collaborators

6 papers

cs.AI2025

AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning

Zhenyu Pan, Yiting Zhang, Zhuo Liu +13

LLM-based multi-agent systems excel at planning, tool use, and role coordination, but their openness and interaction complexity also expose them to jailbreak, prompt-injection, and…

cs.AI2025

Evo-MARL: Co-Evolutionary Multi-Agent Reinforcement Learning for Internalized Safety

Zhenyu Pan, Yiting Zhang, Yutong Zhang +8

Multi-agent systems (MAS) built on multimodal large language models exhibit strong collaboration and performance. However, their growing openness and interaction complexity pose se…

cs.LG2025

Universal Approximation with Softmax Attention

Jerry Yao-Chieh Hu, Hude Liu, Hong-Yu Chen +2

We prove that with linear transformations, both (i) two-layer self-attention and (ii) one-layer self-attention followed by a softmax function are universal approximators for contin…

stat.ML2025

Transformers versus the EM Algorithm in Multi-class Clustering

Yihan He, Hong-Yu Chen, Yuan Cao +2

LLMs demonstrate significant inference capacities in complicated machine learning tasks, using the Transformer model as its backbone. Motivated by the limited understanding of such…

stat.ML2025

Learning Spectral Methods by Transformers

Yihan He, Yuan Cao, Hong-Yu Chen +3

Transformers demonstrate significant advantages as the building block of modern LLMs. In this work, we study the capacities of Transformers in performing unsupervised learning. We…

stat.ML2025

Transformers Simulate MLE for Sequence Generation in Bayesian Networks

Yuan Cao, Yihan He, Dennis Wu +3

Transformers have achieved significant success in various fields, notably excelling in tasks involving sequential data like natural language processing. Despite these achievements,…