Search Results for author:
Found 11 papers, 3 papers with code
WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines
This benchmark includes a visual question answering (VQA) dataset with text-image pairs across 30 languages and dialects, spanning 9 language families and featuring over 1 million data points, making it the largest multicultural VQA benchmark to date.
RainbowPO: A Unified Framework for Combining Improvements in Preference Optimization
Recently, numerous preference optimization algorithms have been introduced as extensions to the Direct Preference Optimization (DPO) family.
LLM Surgery: Efficient Knowledge Unlearning and Editing in Large Language Models
Large language models (LLMs) have revolutionized various domains, yet their utility comes with significant challenges related to outdated or problematic knowledge embedded during pretraining.
Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey
Preference tuning is a crucial process for aligning deep generative models with human preferences.
Compressed-VFL: Communication-Efficient Learning with Vertically Partitioned Data
Our work provides the first theoretical analysis of the effect message compression has on distributed training over vertically partitioned data.
Cross-Silo Federated Learning for Multi-Tier Networks with Vertical and Horizontal Data Partitioning
Each silo contains a hub and a set of clients, with the silo's vertical data shard partitioned horizontally across its clients.
Multi-Tier Federated Learning for Vertically Partitioned Data
Each silo contains a hub and a set of clients, with the silo's vertical data shard partitioned horizontally across its clients.
Multi-Level Local SGD: Distributed SGD for Heterogeneous Hierarchical Networks
We propose Multi-Level Local SGD, a distributed stochastic gradient method for learning a smooth, non-convex objective in a multi-level communication network with heterogeneous workers.
Multi-Level Local SGD for Heterogeneous Hierarchical Networks
In our algorithm, sub-networks execute a distributed SGD algorithm, using a hub-and-spoke paradigm, and the hubs periodically average their models with neighboring hubs.
Privacy is What We Care About: Experimental Investigation of Federated Learning on Edge Devices
Federated Learning enables training of a general model through edge devices without sending raw data to the cloud.
EdgeBench: Benchmarking Edge Computing Platforms
The emerging trend of edge computing has led several cloud providers to release their own platforms for performing computation at the 'edge' of the network.
Networking and Internet Architecture Distributed, Parallel, and Cluster Computing
