5 papers
PersonaArena: Dynamic Simulation for Evaluating and Enhancing Persona-Level Role-Playing in Large Language Models
Wenlong Shi, Jianxun Lian, Mingqi Wu +5
Large language models (LLMs) increasingly serve as interactive social agents, yet their ability to maintain coherent and authentic persona-level role-playing remains limited, parti…
Toward Consistent World Models with Multi-Token Prediction and Latent Semantic Enhancement
Qimin Zhong, Hao Liao, Haiming Qin +4
Whether Large Language Models (LLMs) develop coherent internal world models remains a core debate. While conventional Next-Token Prediction (NTP) focuses on one-step-ahead supervis…
Generative Replica-Exchange: A Flow-based Framework for Accelerating Replica Exchange Simulations
Shengjie Huang, Sijie Yang, Jianqiao Yi +6
Replica exchange (REX) is one of the most widely used enhanced sampling methodologies, yet its efficiency is limited by the requirement for a large number of intermediate temperatu…
Exploring Loss Landscapes through the Lens of Spin Glass Theory
Hao Liao, Wei Zhang, Zhanyi Huang +5
In the past decade, significant strides in deep learning have led to numerous groundbreaking applications. Despite these advancements, the understanding of the high generalizabilit…
Aligning Large Language Models for Controllable Recommendations
Wensheng Lu, Jianxun Lian, Wei Zhang +4
Inspired by the exceptional general intelligence of Large Language Models (LLMs), researchers have begun to explore their application in pioneering the next generation of recommend…