6 papers
Bias Control and Injection for Multi-Agent Aggregation
Sungjae Lee, Soheil Abbasloo, Jabin Koo +1
Multi-agent reasoning with large language models (LLMs) raises a central question for collective decision-making: when agents disagree, whose decision should be trusted? Resolving…
Dynamic Expert Pruning for Multi-Agent Systems
Jabin Koo, Soheil Abbasloo, Sungjae Lee +1
Mixture-of-Experts (MoE) architectures scale language models efficiently by activating only a few experts per token, but the saving is confined to computation: every expert must st…
Federated Variational Preference Alignment with Gumbel-Softmax Prior for Personalized User Preferences
Jabin Koo, Hoyoung Kim, Minwoo Jang +1
Federated Learning (FL) offers a privacy-preserving pathway for aligning Large Language Models (LLMs); however, existing frameworks typically enforce a monolithic reward model, ine…
ChimeraLoRA: Multi-Head LoRA-Guided Synthetic Datasets
Hoyoung Kim, Minwoo Jang, Jabin Koo +2
Beyond general recognition tasks, specialized domains and fine-grained settings often encounter data scarcity, especially for tail classes. To obtain less biased and more reliable…
Making Models Unmergeable via Scaling-Sensitive Loss Landscape
Minwoo Jang, Hoyoung Kim, Jabin Koo +1
The rise of model hubs has made it easier to access reusable model components, making model merging a practical tool for combining capabilities. Yet, this modularity also creates a…
Towards Robust and Efficient Federated Low-Rank Adaptation with Heterogeneous Clients
Jabin Koo, Minwoo Jang, Jungseul Ok
Federated fine-tuning for Large Language Models (LLMs) faces significant challenges due to the heavy communication overhead of transmitting large model updates. Although Low Rank A…