Microsoft at ICLR 2026

Improving Diffusion Models for Class-imbalanced Training Data via Capacity Manipulation

Feng Hong, Jiangchao Yao, Yifei Shen, Dongsheng Li, Ya Zhang, Yanfeng Wang

MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent

Hongli Yu, Tinghong Chen, Jiangtao Feng, Jiangjie Chen, Weinan Dai, Qiying Yu, Ya-Qin Zhang, Wei-Ying Ma, Jingjing Liu, Mingxuan Wang, Hao Zhou

Revela: Dense Retriever Learning via Language Modeling

Fengyu Cai, Tong Chen, Xinran Zhao, Sihao Chen, Hongming Zhang, Sherry Tongshuang Wu, Iryna Gurevych, Heinz Koeppl

EmotionThinker: Prosody-Aware Reinforcement Learning for Explainable Speech Emotion Reasoning

Dingdong Wang, Shujie Liu, Tianhua Zhang, Youjun Chen, Jinyu Li, Helen M. Meng

Token-Importance Guided Direct Preference Optimization

Ning Yang, Hai Lin, Yibo Liu, Baoliang Tian, Guoqing Liu, Haijun Zhang

Sequences of Logits Reveal the Low Rank Structure of Language Models

Noah Golowich, Allen Liu, Abhishek Shetty

LLMs Get Lost In Multi-Turn Conversation

Philippe Laban, Hiroaki Hayashi, Yingbo Zhou, Jennifer Neville

LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts

Siyuan Wang, Gaokai Zhang, L. Zhang, Ning Shang, Fan Yang, Dongyao Chen, Mao Yang

The Coverage Principle: How Pre-Training Enables Post-Training

Fan Chen, Audrey Huang, Noah Golowich, Sadhika Malladi, Adam Block, Jordan T. Ash, Akshay Krishnamurthy, Akshay Krishnamurthy, Dylan J. Foster

AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference

Shitong Duan, Xiaoyuan Yi, Peng Zhang, Dongkuan Xu, Jing Yao, Tun Lu, Ning Gu, Xing Xie

Actions Speak Louder than Prompts: A Large-Scale Study of LLMs for Graph Inference

Ben Finkelshtein, Silviu Cucerzan, Sujay Kumar Jauhar, Ryen W. White

VibeVoice: Expressive Podcast Generation with Next-Token Diffusion

Zhiliang Peng, Jianwei Yu, Wenhui Wang, Yaoyao Chang, Yutao Sun, Li Dong, Yi Zhu, Weijiang Xu, Hangbo Bao, Zehua Wang, Shaohan Huang, Yan Xia, Furu Wei

Quotient-Space Diffusion Model

Yixian Xu, Yusong Wang, Shengjie Luo, Kaiyuan Gao, Tianyu He, Di He, Chang Liu