Related papers: Halo: Learning Semantics-Aware Representations for…
Hierarchical Imitation Learning (HIL) is a promising approach for tackling long-horizon decision-making tasks. While it is a challenging task due to the lack of detailed supervisory labels for sub-goal learning, and reliance on hundreds to…
Continual learning (CL) enables models to adapt to new tasks and environments without forgetting previously learned knowledge. While current CL setups have ignored the relationship between labels in the past task and the new task with or…
The deployment of large language models' (LLMs) inference at the edge can facilitate prompt service responsiveness while protecting user privacy. However, it is critically challenged by the resource constraints of a single edge node.…
We introduce a hyperbolic neural network approach to pixel-level active learning for semantic segmentation. Analysis of the data statistics leads to a novel interpretation of the hyperbolic radius as an indicator of data scarcity. In HALO…
Pretraining neural networks with massive unlabeled datasets has become popular as it equips the deep models with a better prior to solve downstream tasks. However, this approach generally assumes that the downstream tasks have access to…
Deep learning models have achieved remarkable success across various domains, yet their learned representations and decision-making processes remain largely opaque and hard to interpret. This work introduces HOLE (Homological Observation of…
Learning self-supervised image representations has been broadly studied to boost various visual understanding tasks. Existing methods typically learn a single level of image semantics like pairwise semantic similarity or image clustering…
Large language models (LLMs) have significantly advanced natural language processing tasks, yet they are susceptible to generating inaccurate or unreliable responses, a phenomenon known as hallucination. In critical domains such as health…
Continual learning (CL) aims to empower models to learn new tasks without forgetting previously acquired knowledge. Most prior works concentrate on the techniques of architectures, replay data, regularization, \etc. However, the category…
Although active learning (AL) in segmentation tasks enables experts to annotate selected regions of interest (ROIs) instead of entire images, it remains highly challenging, labor-intensive, and cognitively demanding due to the blurry and…
Long-context question answering (QA) over lengthy documents is critical for applications such as financial analysis, legal review, and scientific research. Current approaches, such as processing entire documents via a single LLM call or…
Active learning selects the most informative samples to exploit limited annotation budgets. Existing work follows a cumbersome pipeline that repeats the time-consuming model training and batch data selection multiple times. In this paper,…
Multilingual speech processing requires understanding emotions, a task made difficult by limited labelled data. CLARA, minimizes reliance on labelled data, enhancing generalization across languages. It excels at fostering shared…
In this paper, we investigate the task of zero-shot human-object interaction (HOI) detection, a novel paradigm for identifying HOIs without the need for task-specific annotations. To address this challenging task, we employ CLIP, a…
Human-Object Interaction (HOI) detection is a challenging computer vision task that requires visual models to address the complex interactive relationship between humans and objects and predict HOI triplets. Despite the challenges posed by…
Information Extraction (IE) aims to extract structured information from heterogeneous sources. IE from natural language texts include sub-tasks such as Named Entity Recognition (NER), Relation Extraction (RE), and Event Extraction (EE).…
Information extraction (IE) systems aim to automatically extract structured information, such as named entities, relations between entities, and events, from unstructured texts. While most existing work addresses a particular IE task,…
Online Continual Learning (OCL) aims to learn from endless non\text{-}stationary data streams, yet most existing methods assume a flat label space and overlook the hierarchical organization of real\text{-}world concepts that evolves both…
Active learning aims to address the paucity of labeled data by finding the most informative samples. However, when applying to semantic segmentation, existing methods ignore the segmentation difficulty of different semantic areas, which…
Image retargeting aims to change the aspect-ratio of an image while maintaining its content and structure with less visual artifacts. Existing methods still generate many artifacts or fail to maintain original content or structure. To…