7 accepted papers
Continual learning (CL) empowers AI systems to progressively acquire knowledge from non-stationary data streams. However, catastrophic forgetting remains a critical challenge. In this work, we identify attention drift in Vision Transformers as a primary source of catastrophic forgetting, where the a
Large Language Models are prone to memorizing sensitive, copyrighted, or hazardous content, posing significant privacy and legal concerns. Retraining from scratch is computationally infeasible, whereas current unlearning methods exhibit unstable trade-offs between forgetting and utility, frequently…
Data-driven methods provide effective solutions for robot trajectory generation in dynamic environments. Many physical constraints exist in the real world, and understanding these constraints to generate feasible trajectories for kinematics or dynamics is highly demanding regarding the data quantity…
Large Language Models (LLMs), pre-trained on massive text corpora, exhibit remarkable human-level language understanding, reasoning, and decision-making abilities. However, they tend to memorize unwanted information, such as private or copyrighted content, raising significant privacy and legal conce
Ensuring accessible pedestrian navigation requires reasoning about both semantic and spatial aspects of complex urban scenes, a challenge that existing Large Vision-Language Models (LVLMs) struggle to meet. Although these models can describe visual content, their lack of explicit grounding leads to
A planner for autonomous vehicles must be capable of operating in diverse and complex real-world environments. However, learning-based planners often struggle with limited generalization due to the long-tail distribution in datasets. Moreover, the black-box nature of neural networks limits their int
Large language models signify a pivotal advancement in general artificial intelligence, exhibiting capabilities that exceed human performance in diverse tasks. Nevertheless, these models often lack expertise in specialized knowledge areas. To augment the performance of LLMs in downstream application…