8 papers
Discrete Diffusion Models: A Unified Framework from Tokenization to Generation
Ye Yuan, Weien Li, Rui Song +20
Discrete denoising diffusion models (DDMs) have recently emerged as a compelling alternative to autoregressive (AR) modeling for discrete data, offering parallel generation and ite…
Depth Exploration for LLM Decoding
Weisi Yang, Zipeng Sun, Stephen Xia
Autoregressive LLM decoding evaluates every generated token through the full layer stack, even though many tokens become predictable at intermediate depths. Existing lossless depth…
Support-Proximity Augmented Diffusion Estimation for Offline Black-Box Optimization
Yonghan Yang, Ye Yuan, Zipeng Sun +5
Offline black-box optimization aims to discover novel designs with high property scores using only a static dataset, a task fundamentally challenged by the out-of-distribution (OOD…
Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization
Weixu Zhang, Ye Yuan, Changjiang Han +7
Large Language Models (LLMs) exhibit strong implicit personalization ability, yet most existing approaches treat this behavior as a black box, relying on prompt engineering or fine…
Beyond Message Passing: A Semantic View of Agent Communication Protocols
Dun Yuan, Fuyuan Lyu, Ye Yuan +11
Agent communication protocols are becoming critical infrastructure for large language model (LLM) systems that must use tools, coordinate with other agents, and operate across hete…
Training Diffusion Language Models for Black-Box Optimization
Zipeng Sun, Can Chen, Ye Yuan +4
We study offline black-box optimization (BBO), aiming to discover improved designs from an offline dataset of designs and labels, a problem common in robotics and DNA with limited…
Diffusion Large Language Models for Black-Box Optimization
Ye Yuan, Can, Chen +4
Offline black-box optimization (BBO) aims to find optimal designs based solely on an offline dataset of designs and their labels. Such scenarios frequently arise in domains like DN…
Optimizing User Profiles via Contextual Bandits for Retrieval-Augmented LLM Personalization
Linfeng Du, Ye Yuan, Zichen Zhao +8
Large language models (LLMs) excel at general-purpose tasks, yet adapting their responses to individual users remains challenging. Retrieval augmentation provides a lightweight alt…