Related papers: CoMBO: Conflict Mitigation via Branched Optimizati…
Class Incremental Learning (CIL) is challenging due to catastrophic forgetting. On top of that, Exemplar-free Class Incremental Learning is even more challenging due to forbidden access to previous task data. Recent exemplar-free CIL…
Class-incremental semantic segmentation (CSS) requires that a model learn to segment new classes without forgetting how to segment previous ones: this is typically achieved by distilling the current knowledge and incorporating the latest…
This paper investigates the problem of class-incremental object detection for agricultural applications where a model needs to learn new plant species and diseases incrementally without forgetting the previously learned ones. We adapt two…
Multi-Label Image Classification (MLIC) approaches usually exploit label correlations to achieve good performance. However, emphasizing correlation like co-occurrence may overlook discriminative features of the target itself and lead to…
A novel multiscale consensus-based optimization (CBO) algorithm for solving bi- and tri-level optimization problems is introduced. Existing CBO techniques are generalized by the proposed method through the employment of multiple interacting…
Prompt quality plays a central role in controlling the behavior, reliability, and reasoning performance of large language models (LLMs), particularly for smaller open-source instruction-tuned models that depend heavily on explicit…
In this paper, we study an emergent self-debiasing mechanisms against stereotypical content in Large Language Models (LLMs). Unlike traditional safety mechanisms that are primarily triggered by explicit input-level stimuli, self-debiasing…
Multi-objective Bayesian optimization has been widely adopted in scientific experiment design, including drug discovery and hyperparameter optimization. In practice, regulatory or safety concerns often impose additional thresholds on…
Deep models, e.g., CNNs and Vision Transformers, have achieved impressive achievements in many vision tasks in the closed world. However, novel classes emerge from time to time in our ever-changing world, requiring a learning system to…
Accurate and unambiguous guidelines are critical for large language model (LLM) based graders, yet manually crafting these prompts is often sub-optimal as LLMs can misinterpret expert guidelines or lack necessary domain specificity.…
Intelligent task placement and management of tasks in large-scale fog platforms is challenging due to the highly volatile nature of modern workload applications and sensitive user requirements of low energy consumption and response time.…
We study the new task of class-incremental Novel Class Discovery (class-iNCD), which refers to the problem of discovering novel categories in an unlabelled data set by leveraging a pre-trained model that has been trained on a labelled data…
Multi-label class-incremental learning (MLCIL) is essential for real-world multi-label applications, allowing models to learn new labels while retaining previously learned knowledge continuously. However, recent MLCIL approaches can only…
Consensus-based optimization (CBO) is a powerful and versatile zero-order multi-particle method designed to provably solve high-dimensional global optimization problems, including those that are genuinely nonconvex or nonsmooth. The method…
Incremental learning (IL) aims to overcome catastrophic forgetting of previous tasks while learning new ones. Existing IL methods make strong assumptions that the incoming task type will either only increases new classes or domains (i.e.…
Many text mining models are constructed by fine-tuning a large deep pre-trained language model (PLM) in downstream tasks. However, a significant challenge nowadays is maintaining performance when we use a lightweight model with limited…
Recent progresses on self-supervised 3D human action representation learning are largely attributed to contrastive learning. However, in conventional contrastive frameworks, the rich complementarity between different skeleton modalities…
Learning adaptive visuomotor policies for embodied agents remains a formidable challenge, particularly when facing cross-embodiment variations such as diverse sensor configurations and dynamic properties. Conventional learning approaches…
Process simulation is gaining attention for its ability to assess potential performance improvements and risks associated with business process changes. The existing literature presents various techniques, generally grounded in process…
Most recent few-shot learning approaches are based on meta-learning with episodic training. However, prior studies encounter two crucial problems: (1) \textit{the presence of inductive bias}, and (2) \textit{the occurrence of catastrophic…