37 citations · 53 across the 9 of their papers we have counts for
9 papers
ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning
Ruizhong Qiu, Hanqing Zeng, Yinglong Xia +15
Low-rank adapters (LoRAs) are a parameter-efficient finetuning technique that injects trainable low-rank matrices into pretrained models to adapt them to new tasks. Mixture-of-LoRA…
Can Graph Learning Improve Planning in LLM-based Agents?
Xixi Wu, Yifei Shen, Caihua Shan +8
Task planning in language agents is emerging as an important research topic alongside the development of large language models (LLMs). It aims to break down complex user requests i…
MAG-GNN: Reinforcement Learning Boosted Graph Neural Network
Lecheng Kong, Jiarui Feng, Hao Liu +3
While Graph Neural Networks (GNNs) recently became powerful tools in graph learning tasks, considerable efforts have been spent on improving GNNs' structural encoding ability. A pa…
One for All: Towards Training One Graph Model for All Classification Tasks
Hao Liu, Jiarui Feng, Lecheng Kong +4
Designing a single model to address multiple tasks has been a long-standing objective in artificial intelligence. Recently, large language models have demonstrated exceptional capa…
Distance-Restricted Folklore Weisfeiler-Leman GNNs with Provable Cycle Counting Power
Junru Zhou, Jiarui Feng, Xiyuan Wang +1
The ability of graph neural networks (GNNs) to count certain graph substructures, especially cycles, is important for the success of GNNs on a wide range of tasks. It has been rece…
Extending the Design Space of Graph Neural Networks by Rethinking Folklore Weisfeiler-Lehman
Jiarui Feng, Lecheng Kong, Hao Liu +4
Message passing neural networks (MPNNs) have emerged as the most popular framework of graph neural networks (GNNs) in recent years. However, their expressive power is limited by th…
A Visual Active Search Framework for Geospatial Exploration
Anindya Sarkar, Michael Lanier, Scott Alfeld +4
Many problems can be viewed as forms of geospatial search aided by aerial imagery, with examples ranging from detecting poaching activity to human trafficking. We model this class…
Reward Delay Attacks on Deep Reinforcement Learning
Anindya Sarkar, Jiarui Feng, Yevgeniy Vorobeychik +2
Most reinforcement learning algorithms implicitly assume strong synchrony. We present novel attacks targeting Q-learning that exploit a vulnerability entailed by this assumption by…
How Powerful are K-hop Message Passing Graph Neural Networks
Jiarui Feng, Yixin Chen, Fuhai Li +2
The most popular design paradigm for Graph Neural Networks (GNNs) is 1-hop message passing -- aggregating information from 1-hop neighbors repeatedly. However, the expressive power…