing tools are not widely adopted due to several demerits, including limited support for…