The Fourteenth International Conference on Learning Representations, abbreviated as ICLR 2026, begins this week in Rio de Janeiro, Brazil. Below is a list of work from Princeton students, post-docs, research software engineers and faculty that will be showcased.
Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgetting
Authors: Asher Hancock, Xindi Wu, Lihan Zha, Olga Russakovsky, Anirudha Majumdar
Links: Paper, Project Page
Adversarial Déjà Vu: Jailbreak Dictionary Learning for Stronger Generalization to Unseen Attacks
Authors: Mahavir Dabas, Tran Huynh, Nikhil Billa, Jiachen (Tianhao) Wang, Peng Gao, Charith Peris, Yao Ma, Rahul Gupta, Ming Jin, Prateek Mittal, Ruoxi Jia
Links: Paper, Project Page
ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization
Authors: Lawrence Liu, Alexander Liu, Mengdi Wang, Tuo Zhao, Lin Yang
Links: Paper, Project Page
AutoCode: LLMs as Problem Setters for Competitive Programming
Authors: Shang Zhou, Zihan Zheng, Kaiyuan Liu, Zeyu Shen, Zerui Cheng, Zexing Chen, Hansen He, Jianzhu Yao, Huanzhi Mao, Qiuyang Mang, Tianfu Fu, Beichen Li, Dongruixuan Li, Wenhao Chai, Zhuang Liu, Aleksandra Korolova, Peter Henderson, Natasha Jaques, Pramod Viswanath, Saining Xie, Jingbo Shang
Links: Paper, Project Page
Bound by semanticity: universal laws governing the generalization-identification tradeoff
Authors: Marco Nurisso, Jesseba Fernando, Raj Deshpande, Alan Perotti, Raja Marjieh, Steven Frankland, Richard Lewis, Taylor Webb, Declan Campbell, Francesco Vaccarino, Jonathan Cohen, Giovanni Petri
Links: Paper
Can Small Training Runs Reliably Guide Data Curation? Rethinking Proxy-Model Practice
Authors: Jiachen (Tianhao) Wang, Tong Wu, Kaifeng Lyu, James Y Zou, Dawn Song, Ruoxi Jia, Prateek Mittal
Links: Paper
Continuous multinomial logistic regression for neural decoding
Authors: Anuththara Rupasinghe, Jonathan Pillow
Links: Paper
CubeBench: Diagnosing Interactive, Long-Horizon Physical Intelligence under Partial Observations
Authors: Huan-ang Gao, Zikang Zhang, Tianwei Luo, Kaisen Yang, Xinzhe Juan, Jiahao Qiu, Tianxing Chen, Bingxiang He, Hao Zhao, Hao Zhou, Shilong Liu, Mengdi Wang
Links: Paper, Project Page
Demystifying The Mechanisms Behind Emergent Exploration in Goal-Conditioned RL
Authors: Mahsa Bastankhah, Grace Liu, Dilip Arumugam, Thomas L. Griffiths, Benjamin Eysenbach
Links: Paper
ExoPredicator: Learning Abstract Models of Dynamic Worlds for Robot Planning
Authors: Yichao Liang, Dat Nguyen, Cambridge Yang, Tianyang Li, Joshua B Tenenbaum, Carl Edward Rasmussen, Adrian Weller, Zenna Tavares, Tom Silver, Kevin Ellis
Links: Paper
FMIP: Joint Continuous-Integer Flow For Mixed-Integer Linear Programming
Authors: Hongpei Li, Hui Yuan, Han Zhang, Jianghao Lin, Dongdong Ge, Mengdi Wang, Yinyu Ye
Links: Paper, Project Page
FutureFill: Fast Generation from Convolutional Sequence Models
Authors: Naman Agarwal, Xinyi Chen, Evan Dogariu, Devan Shah, Hubert Strauss, Vladimir Feinberg, Daniel Suo, Peter Bartlett, Elad Hazan
Links: Paper
FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction
Authors: Zhiyuan Zeng, Jiashuo Liu, Siyuan Chen, Tianci He, Yali Liao, Yixiao Tian, Jinpeng Wang, Zaiyuan Wang, YangYang, Lingyue Yin, Mingren Yin, Zhu Zhenwei, Tianle Cai, Xinjie Chen, Zehui Chen, Jiecao Chen, Yantao Du, Xiang Gao, Jiacheng Guo, Liang Hu, Jianpeng Jiao, Xiangsheng Li, Jingkai Liu, Nishuang, Zhoufutu Wen, Ge Zhang, Kaiyuan Zhang, 周欣, Jose Blanchet, Xipeng Qiu, Mengdi Wang, Wenhao Huang
Links: Paper, Project Page
GeneBreaker: Jailbreak Attacks against DNA Language Models with Pathogenicity Guidance
Authors: Zaixi Zhang, Zhenghong Zhou, Ruofan Jin, Le Cong, Mengdi Wang
Links: Paper
Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction
Authors: Yong Lin, Shange Tang, Bohan Lyu, Ziran Yang, Jui-Hui Chung, Haoyu Zhao, Lai Jiang, Yihan Geng, Jiawei Ge, Jingruo Sun, Jiayun Wu, Jiri Gesi, Ximing Lu, David Acuna, Kaiyu Yang, Hongzhou Lin, Yejin Choi, Danqi Chen, Sanjeev Arora, Chi Jin
Links: Paper, Project Website
Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation
