Microsoft at ICML 2026

Benchmarking at the Edge of Comprehension

Samuele Marro, Jialin Yu, Emanuele La Malfa, Oishi Deb, Jiawei Li, Yibo Yang, Ebey Abraham, Sunando Sengupta, Eric Sommerlade, Michael Wooldridge, Philip Torr

FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications

Kieran Didi, Sarah Alamdari, Alex Lu, Bruce Wittmann, Kadina E. Johnston, Ava P. Amini, Ali Madani, Maya Czeneszew, Christian Dallago, Kevin Kaichuang Yang

Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning

Zhaoyang Wang, Canwen Xu, Boyi Liu, Yite Wang, Siwei Han, Zhewei Yao, Huaxiu Yao, Yuxiong He

Closing the Loop: Universal Repository Representation with RPG-Encoder

Jane Luo, Chengyu Yin, Xin Zhang, Qingtao Li, Steven Liu, Yiming Huang, Jie Wu, Hao Liu, Yangyu Huang, Yu Kang, Fangkai Yang, Ying Xin, Scarlett Li

h1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement Learning

S. Motwani, Alesia Ivanova, Ziyang Cai, Philip Torr, Riashat Islam, Shital Shah, Christian Schröder de Witt, Charles London

Kuramoto Oscillatory Phase Encoding: Neuro-inspired Synchronization for Improved Learning Efficiency

Mingqing Xiao, Yansen Wang, Dongqi Han, Caihua Shan, Dongsheng Li

Learning GUI Grounding with Spatial Reasoning from Visual Feedback

Yu Zhao, Wei-Ning Chen, Huseyin Inan, Samuel Kessler, Lu Wang, Lukas Wutschitz, Fangkai Yang, Chaoyun Zhang, Pasquale Minervini, Saravan Rajmohan, Robert Sim

Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity

Menglin Xia, Xuchao Zhang, Shantanu Dixit, Paramaguru Harimurugan, Rujia Wang, Victor Ruehle, Robert Sim, Chetan Bansal, Saravan Rajmohan

Diff-MN: Diffusion Parameterized MoE-NCDE for Continuous Time Series Generation with Irregular Observations

Xu Zhang, Junwei Deng, Chang Xu, Hao Li, Jiang Bian

Moving Beyond Sparse Grounding with Complete Screen Parsing Supervision

A. Said Gurbuz, Sunghwan Hong, Ahmed Nassar, Marc Pollefeys, Peter Staar

Privacy Amplification in Differentially Private Zeroth-Order Optimization with Hidden States

Eli Chien, Wei-Ning Chen, Pan Li

Private Learning with Public Feature Conditioning

Shuli Jiang, Walid Krichene, Nicolas Mayoraz

Proact-VL: A Proactive VideoLLM for Real-Time AI Companions

Weicai Yan, Yuhong Dai, Qimu Ran, Haodong Li, Wang Lin, Haodong Liao, Xing Xie, Tao Jin, Jianxun Lian

RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents

Jialiang Zhu, Gongrui Zhang, Xiaolong Ma, Lin Xu, Miaosen Zhang, Ruiqi Yang, Song Wang, Kai Qiu, Zhirong Wu, Qi Dai, Rui Ma, Bei Liu, Yifan Yang, Chong Luo, Zhengyuan Yang, Linjie Li, Lijuan Wang, Weizhu Chen, Xin Geng, Baining Guo

TestExplora: Benchmarking LLMs for Proactive Bug Discovery via Repository-Level Test Generation

Steven Liu, Jane Luo, Xin Zhang, Aofan Liu, Hao Liu, J. Wu, Ziyang Huang, Yangyu Huang, Yu Kang, Scarlett Li

Test-Time Learning of Causal Structure from Interventional Data

Wei Chen, Rui Ding, Bojun Huang, Yang Zhang, Qiang Fu, Yuxuan Liang, Han Shi, Dongmei Zhang

Video-in-the-Loop: Span-Grounded Long Video QA with Interleaved Reasoning

Chendong Wang, Donglin Bai, Yifan Yang, Xiao Jin, Anlan Zhang, Rui Wang, Shiqi Jiang, Yuqing Yang, Hao Wu, Qi Dai, Chong Luo, Ting Cao, Lili Qiu, Suman Banerjee

Differentially Private Synthetic Data via APIs 4: Tabular Data

Toan Tran, Arturs Backurs, Zinan Lin, Victor Reis, Li Xiong, Sergey Yekhanin

BlueCodeAgent: A Blue Teaming Agent Enabled by Automated Red Teaming for CodeGen AI

