Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Unlocking the Potential of Continual Model Merging: An ODE Perspective
Lihong Lin, Haidong Kang
Continual Model Merging (CMM) enables rapid customization of foundation models by sequentially incorporating task-adapted models without repeated retraining. However, existing merg…
cs.LG2025
Towards Training-free Automatic Proxy Discovery via Large Language Models for Mixed Precision Quantization
Haidong Kang, Jun Du, Guo Yu +1
Mixed-Precision Quantization (MPQ) liberates Deep Neural Networks (DNNs) from the Out-Of-Memory (OOM) bottleneck and has garnered increasing research attention. However, convention…