132 citations · 197 across the 17 of their papers we have counts for
18 papers
SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills
Yingtie Lei, Zhongwei Wan, Jiankun Zhang +13
Large language model (LLM) agents accumulate rich episodic trajectories while solving real-world tasks, but it remains unclear whether such experience can be distilled into reusabl…
Mamoda2.5: Enhancing Unified Multimodal Model with DiT-MoE
Yangming Shi, Shixiang Zhu, Tao Shen +14
We present Mamoda2.5, a unified AR-Diffusion framework that seamlessly integrates multimodal understanding and generation within a single architecture. To efficiently enhance the m…
Reconsidering LLM Uncertainty Estimation Methods in the Wild
Yavuz Bakman, Duygu Nur Yaldiz, Sungmin Kang +4
Large Language Model (LLM) Uncertainty Estimation (UE) methods have become a crucial tool for detecting hallucinations in recent years. While numerous UE methods have been proposed…
Enabling Weak Client Participation via On-device Knowledge Distillation in Heterogeneous Federated Learning
Jihyun Lim, Junhyuk Jo, Tuo Zhang +1
Online Knowledge Distillation (KD) is recently highlighted to train large models in Federated Learning (FL) environments. Many existing studies adopt the logit ensemble method to p…
Leveraging Uncertainty Estimation for Efficient LLM Routing
Tuo Zhang, Asal Mehradfar, Dimitrios Dimitriadis +1
Deploying large language models (LLMs) in edge-cloud environments requires an efficient routing strategy to balance cost and response quality. Traditional approaches prioritize eit…
ModalityMirror: Improving Audio Classification in Modality Heterogeneity Federated Learning with Multimodal Distillation
Tiantian Feng, Tuo Zhang, Salman Avestimehr +1
Multimodal Federated Learning frequently encounters challenges of client modality heterogeneity, leading to undesired performances for secondary modality in multimodal learning. It…
Embracing Federated Learning: Enabling Weak Client Participation via Partial Model Training
Sunwoo Lee, Tuo Zhang, Saurav Prakash +2
In Federated Learning (FL), clients may have weak devices that cannot train the full model or even hold it in their memory space. To implement large-scale FL applications, thus, it…
Creating a Lens of Chinese Culture: A Multimodal Dataset for Chinese Pun Rebus Art Understanding
Tuo Zhang, Tiantian Feng, Yibin Ni +7
Large vision-language models (VLMs) have demonstrated remarkable abilities in understanding everyday content. However, their performance in the domain of art, particularly cultural…
FedAIoT: A Federated Learning Benchmark for Artificial Intelligence of Things
Samiul Alam, Tuo Zhang, Tiantian Feng +8
There is a significant relevance of federated learning (FL) in the realm of Artificial Intelligence of Things (AIoT). However, most existing FL works do not use datasets collected…
FedMultimodal: A Benchmark For Multimodal Federated Learning
Tiantian Feng, Digbalay Bose, Tuo Zhang +6
Over the past few years, Federated Learning (FL) has become an emerging machine learning technique to tackle data privacy challenges through collaborative training. In the Federate…
GPT-FL: Generative Pre-trained Model-Assisted Federated Learning
Tuo Zhang, Tiantian Feng, Samiul Alam +5
In this work, we propose GPT-FL, a generative pre-trained model-assisted federated learning (FL) framework. At its core, GPT-FL leverages generative pre-trained models to generate…
TimelyFL: Heterogeneity-aware Asynchronous Federated Learning with Adaptive Partial Training
Tuo Zhang, Lei Gao, Sunwoo Lee +2
In cross-device Federated Learning (FL) environments, scaling synchronous FL methods is challenging as stragglers hinder the training process. Moreover, the availability of each cl…
Secure Federated Learning against Model Poisoning Attacks via Client Filtering
Duygu Nur Yaldiz, Tuo Zhang, Salman Avestimehr
Given the distributed nature, detecting and defending against the backdoor attack under federated learning (FL) systems is challenging. In this paper, we observe that the cosine si…
FedAudio: A Federated Learning Benchmark for Audio Tasks
Tuo Zhang, Tiantian Feng, Samiul Alam +4
Federated learning (FL) has gained substantial attention in recent years due to the data privacy concerns related to the pervasiveness of consumer devices that continuously collect…
Federated Learning for Internet of Things: Applications, Challenges, and Opportunities
Tuo Zhang, Lei Gao, Chaoyang He +3
Billions of IoT devices will be deployed in the near future, taking advantage of faster Internet speed and the possibility of orders of magnitude more endpoints brought by 5G/6G. W…
Layer-wise Adaptive Model Aggregation for Scalable Federated Learning
Sunwoo Lee, Tuo Zhang, Chaoyang He +1
In Federated Learning, a common approach for aggregating local models across clients is periodic averaging of the full model parameters. It is, however, known that different layers…
Federated Learning for Internet of Things: A Federated Learning Framework for On-device Anomaly Data Detection
Tuo Zhang, Chaoyang He, Tianhao Ma +3
Federated learning can be a promising solution for enabling IoT cybersecurity (i.e., anomaly detection in the IoT environment) while preserving data privacy and mitigating the high…
Mobility-Aware Smart Charging of Electric Bus Fleets
Ahmadreza Moradipari, Nathaniel Tucker, Tuo Zhang +2
We study the joint route assignment and charge scheduling problem of a transit system dispatcher operating a fleet of electric buses in order to maximize solar energy integration a…