Related papers: OASIS: Online Sample Selection for Continual Visua…
Online sampling-supported visual analytics is increasingly important, as it allows users to explore large datasets with acceptable approximate answers at interactive rates. However, existing online spatiotemporal sampling techniques are…
Supervised fine-tuning (SFT) is a commonly used technique to adapt large language models (LLMs) to downstream tasks. In practice, SFT on a full dataset is computationally expensive and sometimes suffers from overfitting or bias…
Datasets nowadays are generally constructed from multiple sources and using different synthetic techniques, making data de-noising and de-duplication crucial before being used for post-training. In this work, we propose to perform…
Researchers train neural simulators on uniformly sampled numerical simulation data. But under the same budget, does systematically sampled data provide the most effective information? A fundamental yet unformalized problem is how to sample…
Algorithm selection is commonly used to predict the best solver from a portfolio per per-instance. In many real scenarios, instances arrive in a stream: new instances become available over time, while the number of class labels can also…
Continual learning in online scenario aims to learn a sequence of new tasks from data stream using each data only once for training, which is more realistic than in offline mode assuming data from new task are all available. However, this…
The pervasive issue of bias in AI presents a significant challenge to painting classification, and is getting more serious as these systems become increasingly integrated into tasks like art curation and restoration. Biases, often arising…
Continual learning remains constrained by the need for repeated retraining, high computational costs, and the persistent challenge of forgetting. These factors significantly limit the applicability of continuous learning in real-world…
Continuous machine learning pipelines are common in industrial settings where models are periodically trained on data streams. Unfortunately, concept drifts may occur in data streams where the joint distribution of the data X and label y,…
Diffusion models have emerged as the dominant paradigm for high-quality image generation, yet their computational expense remains substantial due to iterative denoising. Classifier-Free Guidance (CFG) significantly enhances generation…
Fine-tuning large language models (LLMs) for specialized domains often necessitates a trade-off between acquiring domain expertise and retaining general reasoning capabilities, a phenomenon known as catastrophic forgetting. Existing…
Machine learning relies heavily on data, yet the continuous growth of real-world data poses challenges for efficient dataset construction and training. A fundamental yet unsolved question is: given our current model and data, does a new…
Maintaining predictive accuracy in non-stationary environments requires online model selection to adapt autonomously to unknown distribution shifts. However, existing tuning-free algorithms face a fundamental trade-off between robustness…
In this work, we introduce a novel method for solving the set inversion problem by formulating it as a binary classification problem. Aiming to develop a fast algorithm that can work effectively with high-dimensional and computationally…
Open-world object detection (OWOD) extends traditional object detection to identifying both known and unknown object, necessitating continuous model adaptation as new annotations emerge. Current approaches face significant limitations: 1)…
Open-World Instance Segmentation (OWIS) is an emerging research topic that aims to segment class-agnostic object instances from images. The mainstream approaches use a two-stage segmentation framework, which first locates the candidate…
As massive medical data become available with an increasing number of scans, expanding classes, and varying sources, prevalent training paradigms -- where AI is trained with multiple passes over fixed, finite datasets -- face significant…
Online Lifelong Learning (OLL) addresses the challenge of learning from continuous and non-stationary data streams. Existing online lifelong learning methods based on image classification models often require preset conditions such as the…
Modern recommendation systems frequently employ online learning to dynamically update their models with freshly collected data. The most commonly used optimizer for updating neural networks in these contexts is the Adam optimizer, which…
Class-incremental learning (CIL) aims to enable models to continuously learn new classes while overcoming catastrophic forgetting. The introduction of pre-trained models has brought new tuning paradigms to CIL. In this paper, we revisit…