3 papers
cs.LG2026
AP-BMM: Approximating Capability-Cost Pareto Sets of LLMs via Asynchronous Prior-Guided Bayesian Model Merging
Kesheng Chen, Yamin Hu, Zhenqian Zhu +2
LLM services need to offer a family of models spanning different capability--cost trade-offs to accommodate diverse user preferences. Model merging offers a practical way to constr…
cs.CR2026
From Parameters to Feature Space: Task Arithmetic for Backdoor Mitigation in Model Merging
Zhenqian Zhu, Yamin Hu, Yiya Diao +3
Model merging (MM) has gained significant attention as a cost-effective approach to integrate multiple task-specific models into a unified model. However, recent work reveals that…
cs.AI2025
Nearest-Better Network for Visualizing and Analyzing Combinatorial Optimization Problems: A Unified Tool
Yiya Diao, Changhe Li, Sanyou Zeng +4
The Nearest-Better Network (NBN) is a powerful method to visualize sampled data for continuous optimization problems while preserving multiple landscape features. However, the calc…