Authors: Sayash Kapoor, Benedikt Stroebl, Peter Kirgis, Nitya Nadgir, Zachary Siegel, Boyi Wei, Tianci Xue, Ziru Chen, Felix Chen, Saiteja Utpala, Franck Ndzomga, Dheeraj Oruganty, Sophie Luskin, Kangheng Liu, Botao Yu, Amit Arora, Dongyoon Hahm, Harsh Trivedi, Huan Sun, Juyong Lee, Tengjun Jin, Yifan Mai, Yifei Zhou, Yuxuan Zhu, Rishi Bommasani, Daniel Kang, Dawn Song, Peter Henderson, Yu Su, Percy Liang, Arvind Narayanan
Links: Paper, Project Page
Humanline: Online Alignment as Perceptual Loss
Authors: Sijia Liu, Niklas Muennighoff, Kawin Ethayarajh
Links: Paper
Improved high-dimensional estimation with Langevin dynamics and stochastic weight averaging
Authors: Stanley Wei, Alex Damian, Jason Lee
Links: Paper
Intention-Conditioned Flow Occupancy Models
Authors: Chongyi Zheng, Seohong Park, Sergey Levine, Benjamin Eysenbach
Links: Paper
Learning is Forgetting; LLM Training As Lossy Compression
Authors: Henry Conklin, Tom Hosking, Yi-Chern Tan, Jonathan Cohen, Sarah-Jane Leslie, Thomas L. Griffiths, Max Bartolo, Seraphina Goldfarb-Tarrant
Links: Paper, Author Website
Learning to Maximize Rewards via Reaching Goals
Authors: Chongyi Zheng, Mahsa Bastankhah, Grace Liu, Benjamin Eysenbach
Links: Project Page
The Limits of Inference Scaling Through Resampling
Authors: Benedikt Stroebl, Sayash Kapoor, Arvind Narayanan
Links: Paper, Project Page
Log-Linear Attention
Authors: Han Guo, Songlin Yang, Tarushii Goel, Eric P Xing, Tri Dao, Yoon Kim
Links: Paper
Mamba-3: Improved Sequence Modeling using State Space Principles
Authors: Aakash Sunil Lahoti, Kevin Li, Berlin Chen, Caitlin Wang, Aviv Bick, Zico Kolter, Tri Dao, Albert Gu
Links: Paper
A New Approach to Controlling Linear Dynamical Systems
Authors: Anand Brahmbhatt, Gon Buzaglo, Sofiia Druchyna, Elad Hazan
Links: Paper
Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning
Authors: Aravind Venugopal, Jiayu Chen, Xudong Wu, Chongyi Zheng, Benjamin Eysenbach, Jeff Schneider
Links: Paper, Project Page
Parallel Multimodal Diffusion Language Models for Thinking-Aware Editing and Generation
Authors: Ye Tian, Ling Yang, JiongFan Yang, Anran Wang, Yu Tian, Jiani zheng, Haochen Wang, Zhiyang Teng, Zhuochen Wang, Yinjie Wang, Yunhai Tong, Mengdi Wang, Xiangtai Li
Links: Paper, Project Page
PoseX: AI Defeats Physics-based Methods on Protein Ligand Cross-Docking
Authors: Yize Jiang, Xinze Li, Yuanyuan Zhang, Jin Han, Youjun Xu, Ayush Pandit, Zaixi Zhang, Mengdi Wang, Mengyang Wang, Chong Liu, Guang Yang, Yejin Choi, Yingzhou Lu, Wu-Jun Li, Tianfan Fu, Fang Wu, Junhong Liu
Links: Paper, Project Page
Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models
Authors: Yinjie Wang, Ling Yang, Bowen Li, Ye Tian, Ke Shen, Mengdi Wang
Links: Paper, Project Page
Scaling Goal-conditioned Reinforcement Learning with Multistep Quasimetric Distances
Authors: Bill Zheng, Vivek Myers, Benjamin Eysenbach, Sergey Levine
Links: Paper
Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning
Authors: Patrik Reizinger, Bálint Mucsányi, Siyuan Guo, Benjamin Eysenbach, Bernhard Schölkopf, Wieland Brendel
Links: Paper
SLAP: Shortcut Learning for Abstract Planning
Authors: Y. Isabel Liu, Bowen Li, Benjamin Eysenbach, Tom Silver
Links: Paper, Project Page
SonicMoE: Accelerating MoE with IO and Tile-aware Optimizations
Authors: Wentao Guo, Mayank Mishra, Xinle Cheng, Ion Stoica, Tri Dao
Links: Paper
Speculative Speculative Decoding
Authors: Tanishq Kumar, Tri Dao, Avner May
Links: Paper
STAT: Skill-Targeted Adaptive Training
Authors: Yinghui “Gracie” He, Abhishek Panigrahi, Yong Lin, Sanjeev Arora
Links: Paper
Temporal Representations for Exploration: Learning Complex Exploratory Behavior without Extrinsic Rewards
Authors: Faisal Mohamed, Catherine Ji, Benjamin Eysenbach, Glen Berseth
Links: Paper, Project Page
Understanding Transformers for Time Series Forecasting: A Case Study on MOIRAI
Authors: Yu-Hsuan Wu, Yihan He, Yuan Cao, Jianqing Fan, Han Liu
Links: Paper
Value Flows
Authors: Perry Dong, Chongyi Zheng, Chelsea Finn, Dorsa Sadigh, Benjamin Eysenbach
Links: Paper
Visual Compositional Tuning
Authors: Xindi Wu, Hee Seung Hwang, Polina Kirichenko, Esin Tureci, Olga Russakovsky
Links: Paper, Project Page
WAFT: Warping-Alone Field Transforms for Optical Flow
Authors: Yihan Wang, Jia Deng
Links: Paper, Project Page
Why is Your Language Model a Poor Implicit Reward Model?
Authors: Noam Razin, Yong Lin, Jiarui Yao, Sanjeev Arora
Links: Paper
Leave a Reply