Goto

Collaborating Authors

 Asia







Stepping on the Edge: Curvature A ware Learning Rate Tuners

Neural Information Processing Systems

(Liu and Nocedal, 1989). Similar efforts have been made for Polyak stepsizes (Berrada et al., 2020; Loizou et al., 2021), in addition to new methods which combine distance to optimality with online learning convergence bounds (Cutkosky et al., 2023; Classically-inspired methods, however, have generally struggled to gain traction in deep learning.



Glance and Focus: Memory Prompting for Multi-Event Video Question Answering Ziyi Bai

Neural Information Processing Systems

Video Question Answering (VideoQA) has emerged as a vital tool to evaluate agents' ability to understand human daily behaviors. Despite the recent success of large vision language models in many multi-modal tasks, complex situation reasoning over videos involving multiple human-object interaction events still remains challenging.



Video Dynamics Prior: An Internal Learning Approach for Robust Video Enhancements

Neural Information Processing Systems

In this paper, we present a novel robust framework for low-level vision tasks, including denoising, object removal, frame interpolation, and super-resolution, that does not require any external training data corpus.