1. Track: Poster Session 3 - ICML 2025
We study few-shot learning with PLMs from a different perspective: We first tune an autoregressive PLM on the few-shot samples and then use it as a generator.
Abstract:
2. Winners - UX Design Awards
Proudly presenting all UX Design Awards winners and nominees! Projects; Awards; Category; Year; Application; Industry. organizations.
The UX Design Awards are the global competition for excellent user experiences – honoring the best products and concepts across all industries twice per year.
3. [PDF] Emerging Safety Attack and Defense in Federated Instruction Tuning of ...
15 jun 2024 · There are 10 clients in total, with 7 benign and 3 malicious clients, and 3 are sampled for each round. Each client holds 500 data samples and ...
4. Yang song | Papers With Code
Papers by Yang song with links to code and results.
5. [PDF] FedLLM-Bench: Realistic Benchmarks for Federated Learning of Large ...
FedLLM involves four iterative steps: server-to-client model downloading, local model training, client-to-server model uploading, and global model aggregation.
6. Topology-aware Federated Learning in Edge Computing
Federated learning (FL) is a natural solution for massive user-owned devices in edge computing with distributed and private training data.
The ultra-low latency requirements of 5G/6G applications and privacy constraints call for distributed machine learning systems to be deployed at the edge. With its simple yet effective approach, fe...
7. Text-Conditioned Neural Network Diffusion for Train-Once-for-All ...
23 mei 2024 · We study a practical scenario termed train-once-for-all personalization, aiming to generate personalized models for diverse end-users and tasks using text ...
Zexi Li Zhejiang University zexi.li@zju.edu.cn &Lingzhi Gao∗ Zhejiang University lingzhigao@zju.edu.cn &Chao Wu Zhejiang University chao.wu@zju.edu.cn Equal contributions.Corresponding author.
8. [PDF] Federated Class-Continual Learning via Exemplar-Free Distillation
This paper focuses on an under-explored yet important problem: Federated Class-Continual Learning (FCCL), where new classes are dynamically added in ...
