HourVideo: 1-Hour Video-Language Understanding

no code implementations • 7 Nov 2024 • Keshigeyan Chandrasegaran, Agrim Gupta, Lea M. Hadzic, Taran Kota, Jimming He, Cristóbal Eyzaguirre, Zane Durante, Manling Li, Jiajun Wu, Li Fei-Fei

We present HourVideo, a benchmark dataset for hour-long video-language understanding.

Benchmarking counterfactual +3

When Do Universal Image Jailbreaks Transfer Between Vision-Language Models?

no code implementations • 21 Jul 2024 • Rylan Schaeffer, Dan Valentine, Luke Bailey, James Chua, Cristóbal Eyzaguirre, Zane Durante, Joe Benton, Brando Miranda, Henry Sleight, John Hughes, Rajashree Agrawal, Mrinank Sharma, Scott Emmons, Sanmi Koyejo, Ethan Perez

These results stand in stark contrast to existing evidence of universal and transferable text jailbreaks against language models and transferable adversarial attacks against image classifiers, suggesting that VLMs may be more robust to gradient-based transfer attacks.

Instruction Following Language Modelling +1

Revisiting the "Video" in Video-Language Understanding

1 code implementation • CVPR 2022 • Shyamal Buch, Cristóbal Eyzaguirre, Adrien Gaidon, Jiajun Wu, Li Fei-Fei, Juan Carlos Niebles

Building on recent progress in self-supervised image-language models, we revisit this question in the context of video and language tasks.

Benchmarking Question Answering +4

DACT-BERT: Differentiable Adaptive Computation Time for an Efficient BERT Inference

no code implementations • nlppower (ACL) 2022 • Cristóbal Eyzaguirre, Felipe del Río, Vladimir Araujo, Álvaro Soto

Large-scale pre-trained language models have shown remarkable results in diverse NLP applications.