Related papers: LLM-Guided Taxonomy and Hierarchical Uncertainty f…

Enabling Large Language Models (LLMs) to interact with 3D environments is challenging. Existing approaches extract point clouds either from ground truth (GT) geometry or 3D scenes reconstructed by auxiliary models. Text-image aligned 2D…

Understanding 3D point cloud models for learning purposes has become an imperative challenge for real-world identification such as autonomous driving systems. A wide variety of solutions using deep learning have been proposed for point…

Although the annotation paradigm based on Large Language Models (LLMs) has made significant breakthroughs in recent years, its actual deployment still has two core bottlenecks: first, the cost of calling commercial APIs in large-scale…

Active learning (AL) techniques reduce labeling costs for training neural machine translation (NMT) models by selecting smaller representative subsets from unlabeled data for annotation. Diversity sampling techniques select heterogeneous…

Object detection models typically rely on predefined categories, limiting their ability to identify novel objects in open-world scenarios. To overcome this constraint, we introduce ADAM: Autonomous Discovery and Annotation Model, a…

We present the first active learning tool for fine-grained 3D part labeling, a problem which challenges even the most advanced deep learning (DL) methods due to the significant structural variations among the small and intricate parts. For…

Adapting large language models (LLMs) to specific domains often faces a critical bottleneck: the scarcity of high-quality, human-curated data. While large volumes of unchecked data are readily available, indiscriminately using them for…

Point cloud segmentation is a fundamental task in 3D. Despite recent progress on point cloud segmentation with the power of deep networks, current deep learning methods based on the clean label assumptions may fail with noisy labels. Yet,…

Steering, or direct manipulation of internal activations to guide LLM responses toward specific semantic concepts, is emerging as a promising avenue for both understanding how semantic concepts are stored within LLMs and advancing LLM…

Point cloud semantic segmentation plays an essential role in autonomous driving, providing vital information about drivable surfaces and nearby objects that can aid higher level tasks such as path planning and collision avoidance. While…

The task of Novel Class Discovery (NCD) in semantic segmentation entails training a model able to accurately segment unlabelled (novel) classes, relying on the available supervision from annotated (base) classes. Although extensively…

Point cloud semantic segmentation is a crucial task in 3D scene understanding. Existing methods mainly focus on employing a large number of annotated labels for supervised semantic segmentation. Nonetheless, manually labeling such large…

With the rise of large-scale models trained on broad data, in-context learning has become a new learning paradigm that has demonstrated significant potential in natural language processing and computer vision tasks. Meanwhile, in-context…

Large Language Models (LLMs) have shown remarkable promise in reasoning and decision-making, yet their integration with Reinforcement Learning (RL) for complex robotic tasks remains underexplored. In this paper, we propose an LLM-guided…

Active learning (AL) accelerates scientific discovery by prioritizing the most informative experiments, but traditional machine learning (ML) models used in AL suffer from cold-start limitations and domain-specific feature engineering,…

3D Affordance detection is a challenging problem with broad applications on various robotic tasks. Existing methods typically formulate the detection paradigm as a label-based semantic segmentation task. This paradigm relies on predefined…

While pre-trained language model (PLM) fine-tuning has achieved strong performance in many NLP tasks, the fine-tuning stage can be still demanding in labeled data. Recent works have resorted to active fine-tuning to improve the label…

Prompt learning has become a prevalent strategy for adapting vision-language foundation models (VLMs) such as CLIP to downstream tasks. With the emergence of large language models (LLMs), recent studies have explored the potential of using…

Multi-level Hierarchical Classification (MLHC) tackles the challenge of categorizing items within a complex, multi-layered class structure. However, traditional MLHC classifiers often rely on a backbone model with independent output layers,…

We present a self-supervised learning approach for the semantic segmentation of lidar frames. Our method is used to train a deep point cloud segmentation architecture without any human annotation. The annotation process is automated with…