Chengquan Guo, Yuzhou Nie, Chulin Xie, Zinan Lin, Wenbo Guo, Bo Li

Foundation VAEs for 3D CT Reconstruction, Augmentation, and Generation

Qi Chen, Shuhan Ding, Yu Gu, Ning Liu, Jiang Bian, Alan L. Yuille, Zongwei Zhou, Jingjing Fu

FT-Dojo: Towards Autonomous LLM Fine-Tuning with Language Agents

Qizheng Li, Yifei Zhang, Xiao Yang, Xu Yang, Zhuo Wang, Weiqing Liu, Jiang Bian

Learning Sparse Visual Representations via Spatial-Semantic Factorization

Theodore Zhao, Sid Kiblawi, Jianwei Yang, Naoto Usuyama, Reuben Tan, Noel Codella, Tristan Naumann, Hoifung Poon, Mu-Hsin Wei

NorMuon: Making Muon more efficient and scalable

Zichong Li, Liming Liu, Chen Liang, Weizhu Chen, Tuo Zhao

Position: Beyond Reasoning Zombies — AI Reasoning Requires Process Validity

Rachel Lawrence, Jacqueline Maasch

Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methods

Michal Moshkovitz, Suraj Srinivas, Lesia Semenova, Nave Frost, Cyrus Rashtchian, Valentyn Boreiko, Shichang Zhang, Himabindu Lakkaraju, Cynthia Rudin, Jennifer Wortman Vaughan

Position: Web Agents Should Use Typed Actions Instead of Click-Based Browsing

Linxi Jiang, Rui Xi, Zhijie Liu, Shuo Chen, Zhiqiang Lin, Suman Nath

Predicting evolutionary rate as a pretraining task improves genome language model representations

Micaela Elisa Consens, Kevin Kaichuang Yang, Jimmy Hall, Ashley Conard, Bo Wang, Lorin Crawford, Alan M. Moses, Alex Lu

World-R1: Reinforcing 3D Constraints for Text-to-Video Generation

Weijie Wang, Xiaoxuan He, Youping Gu, Yifan Yang, Zeyu Zhang, Yefei He, Yanbo Ding, Xirui Hu, Donny Y. Chen, Zhiyuan He, Yuqing Yang, Bohan Zhuang

Position: Beyond Prediction: Toward Verifiable Physiological Waveform Reasoning with Foundation Models and Agentic LLMs

Xiaoda Wang, Ching Chang, Defu Cao, Kaiqiao Han, Fang Sun, Yue Huang, Minxiao Wang, Chang Xu, Xiao Luo, Runze Yan, Xiangliang Zhang, Xiao Hu, Yan Liu, Yizhou Sun, Wei Wang, Carl Yang

Euclean: Automated Geometry Problem Formalization with Unified Verification in Lean

Linbin Tang, Jingyan You, Zilin Kang, Hanzhang Liu, Sophia Zhang, Zenan Li, Chenrui Cao, Liangcheng Song, Jiaao Wu, Xian Zhang, Fan Yang

Contextual Slate GLM Bandits with Limited Adaptivity

Tanmay Goyal, Sukruta Midigeshi, Gaurav Sinha

Controlled LLM Training on Spectral Sphere

Tian Xie, Haoming Luo, Haoyu Tang, Yiwen Hu, Jason Klein Liu, Qingnan Ren, Yang Wang, Wayne Xin Zhao, Rui Yan, Bing Su, Chong Luo, Baining Guo

Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding

Hee Suk Yoon, Eunseop Yoon, Jaehyun Jang, Soohwan Eom, Jiajing Hong, M. Hasegawa-Johnson, Qi Dai, Chong Luo, C. Yoo

Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook

Jaehyeok Lee, Xiaoyuan Yi, Jingtao Yao, Hyunjin Hwang, Roy Ka-Wei Lee, Xing Xie, Jinyeong Bak

HOBIT: Hardness Optimized Batch Sampling for InfoNCE Training

Himanshu Dutta, Lokesh Nagalapatti, Yashoteja Prabhu

MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety

Jialin Song, Xiaodong Liu, Weiwei Yang, Wuyang Chen, Mingqian Feng, Xuekai Zhu, Jianfeng Gao

MVP-LAM: Learning Action-Centric Latent Action via Cross-Viewpoint Reconstruction

