6 papers
Layer-wise Representation Dynamics: An Empirical Investigation Across Embedders and Base LLMs
Jingzhou Jiang, Yi Yang, Kar Yan Tam
Hidden states change substantially across the layers of modern language models, but most layer-wise analyses focus on one aspect of that change. We propose Layer-wise Representatio…
Bi-level Personalization for Federated Foundation Models: A Task-vector Aggregation Approach
Yiyuan Yang, Guodong Long, Qinghua Lu +2
Federated foundation models represent a new paradigm to jointly fine-tune pre-trained foundation models across clients. It is still a challenge to fine-tune foundation models for a…
Federated Low-Rank Adaptation for Foundation Models: A Survey
Yiyuan Yang, Guodong Long, Qinghua Lu +3
Effectively leveraging private datasets remains a significant challenge in developing foundation models. Federated Learning (FL) has recently emerged as a collaborative framework t…
Federated Adapter on Foundation Models: An Out-Of-Distribution Approach
Yiyuan Yang, Guodong Long, Tianyi Zhou +3
As foundation models gain prominence, Federated Foundation Models (FedFM) have emerged as a privacy-preserving approach to collaboratively fine-tune models in federated learning (F…
WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents
Siyu Zhou, Tianyi Zhou, Yijun Yang +4
Can we build accurate world models out of large language models (LLMs)? How can world models benefit LLM agents? The gap between the prior knowledge of LLMs and the specified envir…
WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents
Siyu Zhou, Tianyi Zhou, Yijun Yang +4
Can large language models (LLMs) directly serve as powerful world models for model-based agents? While the gaps between the prior knowledge of LLMs and the specified environment's…