6 accepted papers
Systems such as video chatbots and navigation robots often depend on streaming image captioning to interpret visual inputs. Existing approaches typically employ large multimodal language models (MLLMs) for this purpose, but their substantial computational cost hinders practical application.This limi
A dominant assumption in Multimodal Language Model (MLLM) research is that its performance is largely inherited from the LLM backbone, given its immense parameter scale and remarkable capabilities. This has created a void in the understanding of the vision encoder, which determines 'how MLLMs perce…
Path planning in obstacle-dense environments is a challenging problem, particularly for robots with asymmetric rectangular footprints. To address this problem, we propose a novel collision-checking approach, called a Rotatable Area, which represents a range of heading angles where the robot can rota…
With the increasing popularity of masked autoencoders, self-supervised learning (SSL) in vision undertakes a similar trajectory as in NLP. Specifically, generative pretext tasks with the masked prediction have become a de facto standard SSL practice in NLP (e.g., BERT). By contrast, early attempts a…
This paper presents a simple yet effective approach that improves continual test-time adaptation (TTA) in a memory-efficient manner. TTA may primarily be conducted on edge devices with limited memory, so reducing memory is crucial but has been overlooked in previous TTA studies. In addition, long-te…
Prior to the deployment of robotic systems, pre-training the deep-recognition models on all potential visual cases is infeasible in practice. Hence, test-time adaptation (TTA) allows the model to adapt itself to novel environments and improve its performance during test time (i.e., lifelong adaptati