Jung Min Lee, Dohyeok Lee, Seokhun Ju, Taehyun Cho, Jin Woo Koo, Li Zhao, Sangwoo Hong, Jungwoo Lee

Position: Towards Responsible Evaluation for Text-to-Speech

Yifan Yang, Hui Wang, Bing Han, Shujie Liu, Jinyu Li, Yong Qin, Xie Chen

Reasoning about Reasoning: BAPO Bounds on Chain-of-Thought Token Complexity in LLMs

Kiran Tomlinson, Tobias Schnabel, Adith Swaminathan, Jennifer Neville

ThetaEvolve: Test-time Learning on Open Problems

Yiping Wang, Shao-Rong Su, Zhiyuan Zeng, Eva Xu, Liliang Ren, Xinyu Yang, Zeying Huang, Xuehai He, Luyao Ma, Baolin Peng, Hao Cheng, Pengcheng He, Weizhu Chen, Shuohang Wang, Simon Shaolei Du, Yelong Shen

RAGEN-2: Reasoning Collapse in Agentic RL

Zihan Wang, Chi Gui, Xing Jin, Qineng Wang, Licheng Liu, Kangrui Wang, Shiqi Chen, Linjie Li, Zhengyuan Yang, Pingyue Zhang, Yiping Lu, Jiajun Wu, Fei-Fei Li, Lijuan Wang, Yejin Choi, Manling Li

Unlocking Zero-Shot Geospatial Reasoning via Indirect Rewards

Chenhui Xu, Fuxun Yu, Mike Bianco, Jacob Kovarskiy, Raphael Tang, Qi Zhang, Zirui Xu, William Levine, Brandon Dubbs, Heming Liao, C. Burgess, Suvam Bag, Jay Patravali, Rupanjali Kukal, Mikael Figueroa, Rishi Madhok, Nikolaos Karianakis, Jinjun Xiong

WildCat: Near-Linear Attention in Theory and Practice

Tobias Schröder, Lester Mackey

Towards Functional Correctness of Large Code Models with Selective Generation

J. Jeong, Taesoo Kim, Sangdon Park

Bandit Social Leaning Dynamics with Exploration Episodes

Kiarash Banihashem, Natalie Collina, Aleksandrs Slivkins

Coevolutionary Continuous Discrete Diffusion: Make Your Diffusion Language Model a Latent Reasoner

Cai Zhou, Chenxiao Yang, Yi Hu, Chenyu Wang, Chubin Zhang, Muhan Zhang, Lester Mackey, Tommi Jaakkola, Stephen Bates, Dinghuai Zhang

Distributional Alignment Games for Answer-Level Fine-Tuning

M. Mohri, Jon Schneider, Yifan Wu

Linguistic properties and model scale in brain encoding: from small to compressed language models

Subba Reddy Oota, Vijay Rowtula, Satya Sai Srinath Namburi, Khushbu Pahwa, Anant Khandelwal, Manish Gupta, Tanmoy Chakraborty, Bapi S. Raju

MoLoRA: Composable Specialization via Per-Token Adapter Routing

Shrey Shah, Justin Wagle

Pull Requests as a Training Signal for Repo-Level Code Editing

Qinglin Zhu, Tianyu Chen, Shuai Lu, Lei Ji, Runcong Zhao, Murong Ma, Xiangxiang Dai, Yulan He, Lin Gui, Peng Cheng, Yeyun Gong

Temporal Preference Optimization for Unsupervised Retrieval

HyunJin Kim, Jaejun Shim, Young Jin Kim, JinYeong Bak

CAReDiO: Cultural Alignment via Representativeness and Distinctiveness Guided Data Optimization

Jing Yao, Xiaoyuan Yi, Jindong Wang, Zhicheng Dou, Xing Xie

SG2Loc: Sequential Visual Localization on 3D Scene Graphs

Nicole Damblon, Olga Vysotska, Federico Tombari, Marc Pollefeys, Dániel Baráth

ACON: Optimizing Context Compression for Long-horizon LLM Agents

Minki Kang, Wei-Ning Chen, Dongge Han, Huseyin Inan, Lukas Wutschitz, Yanzhi Chen, Robert Sim, Saravan Rajmohan

AdaNav: Adaptive Reasoning with Uncertainty for Vision-Language Navigation

Xin Ding, Jianyu Wei, Yifan Yang, Shiqi Jiang, Qianxi Zhang, Hao Wu, Fucheng Jia, Liang Mi, Yuxuan Yan, Weijun Wang, Yunxin Liu, Zhibo Chen, Ting Cao

