Goto

Collaborating Authors

 Stony Brook





A Additional Results

Neural Information Processing Systems

The acronym dataset is a QA task that requires models to decode financial acronyms. The FinMA7B-full model achieved the highest ROUGE-1 score of 0.12 and the B.1 Why was the datasheet created? B.2 Has the dataset been used already? If so, where are the results so others can compare (e.g., links to published papers)? Y es, the dataset has already been used. It was employed in the FinLLM Share Task during the FinNLP-AgentScen Workshop at IJCAI 2024, known as the FinLLM Challenge.




Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models Ziyi Yin 1 Muchao Y e

Neural Information Processing Systems

Vision-Language (VL) pre-trained models have shown their superiority on many multimodal tasks. However, the adversarial robustness of such models has not been fully explored. Existing approaches mainly focus on exploring the adversarial robustness under the white-box setting, which is unrealistic. In this paper, we aim to investigate a new yet practical task to craft image and text perturbations using pre-trained VL models to attack black-box fine-tuned models on different downstream tasks.




Radio waves could help driverless cars see around corners

Popular Science

HoloRadar helps give the vehicles a more complete picture of their surroundings. Breakthroughs, discoveries, and DIY tips sent six days a week. In late January, an Alphabet-owned Waymo self-driving car was cruising near an elementary school in Santa Monica, California, when a young child suddenly darted into the street . Waymo's LiDAR sensors detected the student, who had just emerged from behind a parked SUV, but it was too late. Despite slamming on the brakes and slowing from 17 to six mph, the driverless car struck the child, knocking them to the pavement.