papers

Publications (9)

cs.NI2026

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…

cs.CL2025

Warmup Generations: A Task-Agnostic Approach for Guiding Sequence-to-Sequence Learning with Unsupervised Initial State Generation

Senyu Li, Zipeng Sun, Jiayi Wang +4

Traditional supervised fine-tuning (SFT) strategies for sequence-to-sequence tasks often train models to directly generate the target output. Recent work has shown that guiding mod…

cs.LG2026

Discrete Diffusion Models: A Unified Framework from Tokenization to Generation

Ye Yuan, Weien Li, Rui Song +19

The paper proposes a unified framework for discrete denoising diffusion models that ties together tokenization, vocabulary design, and generation methods, showing how existing appr…

#discrete diffusion models#tokenization#generative modeling#parallel generation
cs.LG2026

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…

cs.LG2026

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…

cs.CE2026

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…

cs.CL2026

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…

cs.CE2026

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…

cs.CL2026

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…