4 papers
Quality-Aware Cross-Model Computation Reuse
Jin Cheng, Xiangxiang Dai, Maoli Liu +3
An intermediate result computed by one model can be reused by other models to perform their tasks. Existing work mainly focuses on practical execution, leaving a theoretical gap in…
Steering Frozen LLMs: Adaptive Social Alignment via Online Prompt Routing
Zeyu Zhang, Xiangxiang Dai, Ziyi Han +2
Large language models (LLMs) are typically governed by post-training alignment (e.g., RLHF or DPO), which yields a largely static policy during deployment and inference. However, r…
HiLoRA: Adaptive Hierarchical LoRA Routing for Training-Free Domain Generalization
Ziyi Han, Huanyu Wang, Zeyu Zhang +3
Low-Rank Adaptation (LoRA) has emerged as a widely used technique for adapting large language models (LLMs) to new domains, due to its modular design and broad availability on plat…
Faster, Smaller, and Smarter: Task-Aware Expert Merging for Online MoE Inference
Ziyi Han, Xutong Liu, Ruiting Zhou +2
Sparse Mixture of Experts (SMoE) has become a preferred architecture for scaling Transformer capacity without increasing computational cost, as it activates only a small subset of…