Accepted Papers

Please check the OpenReview workshop page for full content.

(Oral) Masked Generative Priors Improve World Models Sequence Modelling Capabilities
Cristian Meo, Mircea Lică, Zarif Ikram, Akihiro Nakano, Vedant Shah, Aniket Rajiv Didolkar, Dianbo Liu, Anirudh Goyal, Justin Dauwels

(Oral) From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment
Yilin Wu, Ran Tian, Gokul Swamy, Andrea Bajcsy

(Oral) Temporal Difference Flows
Jesse Farebrother, Matteo Pirotta, Andrea Tirinzoni, Remi Munos, Alessandro Lazaric, Ahmed Touati

(Oral) Improving Transformer World Models for Data-Efficient RL
Antoine Dedieu, Joseph Ortiz, Xinghua Lou, Carter Wendelken, Wolfgang Lehrach, J. Swaroop Guntupalli, Miguel Lazaro-Gredilla, Kevin Murphy

(Oral) Scalable Humanoid Whole-Body Control via Differentiable Neural Network Dynamics
Yu Lei, Zhengyi Luo, Tairan He, Jinkun Cao, Guanya Shi, Kris Kitani

(Oral) When do neural networks learn world models?
Tianren Zhang, Guanyu Chen, Feng Chen

Recurrent world model with tokenized latent states
Guangyao Zhai, Xingyuan Zhang, Nassir Navab

Newton - A Small Benchmark for Interactive Foundation World Models
Spruce Campbell

Effectively Designing 2-Dimensional Sequence Models for Multivariate Time Series
Daniel Cao, Ali Behrouz, Ali Parviz, Mahdi Karami, Michele Santacatterina, Ramin Zabih

Stress-Testing Offline Reward-Free Reinforcement Learning: A Case for Planning with Latent Dynamics Models
Vlad Sobal, Wancong Zhang, Kyunghyun Cho, Randall Balestriero, Tim G. J. Rudner, Yann LeCun

Accelerating Goal-Conditioned RL Algorithms and Research
Michał Bortkiewicz, Władysław Pałucki, Vivek Myers, Tadeusz Dziarmaga, Tomasz Arczewski, Łukasz Kuciński, Benjamin Eysenbach

COMPARATIVE STUDY OF WORLD MODELS, NVAE- BASED HIERARCHICAL MODELS, AND NOISYNET- AUGMENTED MODELS IN CARRACING-V2
Vidyavarshini Jayashankar, Banafsheh Rekabdar

Utilizing World Models for Adaptively Covariate Acquisition Under Limited Budget for Causal Decision Making Problem
Haocheng Yang

Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models
Victor Weixin Liang, Lili Yu, Liang Luo, Srini Iyer, Ning Dong, Chunting Zhou, Gargi Ghosh, Mike Lewis, Scott Yih, Luke Zettlemoyer, Victoria Lin

LEARNING FROM LESS: SINDY SURROGATES IN RL
Aniket Dixit, Muhammad Ibrahim Khan, Faizan Ahmed, James Brusey

Latent Action Learning Requires Supervision in the Presence of Distractors
Alexander Nikulin, Ilya Zisman, Denis Tarasov, Lyubaykin Nikita, Andrei Polubarov, Igor Kiselev, Vladislav Kurenkov

Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation
Qiyue Gao, Xinyu Pi, Kevin Liu, Junrong Chen, Ruolan Yang, Xinqi Huang, Xinyu Fang, Lu Sun, Gautham Kishore, Bo Ai, Stone Tao, Mengyang Liu, Jiaxi Yang, Chao-Jung Lai, Chuanyang Jin, Jiannan Xiang, Benhao Huang, David Danks, Hao Su, Tianmin Shu, Ziqiao Ma, Lianhui Qin, Zhiting Hu

BEYOND SINGLE-STEP: MULTI-FRAME ACTION- CONDITIONED VIDEO GENERATION FOR REINFORCE- MENT LEARNING ENVIRONMENTS
Zongyue Li, Sikuan Yan, Yunpu Ma, Yusong Li, Xing Lyu, Matthias Schubert

