Related papers: Where Do Flow Semantics Reside? A Protocol-Native …

Bioacoustic recognition requires fine-grained acoustic understanding to distinguish similar-sounding species. However, many large-scale data repositories such as iNaturalist are weakly annotated, often with only a single positive species…

Pretrained encoders for mathematical texts have achieved significant improvements on various tasks such as formula classification and information retrieval. Yet they remain limited in representing and capturing student strategies for entire…

Most image watermarking systems focus on robustness, capacity, and imperceptibility while treating the embedded payload as meaningless bits. This bit-centric view imposes a hard ceiling on capacity and prevents watermarks from carrying…

Graph masked autoencoders (GMAE) have emerged as a significant advancement in self-supervised pre-training for graph-structured data. Previous GMAE models primarily utilize a straightforward random masking strategy for nodes or edges during…

The performance of a deep learning model on a specific task and dataset depends heavily on its neural architecture, motivating considerable efforts to rapidly and accurately identify architectures suited to the target task and dataset. To…

In this paper we present a new approach to solve semi-supervised classification tasks for biomedical applications, involving a supervised autoencoder network. We create a network architecture that encodes labels into the latent space of an…

Deep generative models have made rapid progress in image, text, audio, and video generation, and are increasingly being applied to structured records. For tabular data, however, generative modeling remains difficult: a dataset may contain…

Masked Autoencoders (MAEs) achieve impressive performance in image classification tasks, yet the internal representations they learn remain less understood. This work started as an attempt to understand the strong downstream classification…

Recent advances in semi-supervised learning (SSL) demonstrate that a combination of consistency regularization and pseudo-labeling can effectively improve image classification accuracy in the low-data regime. Compared to classification,…

Cloud networks increasingly rely on machine learning based Network Intrusion Detection Systems to defend against evolving cyber threats. However, real-world deployments are challenged by limited labeled data, non-stationary traffic, and…

Language modeling on large-scale datasets leads to impressive performance gains on various downstream language tasks. The validation pre-training loss (or perplexity in autoregressive language modeling) is often used as the evaluation…

Representation learning stands as one of the critical machine learning techniques across various domains. Through the acquisition of high-quality features, pre-trained embeddings significantly reduce input space redundancy, benefiting…

Fast domain adaptation remains a fundamental challenge for deploying multi-agent systems across diverse environments in Vehicle-to-Everything (V2X) collaborative perception. Despite the success of Parameter-Efficient Fine-Tuning (PEFT) in…

Statistical decision algorithms are increasingly deployed in domains where ground-truth labels are hard to obtain, such as hiring, university admissions, and content moderation. In these settings, models are typically trained on historical…

Self-supervised learning (SSL) is a powerful paradigm for learning from unlabeled time-series data. However, popular methods such as masked autoencoders (MAEs) rely on reconstructing inputs from a fixed, predetermined masking ratio. Instead…

We propose a pre-training strategy called Multi-modal Multi-task Masked Autoencoders (MultiMAE). It differs from standard Masked Autoencoding in two key aspects: I) it can optionally accept additional modalities of information in the input…

Systems which incrementally create 3D semantic maps from image sequences must store and update representations of both geometry and semantic entities. However, while there has been much work on the correct formulation for geometrical…

The recently proposed Bayesian Flow Networks~(BFNs) show great potential in modeling parameter spaces, offering a unified strategy for handling continuous, discretized, and discrete data. However, BFNs cannot learn high-level semantic…

Semantic watermarking methods enable the direct integration of watermarks into the generation process of latent diffusion models by only modifying the initial latent noise. One line of approaches building on Gaussian Shading relies on…

Tabular data is the foundation of many applications in fields such as finance and healthcare. Although DNNs tailored for tabular data achieve competitive predictive performance, they are blackboxes with little interpretability. We introduce…