7 citations · 15 across the 28 of their papers we have counts for
30 papers
Fisher-Informed Recalibration for Feedback-Based On-Policy Self-Distillation of LLMs
Seohyun Lee, Dong-Jun Han, Seyyedali Hosseinalipour +1
Feedback-based on-policy self-distillation has emerged as a promising approach for enabling foundation models, more specifically Large Language Models (LLMs), to learn from their o…
Bridging the Semantic-Utility Gap in Multimodal RAG via Generator-in-the-Loop Alignment
Zhan-Lun Chang, Dong-Jun Han, Seyyedali Hosseinalipour +2
Vision-language models (VLMs) augmented with retrieval-augmented generation (RAG) benefit from access to external evidence. However, standard retrievers and rerankers optimize for…
Gaze Attention: Query-Adaptive Visual Routing for Efficient Multimodal LLMs
Junha Song, Byeongho Heo, Geonmo Gu +3
When humans describe a visual scene, they do not process the entire image uniformly; instead, they selectively fixate on regions relevant to their intended description. In contrast…
Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning
Hyeonjin Kim, Hangyeol Jung, Heechan Yun +2
Unlearning specific concepts in text-to-image diffusion models has become increasingly important for preventing undesirable content generation. Among prior approaches, sparse autoe…
Iterative Critique-and-Routing Controller for Multi-Agent Systems with Heterogeneous LLMs
Wenzhi Fang, Liangqi Yuan, Guangchen Lan +2
Multi-agent large language model (LLM) systems often rely on a controller to coordinate a pool of heterogeneous models, yet existing controllers are typically limited to one-shot r…
Self-Play Enhancement via Advantage-Weighted Refinement in Online Federated LLM Fine-Tuning
Seohyun Lee, Wenzhi Fang, Dong-Jun Han +2
Recent works have advanced feedback-based learning systems, whereby a foundation model is able to intake incoming feedback (e.g., from a user) to self-improve, creating a self-loop…
Sporadic Gradient Tracking over Directed Graphs: A Theoretical Perspective on Decentralized Federated Learning
Shahryar Zehtabi, Dong-Jun Han, Seyyedali Hosseinalipour +1
Decentralized Federated Learning (DFL) enables clients with local data to collaborate in a peer-to-peer manner to train a generalized model. In this paper, we unify two branches of…
Next-Generation LLM for UAV: From Natural Language to Autonomous Flight
Liangqi Yuan, Chuhao Deng, Dong-Jun Han +3
With the rapid advancement of Large Language Models (LLMs), their capabilities in various automation domains, particularly Unmanned Aerial Vehicle (UAV) operations, have garnered i…
LLMAP: LLM-Assisted Multi-Objective Route Planning with User Preferences
Liangqi Yuan, Dong-Jun Han, Christopher G. Brinton +1
The rise of large language models (LLMs) has made natural language-driven route planning an emerging research area that encompasses rich user objectives. Current research exhibits…
TAP: Two-Stage Adaptive Personalization of Multi-Task and Multi-Modal Foundation Models in Federated Learning
Seohyun Lee, Wenzhi Fang, Dong-Jun Han +2
In federated learning (FL), local personalization of models has received significant attention, yet personalized fine-tuning of foundation models remains underexplored. In particul…
Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training
Wenzhi Fang, Dong-Jun Han, Liangqi Yuan +2
Device-cloud collaboration holds promise for deploying large language models (LLMs), leveraging lightweight on-device models for efficiency while relying on powerful cloud models f…
Decentralized Domain Generalization with Style Sharing: Formal Model and Convergence Analysis
Shahryar Zehtabi, Dong-Jun Han, Seyyedali Hosseinalipour +1
Much of federated learning (FL) focuses on settings where local dataset statistics remain the same between training and testing. However, this assumption often does not hold in pra…
Communication-Efficient and Differentially Private Vertical Federated Learning with Zeroth-Order Optimization
Jianing Zhang, Evan Chen, Dong-Jun Han +2
Vertical Federated Learning (VFL) enables collaborative model training across feature-partitioned devices, yet its reliance on device-server information exchange introduces signifi…
Device-Cloud Collaborative LLM Inference with Multi-Modal, Multi-Task, Multi-Turn Conversations
Liangqi Yuan, Dong-Jun Han, Shiqiang Wang +1
Compared to traditional machine learning models, recent large language models (LLMs) can exhibit multi-task-solving capabilities through multi-modal data sources and multi-turn con…
Differentially-Private Multi-Tier Federated Learning: A Formal Analysis and Evaluation
Evan Chen, Frank Po-Chen Lin, Dong-Jun Han +1
While federated learning (FL) eliminates the transmission of raw data over a network, it is still vulnerable to privacy breaches from the communicated model parameters. Differentia…
Federated Sketching LoRA: A Flexible Framework for Heterogeneous Collaborative Fine-Tuning of LLMs
Wenzhi Fang, Dong-Jun Han, Liangqi Yuan +2
Fine-tuning large language models (LLMs) on resource-constrained clients remains a challenging problem. Recent works have fused low-rank adaptation (LoRA) techniques with federated…
Using Diffusion Models as Generative Replay in Continual Federated Learning -- What will Happen?
Yongsheng Mei, Liangqi Yuan, Dong-Jun Han +3
Federated learning (FL) has become a cornerstone in decentralized learning, where, in many scenarios, the incoming data distribution will change dynamically over time, introducing…
Communication-Efficient Federated Learning under Dynamic Device Arrival and Departure: Convergence Analysis and Algorithm Design
Zhan-Lun Chang, Dong-Jun Han, Seyyedali Hosseinalipour +2
Most federated learning (FL) approaches assume a fixed device set. However, real-world scenarios often involve devices dynamically joining or leaving the system, driven by, e.g., u…
Hierarchical Federated Learning with Multi-Timescale Gradient Correction
Wenzhi Fang, Dong-Jun Han, Evan Chen +2
While traditional federated learning (FL) typically focuses on a star topology where clients are directly connected to a central server, real-world distributed systems often exhibi…
Unlocking the Potential of Model Calibration in Federated Learning
Yun-Wei Chu, Dong-Jun Han, Seyyedali Hosseinalipour +1
Over the past several years, various federated learning (FL) methodologies have been developed to improve model accuracy, a primary performance metric in machine learning. However,…
Orchestrating Federated Learning in Space-Air-Ground Integrated Networks: Adaptive Data Offloading and Seamless Handover
Dong-Jun Han, Wenzhi Fang, Seyyedali Hosseinalipour +2
Devices located in remote regions often lack coverage from well-developed terrestrial communication infrastructure. This not only prevents them from experiencing high quality commu…
Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence Analysis
Guangchen Lan, Dong-Jun Han, Abolfazl Hashemi +2
To improve the efficiency of reinforcement learning (RL), we propose a novel asynchronous federated reinforcement learning (FedRL) framework termed AFedPG, which constructs a globa…
Decentralized Sporadic Federated Learning: A Unified Algorithmic Framework with Convergence Guarantees
Shahryar Zehtabi, Dong-Jun Han, Rohit Parasnis +2
Decentralized federated learning (DFL) captures FL settings where both (i) model updates and (ii) model aggregations are exclusively carried out by the clients without a central se…
Rethinking the Starting Point: Collaborative Pre-Training for Federated Downstream Tasks
Yun-Wei Chu, Dong-Jun Han, Seyyedali Hosseinalipour +1
A few recent studies have demonstrated that leveraging centrally pre-trained models can offer advantageous initializations for federated learning (FL). However, existing pre-traini…