Trajectory World Models for Heterogeneous Environments
Shaofeng Yin, Jialong Wu, Siqiao Huang, Xingjian Su, Xu He, Jianye HAO, Mingsheng Long

SEAL: SEmantic-Augmented Imitation Learning via Language Model
Chengyang GU, Yuxin Pan, Haotian Bai, Hui Xiong, Yize Chen

Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Models
Yang Zhang, Chenjia Bai, Bin Zhao, Junchi Yan, Xiu Li, Xuelong Li

Accelerating Model-Based Reinforcement Learning with State-Space World Models
Elie Aljalbout, Maria Krinner, Angel Romero, Davide Scaramuzza

Programmatic Video Prediction Using Large Language Models
Hao Tang, Kevin Ellis, Suhas Lohit, Michael Jones, Moitreya Chatterjee

Pre-Trained Video Generative Models as World Simulators
Haoran He, Yang Zhang, Liang Lin, Zhongwen Xu, Ling Pan

Emergent Stack Representations in Modeling Counter Languages Using Transformers
Utkarsh Tiwari, Aviral Gupta, Michael Hahn

Mixture-of-Mamba: Enhancing Multi-Modal State-Space Models with Modality-Aware Sparsity
Victor Weixin Liang, Junhong Shen, Genghan Zhang, Ning Dong, Luke Zettlemoyer, Lili Yu

Improving World Models using Supervision with Co-Evolving Linear Probes
Andrii Zahorodnii

MS-SSM: A Multi-Scale State Space Model for Enhanced Sequence Modeling
Mahdi Karami, Ali Behrouz, Peilin Zhong, Razvan Pascanu, Vahab Mirrokni

PINT: Physics-Informed Neural Time Series Models with Applications to Long-term Inference on WeatherBench 2m-Temperature Data
Keon Vin Park, Jisu Kim, Jaemin Seo

Text2World: Benchmarking World Modeling Capabilities of Large Language Models via Program Synthesis
Mengkang Hu, Tianxing Chen, Yude Zou, Yuheng Lei, Qiguang Chen, Ming Li, Qiwei Liang, Yao Mu, Hongyuan Zhang, Wenqi Shao, Ping Luo

DIALOGUES BETWEEN ADAM AND EVE: EXPLORATION OF UNKNOWN CIVILIZATION LANGUAGE BY LLM
Wang Xu, Fengzhou Wang, Yiquan Wang

Model-based Offline Reinforcement Learning with Lower Expectile Q-Learning
Kwanyoung Park, Youngwoon Lee

RADI: LLMs as World Models for Robotic Action Decomposition and Imagination
Dongqi Zuo, Chuan Zhou, Yandong Guo, Xiao He, Mingming Gong

Combining Unsupervised and Offline RL via World Models
Daniel Khapun, Dan Rosenbaum

Generalist World Model Pre-Training for Efficient Reinforcement Learning
Yi Zhao, Aidan Scannell, Yuxin Hou, Tianyu Cui, Le Chen, Dieter Büchler, Arno Solin, Juho Kannala, Joni Pajarinen

A Virtual Reality-Integrated System for Behavioral Analysis in Neurological Decline
Chen Zhang, Jiaxin Shi, Yanan Sui

Object-Centric Latent Action Learning
Albina Klepach, Alexander Nikulin, Ilya Zisman, Denis Tarasov, Alexander Derevyagin, Andrei Polubarov, Lyubaykin Nikita, Vladislav Kurenkov

Memory Helps, but Confabulation Misleads: Understanding Streaming Events in Videos with MLLMs
Gengyuan Zhang, Mingcong Ding, Tong Liu, Yao Zhang, Volker Tresp

HEP-JEPA: A foundation model for collider physics
Jai Bardhan, Radhikesh Agrawal, Abhiram Tilak, Cyrin Neeraj, Subhadip Mitra

Transformers Use Causal World Models in Maze-Solving Tasks
Alexander Spies, William Edwards, Michael Ivanitskiy, Adrians Skapars, Tilman Räuker, Katsumi Inoue, Alessandra Russo, Murray Shanahan

