most citedMemento: Fine-tuning LLM Agents without Fine-tuning LLMs

2 citations · 3 across the 6 of their papers we have counts for

collaborators

6 papers

cs.RO2025

PUB: A Plasma-Propelled Ultra-Quiet Blimp with Two-DOF Vector Thrusting

Zihan Wang

This study presents the design and control of a Plasma-propelled Ultra-silence Blimp (PUB), a novel aerial robot employing plasma vector propulsion for ultra-quiet flight without m…

cs.LG2025★ 2 cited

Memento: Fine-tuning LLM Agents without Fine-tuning LLMs

Huichi Zhou, Yihang Chen, Siyuan Guo +8

In this paper, we introduce a novel learning paradigm for Adaptive Large Language Model (LLM) agents that eliminates the need for fine-tuning the underlying LLMs. Existing approach…

cs.CL2025

Bridging Cognition and Emotion: Empathy-Driven Multimodal Misinformation Detection

Zihan Wang, Lu Yuan, Zhengxuan Zhang +1

In the digital era, social media has become a major conduit for information dissemination, yet it also facilitates the rapid spread of misinformation. Traditional misinformation de…

cs.AI2025★ 1 cited

OmniScience: A Domain-Specialized LLM for Scientific Reasoning and Discovery

Vignesh Prabhakar, Md Amirul Islam, Adam Atanas +8

Large Language Models (LLMs) have demonstrated remarkable potential in advancing scientific knowledge and addressing complex challenges. In this work, we introduce OmniScience, a s…

stat.ML2024

Reproduction of IVFS algorithm for high-dimensional topology preservation feature selection

Zihan Wang

Feature selection is a crucial technique for handling high-dimensional data. In unsupervised scenarios, many popular algorithms focus on preserving the original data structure. In…

stat.ML2024

Reproduction of scan B-statistic for kernel change-point detection algorithm

Zihan Wang

Change-point detection has garnered significant attention due to its broad range of applications, including epidemic disease outbreaks, social network evolution, image analysis, an…