activity
20242026
collaborators

15 papers

cs.AI2026

Best Arm Identification in Generalized Linear Bandits via Hybrid Feedback

Qirun Zeng, Xuchuang Wang, Jiayi Shen +3

We study fixed-confidence best arm identification in generalized linear bandits under a hybrid feedback model: at each round, the learner may query either (i) absolute reward feedb…

cs.LG2026

Semantic Caching for Low-Cost LLM Serving: From Offline Learning to Online Adaptation

Xutong Liu, Baran Atalar, Xiangxiang Dai +5

Large Language Models (LLMs) are revolutionizing how users interact with information systems, yet their high inference cost poses serious scalability and sustainability challenges.…

cs.LG2026

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…

cs.LG2025

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…

cs.LG2025

Online Multi-LLM Selection via Contextual Bandits under Unstructured Context Evolution

Manhin Poon, XiangXiang Dai, Xutong Liu +3

Large language models (LLMs) exhibit diverse response behaviors, costs, and strengths, making it challenging to select the most suitable LLM for a given user query. We study the pr…

cs.LG2025

Offline Learning for Combinatorial Multi-armed Bandits

Xutong Liu, Xiangxiang Dai, Jinhang Zuo +4

The combinatorial multi-armed bandit (CMAB) is a fundamental sequential decision-making framework, extensively studied over the past decade. However, existing work primarily focuse…