2 papers
cs.LG2026
AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization
Wanqi Yang, Yuexiao Ma, Alexander Conzelmann +4
Mixture-of-Experts (MoE) architectures scale model capacity through sparse expert activation, but their deployment remains memory-bound because all expert weights must reside in me…
cs.LG2026
Decomposing and Composing: Towards Efficient Vision-Language Continual Learning via Rank-1 Expert Pool in a Single LoRA
Zhan Fa, Yue Duan, Jian Zhang +3
Continual learning (CL) in vision-language models (VLMs) faces significant challenges in improving task adaptation and avoiding catastrophic forgetting. Existing methods usually ha…