ICLR 2026 Accepted Papers - ASSET Center Contributors
- A Scalable Distributed Framework for Multimodal GigaVoxel Image Registration
- Authors: Rohit Jena, Vedant Zope, Pratik Chaudhari, James Gee
- Action Chunking and Data Augmentation Yield Exponential Improvements for Imitation Learning in Continuous Spaces
- Authors: Thomas TCK Zhang, Daniel Pfrommer, Chaoyi Pan, Nikolai Matni, Max Simchowitz
- Bi-Lipschitz Autoencoder With Injectivity Guarantee
- Authors: Qipeng Zhan, Zhuoping Zhou, Zexuan Wang, Qi Long, Li Shen
- Break the Trade-off Between Watermark Strength and Speculative Sampling Efficiency for Language Models
- Authors: Weiqing He, Xiang Li, Li Shen, Weijie Su, Qi Long
- CONCUR: A Framework for Continual Constrained and Unconstrained Routing
- Authors: Peter Baile Chen, Weiyue Li, Dan Roth, Mike Cafarella, Samuel Madden, Jacob Andreas
- Correspondence-Driven Trajectory Warping for Data-Efficient Imitation and Autonomous Play
- Authors: William Liang, Sam Wang, Hung-Ju Wang, Osbert Bastani, Yecheng Jason Ma, and Dinesh Jayaraman
- Demystifying Supervision Data Generalization in Multimodal LMs
- Authors: Xuan Qi, Luxi He, Dan Roth, Xingyu Fu
- Divide and Abstract: Autoformalization via Decomposition and Abstraction Learning
- Authors: Marcus J. Min, Yeqi Gao, Wilson Sy, Zhaoyu Li, Xujie Si, Osbert Bastani
- FACET: A Fragment-Aware Conformer Ensemble Transformer
- Authors: DMH Nguyen, TQ Nguyen, HTH Le, MTN Truong, T Nguyen, N Ho, KD Doan, D Duong-Tran, L Shen, D Sonntag, J Zou, M Niepert, H Kim, JE Allen
- Fair Classification by Direct Intervention on Operating Characteristics
- Authors: Kevin Jiang, Edgar Dobriban
- In Good GRACES: Principled Teacher Selection for Knowledge Distillation
- Authors: Abhishek Panigrahi, Bingbin Liu, Sadhika Malladi, Sham Kakade, Surbhi Goel
- Knowledgeable Language Models as Black-Box Optimizers for Personalized Medicine
- Authors: Michael S Yao, Osbert Bastani, Alma Andersson, Tommaso Biancalani, Aicha BenTaieb, Claudia Iriondo
- Learned Meta-Tokens for Language Modeling
- Authors: Alok Shah, Khush Gupta, Keshav Ramji, Pratik Chaudhari
- Log-Augmented Generation: Scaling Test-Time Reasoning with Reusable Computation
- Authors: Peter Baile Chen, Yi Zhang, Dan Roth, Samuel Madden, Jacob Andreas, Mike Cafarella
- Missingness Bias Calibration in Feature Attribution Explanations
- Authors: Shailesh Sridhar, Anton Xue, Eric Wong
- QLCoder: A Query Synthesizer For Static Analysis of Security Vulnerabilities
- Authors: Claire Wang, Ziyang Li, Saikat Dutta, Mayur Naik
- Replicable Reinforcement Learning with Linear Function Approximation
- Authors: Eric Eaton, Marcel Hussing, Michael Kearns, Aaron Roth, Sikata Bela Sengupta, Jessica Sorrell
- Risk-Sensitive Agent Compositions
- Authors: Guruprerana Shabadi, Rajeev Alur
- Robust Decision Making with Partially Calibrated Forecasts
- Authors: Shayan Kiyani, Hamed Hassani, George Pappas, Aaron Roth
- Scaling Multi-Task Bayesian Optimization with Large Language Models
- Authors: Yimeng Zeng, Natalie Maus, Haydn Thomas Jones, Jeffrey Tao, Fangping Wan, Marcelo Der Torossian Torres, Cesar de la Fuente-Nunez, Ryan Marcus, Osbert Bastani, Jacob R. Gardner
- Shuffling the Data, Extrapolating the Step: Sharper Bias In Constant Step-Size SGD
- Authors: Konstantinos Emmanouilidis, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Rene Vidal
- Singleton-Optimized Conformal Prediction
- Authors: Tao Wang, Yan Sun, Edgar Dobriban
- Sparling: End-to-End Spatial Concept Learning via Extremely Sparse Activations
- Authors: Kavi Gupta, Osbert Bastani, Armando Solar-Lezama
- Tree-based Dialogue Reinforced Policy Optimization for Red-Teaming Attacks
- Authors: Ruohao Guo, Afshin Oroojlooy, Roshan Sridhar, Miguel Ballesteros, Alan Ritter, Dan Roth
- VLMgineer: Vision-Language Models as Robotic Toolsmiths
- Authors: George Jiayuan Gao, Tianyu Li, Junyao Shi, Yihan Li, Zizhe Zhang, Nadia Figueroa, and Dinesh Jayaraman
- ZeroTuning: Unlocking the Initial Token’s Power to Enhance Large Language Models Without Training
- Authors: Feijiang Han, Xiaodong Yu, Jianheng Tang, Delip Rao, Weihua Du, Lyle Ungar