Beyond Sunk Costs: Boosting LLM Pre-training Efficiency via Orthogonal Growth of Mixture-of-Experts

Ruizhe Wang, Yucheng Ding, Xiao Liu, Yaoxiang Wang, Peng Cheng, Baining Guo, Zhengjun Zha, Yeyun Gong

Co-Evolving Latent Action World Models

Yucen Wang, Feng Zhang, De-Chuan Zhan, Li Zhao, Kaixin Wang, Jiang Bian

ConPress: Learning Efficient Reasoning from Multi-Question Contextual Pressure

Jie Deng, Shining Liang, Jun Li, Hongzhi Li, Yutao Xie

CrispEdit: Low-Curvature Projections for Scalable Non-Destructive LLM Editing

Zarif Ikram, Arad Firouzkouhi, Stephen Tu, Mahdi Soltanolkotabi, Paria Rashidinejad

ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation

Yiran Wu, Mauricio Velazco, Andrew Zhao, Manuel Ra'ul Mel'endez Luj'an, Srisuma Movva, Yogesh K Roy, Quang-Huy Nguyen, Roberto Rodriguez, Qingyun Wu, Michael Albada, Julia Kiseleva, Anand Mudgerikar

Next-Token Prediction and Regret Minimization

M. Mohri, C. Sanford, Jon Schneider, Kiran Vodrahalli, Yifan Wu

Thinned Mean Field Langevin Dynamics

Zonghao Chen, Heishiro Kanagawa, Franc¸ois-Xavier Briol, Chris J. Oates, Lester Mackey

PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimization

Han Jiang, Dongyao Zhu, Zhihua Wei, Xiaoyuan Yi, Ziang Xiao, Xing Xie

Disentangling Consensus and Value-Specific Representations for Controllable Pluralistic Value Alignment of LLMs

JianKui Zhou, Jing Yao, Xiaoyuan Yi, Peng Zhang, Ning Gu, Zhan Hu, Xing Xie, Tun Lu

A Tale of Two Graphs: Separating Knowledge Exploration from Outline Structure for Open-Ended Deep Research

Zhuofan Shi, M. Ma, Zekun Yao, Fangkai Yang, Jue Zhang, Dongge Han, Victor Ruhle, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang

AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation

Ziwei Zhou, Zeyuan Lai, Rui Wang, Yifan Yang, Zhening Xing, Yuqing Yang, Qi Dai, Lili Qiu, Chong Luo

Entropy-Aware Dynamic KV Cache Sparsification for Autoregressive Image Generation and Editing

Tong Tong, Ling Xing, Linjie Li, Rui Yan, Zhengyuan Yang, Lijuan Wang, Alex Jinpeng Wang

Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory

Sijia Li, Yuchen Huang, Zifan Liu, Zijian Li, Jingjing Fu, Lei Song, Jiang Bian, Jun Zhang, Rui Wang

LIVE: Long-horizon Interactive Video World Modeling

Junchao Huang, Ziyang Ye, Xinting Hu, Tianyu He, Guiyu Zhang, Shaoshuai Shi, Jiang Bian, Li Jiang

Sonar-TS: Search-Then-Verify Natural Language Querying for Time Series Databases

Zhao Tan, Yiji Zhao, Shiyu Wang, Chang Xu, Yuxuan Liang, Xiping Liu, Shirui Pan, Ming Jin

A Foundation-style Model for Zero-Shot Statistical Dependency Measurement

Zhengyang Hu, Yanzhi Chen, Hanxiang Ren, Qunsong Zeng, Youyi Zheng, Adrian Weller, Kaibin Huang, Yanchao Yang

3DMedAgent: Unified Perception-to-Understanding for 3D Medical Analysis

Ziyue Wang, Linghan Cai, Chang Han Low, Hao Liu, Junde Wu, Jingyu Wang, Rui Wang, Lei Song, Jiang Bian, Jingjing Fu, Yueming Jin

A Benchmark and Framework for Evaluating Next Action Predictions in Spreadsheets

Tejas Agrawal, Vu Le, Sumit Gulwani, Gust Verbruggen

Algorithmic Primitives and Compositional Geometry of Reasoning in Language Models

Samuel Lippl, Thomas McGee, Kimberly A. Lopez, Ziwen Pan, Pierce Zhang, Salma Ziadi, Oliver Eberle, Ida Momennejad

