robustness
Large Vision-Language Models (LVLMs) struggle with distractions, particularly in the presence of irrelevant visual or textual inputs. This paper introduces the Irrelevance Robust Visual Question Answering (IR-VQA) benchmark to systematically evaluate and mitigate this ``multimodal distractibility". IR-VQA targets three key paradigms: irrelevant visual contexts in image-independent questions, irrelevant textual contexts in image-dependent questions, and text-only distractions.
- Categories:
29 Views
Description
- Categories:
70 Views
Achieving robust path tracking is essential for efficiently operating autonomous driving systems, particularly in unpredictable environments. This paper introduces a novel path-tracking control methodology utilizing a variable second-order Sliding Mode Control (SMC) approach. The proposed control strategy addresses the challenges posed by uncertainties and disturbances by reconfiguring and expanding the state-space matrix of a kinematic bicycle model guaranteeing Lyapunov stability and convergence of the system.
- Categories:
35 Views
As one of the research directions at OLIVES Lab @ Georgia Tech, we focus on the robustness of data-driven algorithms under diverse challenging conditions where trained models can possibly be depolyed. To achieve this goal, we introduced a large-sacle (~1.72M frames) traffic sign detection video dataset (CURE-TSD) which is among the most comprehensive datasets with controlled synthetic challenging conditions. The video sequences in the
- Categories:
5425 Views
As one of the research directions at OLIVES Lab @ Georgia Tech, we focus on the robustness of data-driven algorithms under diverse challenging conditions where trained models can possibly be depolyed.
- Categories:
4210 Views