Adapting a World Model for Trajectory Following in a 3D Game
Marko Tot, Shu Ishida, Abdelhak Lemkhenter, David Bignell, Pallavi Choudhury, Chris Lovett, Luis França, Matheus de Mendonça, Tarun Gupta, Darren Gehring, Sam Devlin, Sergio Valcarcel Macua, Raluca Georgescu

Scaling Laws for Pre-training Agents and World Models
Tim Pearce, Tabish Rashid, David Bignell, Raluca Georgescu, Sam Devlin, Katja Hofmann

BiD: Behavioral Agents in Dynamic Auctions
Weitong Zhang, Chengqi Zang, Mark Schmidt, Richard Blythman

World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning
Siyin Wang, Zhaoye Fei, Qinyuan Cheng, Shiduo Zhang, Panpan Cai, Jinlan Fu, Xipeng Qiu

A Proposal for Networks Capable of Continual Learning
Zeki Doruk Erden, Boi Faltings

Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension
Xiyao Wang, Zhengyuan Yang, Linjie Li, Hongjin Lu, Yuancheng Xu, Chung-Ching Lin, Kevin Lin, Furong Huang, Lijuan Wang

TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets
Yuzhe YANG, Yifei Zhang, Minghao Wu, Kaidi Zhang, Yunmiao Zhang, Honghai Yu, Yan Hu, Wang Benyou

Object-Centric World Model for Language-Guided Manipulation
Youngjoon Jeong, Junha Chun, Soonwoo Cha, Taesup Kim

Reward-free World Models for Online Imitation Learning
Shangzhe Li, Zhiao Huang, Hao Su

HuWo: Building Physical Interaction World Models for Humanoid Robot Locomotion
Han Zheng, Yi Cheng, Hang Liu, Linqi Ye, Houde Liu

Distribution Recovery in Compact Diffusion World Models via Conditioned Frame Interpolation
Sam Gijsen, Kerstin Ritter

Fixed-Point RNNs: From Diagonal to Dense in a Few Iterations
Sajad Movahedi, Felix Sarnthein, Nicola Muca Cirone, Antonio Orvieto

Pushing the Limit of Sample-Efficient Offline Reinforcement Learning
Peng Cheng, Zhihao Wu, Jianxiong Li, Ziteng He, Haoran Xu, Wei Sun, Youfang Lin, Xianyuan Zhan

Unifying Causal and Object-centric Representation Learning allows Causal Composition
Avinash Kori, Ben Glocker, David Ha, Francesco Locatello

Object-Centric Representations Generalize Better Compositionally with Less Compute
Ferdinand Kapl, Amir Mohammad Karimi Mamaghan, Max Horn, Carsten Marr, Stefan Bauer, Andrea Dittadi

Latent Representation Encoding and Multimodal Biomarkers for Post-Stroke Speech Assessment
Giulia Sanguedolce, Dragos-Cristian Gruia, Patrick Naylor, Fatemeh Geranmayeh

Knowledge Graphs as World Models for Material-Aware Obstacle Handling in Autonomous Vehicles
Ayush Bheemaiah, Seungyong Yang

Reframing LLM Finetuning Through the Lens of Bayesian Optimization
Bojana Ranković, Ryan-Rhys Griffiths, Philippe Schwaller

ACT-Bench: Towards Action Controllable World Models for Autonomous Driving
Hidehisa Arai, Keishi Ishihara, Tsubasa Takahashi, Yu Yamaguchi

ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer
Jinyi Hu, Shengding Hu, Yuxuan Song, Yufei Huang, Mingxuan Wang, Hao Zhou, Zhiyuan Liu, Wei-Ying Ma, Maosong Sun

Revisiting the Othello World Model Hypothesis
Yifei Yuan, Anders Søgaard

Reconstructing Dynamics from Steady Spatial Patterns with Partial Observations
Xinyue Luo, Xuzhe Qian, Yu Chen, Huaxiong Huang, Jin Cheng

Generating Symbolic World Models via Test-time Scaling of Large Language Models
Zhouliang Yu, yuhuan yuan, Tim Xiao, Fuxiang Xia, Jie Fu, Ge Zhang, Ge lin, