activity
20232026
most citedFederated Sketching LoRA: A Flexible Framework for Heterogeneous Collaborative Fine-Tuning of LLMs

1 citations · 3 across the 13 of their papers we have counts for

collaborators

13 papers

cs.AI2026

Reasoning-Preserving Fine-Tuning of Post-RL LLMs with Null-Basis LoRA

Wenzhi Fang, Nicholas Tzou, Lazar Valkov +1

Reinforcement learning (RL)-based post-training has become an effective approach for eliciting reasoning capabilities in large language models (LLMs). However, adapting post-RL mod…

cs.AI2026

Iterative Critique-and-Routing Controller for Multi-Agent Systems with Heterogeneous LLMs

Wenzhi Fang, Liangqi Yuan, Guangchen Lan +2

Multi-agent large language model (LLM) systems often rely on a controller to coordinate a pool of heterogeneous models, yet existing controllers are typically limited to one-shot r…

cs.LG2026

PAAC: Privacy-Aware Agentic Device-Cloud Collaboration

Liangqi Yuan, Wenzhi Fang, Shiqiang Wang +1

Large language model (LLM) agents face a structural tension: cloud agents provide strong reasoning but expose user data, while on-device agents preserve privacy at the cost of over…

eess.SP2026

Large Language Models over Networks: Collaborative Intelligence under Resource Constraints

Liangqi Yuan, Wenzhi Fang, Shiqiang Wang +2

Large language models (LLMs) are transforming society, powering applications from smartphone assistants to autonomous driving. Yet cloud-based LLM services alone cannot serve a gro…

cs.LG2026

Self-Play Enhancement via Advantage-Weighted Refinement in Online Federated LLM Fine-Tuning with Real-Time Feedback

Seohyun Lee, Wenzhi Fang, Dong-Jun Han +2

Recent works have advanced feedback-based learning systems, whereby a foundation model is able to intake incoming feedback (e.g., a user) to self-improve, creating a self-loop syst…

cs.LG2026

Joint Continual Learning of Local Language Models and Cloud Offloading Decisions with Budget Constraints

Evan Chen, Wenzhi Fang, Shiqiang Wang +1

Locally deployed Small Language Models (SLMs) must continually support diverse tasks under strict memory and computation constraints, making selective reliance on cloud Large Langu…