Kaiwen Zhou
5 أوراق في مجموعة PaperMetrix
أوراق هذا المؤلف
-
Direct Acceleration of SAGA using Sampled Negative Momentum
2018 · arXiv (Cornell University)
Variance reduction is a simple and effective technique that accelerates convex (or non-convex) stochastic optimization. Among existing variance reduction methods, SVRG and SAGA adopt unbiased gradient estimators and are the most popular variance reduction methods …
-
FedVLN: Privacy-preserving Federated Vision-and-Language Navigation
2022 · arXiv (Cornell University)
Data privacy is a central problem for embodied agents that can perceive the environment, communicate with humans, and act in the real world. While helping humans complete tasks, the agent may observe and process sensitive …
-
On the Finite-Time Complexity and Practical Computation of Approximate Stationarity Concepts of Lipschitz Functions
2021 · arXiv (Cornell University)
We report a practical finite-time algorithmic scheme to compute approximately stationary points for nonconvex nonsmooth Lipschitz functions. In particular, we are interested in two kinds of approximate stationarity notions for nonconvex nonsmooth problems, i.e., Goldstein …
-
Norm-Range Partition: A Universal Catalyst for LSH based Maximum Inner Product Search (MIPS)
2018 · arXiv (Cornell University)
Recently, locality sensitive hashing (LSH) was shown to be effective for MIPS and several algorithms including $L_2$-ALSH, Sign-ALSH and Simple-LSH have been proposed. In this paper, we introduce the norm-range partition technique, which partitions the …
-
FALCON: Resolving Visual Redundancy and Fragmentation in High-Resolution Multimodal Large Language Models via Visual Registers
2025
The incorporation of high-resolution visual input equips multimodal large language models (MLLMs) with enhanced visual perception capabilities for real-world tasks. However, most existing high-resolution MLLMs rely on a cropping-based approach to process images, which leads …