Beyond Pixel Context Windows: Neural World Simulators with Persistent 3D State

Samuel Garcin, Tom Walker, Steven McDonagh, Tim Pearce, Hakan Bilen, Tianyu He, Kaixin Wang, Jiang Bian

Improving Diffusion Planners by Self-Supervised Action Gating with Energies

Yuanjie Lu, Dongqi Han, Yansen Wang, Dongsheng Li

Interpreting and Steering State-Space Models via Activation Subspace Bottlenecks

Vamshi Sunku Mohan, Kaustubh Gupta, Aneesha Das, Chandan Singh

Multimodal Latent Language Modeling with Next-Token Diffusion

Yutao Sun, Hangbo Bao, Wenhui Wang, Zhiliang Peng, Li Dong, Shaohan Huang, Jianyong Wang, Furu Wei

On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length

Sunghwan Kim, Junhee Cho, Beong-woo Kwak, Taeyoon Kwon, Liang Wang, Nan Yang, Xingxing Zhang, Furu Wei, Jinyoung Yeo

PISCES: Annotation-free Text-to-Video Post-Training via Optimal Transport-Aligned Rewards

Minh-Quan Le, Gaurav Mittal, Cheng Zhao, David Gu, Dimitris Samaras, Mei Chen

Towards Efficient LLMs Annealing with Principled Sample Selection

Yuanjian Xu, Jianing Hao, Wanbo Zhang, Zhong Li, Guang Zhang

When does predictive inverse dynamics outperform behavior cloning?

Lukas Schäfer, Pallavi Choudhury, Abdelhak Lemkhenter, Chris Lovett, Somjit Nath, Luis França, Matheus Ribeiro Furtado de Mendonça, Alex Lamb, Riashat Islam, Siddhartha Sen, John Langford, Katja Hofmann, Sergio Valcarcel Macua

Diversity Over Frequency: Rethinking Tool Use in Visual Chain-of-Thought Agents

Donghyun Kim, Reuben Tan, Donghyun Kim

A Computational Framework for Evaluating Human-likeness in LLMs' Open-ended Human Behaviors

Yuxuan Lei, Jianxun Lian, Defu Lian, Jincenzi Wu, Tianfu Wang, Xing Xie

D^3: Dynamic Directional Graph-Constrained Data Scheduling for LLM Training

Yuanjian Xu, Jianing Hao, Guang Zhang, Zhong Li

Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use

Aradhye Agarwal, Gurdit Siyan, Yash Pandya, Joykirat Singh, Akshay Nambi, Ahmed Awadallah

PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents

Ke Yang, Zixiang Chen, Xuan He, Jize Jiang, Michel Galley, Chenglong Wang, Jianfeng Gao, Jiawei Han, ChengXiang Zhai

SlideSparse: Fast and Flexible (2N-2):2N Structured Sparsity

Hanyong Shao, Yingbo Hao, Ting Song, Yan Xia, Di Zhang, Shaohan Huang, Xun Wu, Songcheng Xu, Le Xu, Li Dong, Zewen Chi, Yinxue Zou, Furu Wei

Subliminal Effects in Your Data: A General Mechanism via Log-Linearity

Ishaq Aden-Ali, Noah Golowich, Allen Liu, Abhishek Shetty, Ankur Moitra, Nika Haghtalab

Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM Training

Miaosen Zhang, Yishan Liu, Shuxia Lin, Xu Yang, Qi Dai, Chong Luo, Wei Jiang, Peng-Fei Hou, Anxiang Zeng, Xin Geng, Baining Guo

From Content to Knowledge: Lightning Fast Long-Video Understanding with Neural Knowledge Representations

Yuchen Guan, X. Li, Zongyu Guo, Xiaoyi Zhang, Xiulian Peng, Chun Yuan, Yan Lu

Understand and Accelerate Memory Processing Pipeline for Large Language Model Inference

Zifan He, Rui Ma, Yizhou Sun, Jason Cong

Minibatch Selection for Language Models via Partition Matroid Constrained Gradient Matching

Prayas Agrawal, Prateek Chanda, Ishita Khatri, Ganesh Ramakrishnan, Bamdev Mishra, Pratik Jawanpuria

Compression as Adaptation: Implicit Visual Representation with Diffusion Foundation Models

Jiajun He, Zongyu Guo, Zhaoyang Jia, Xiaoyi Zhang, Jiahao Li, Xiao Li, Bin Li, José Miguel Hernández-Lobato, Yan Lu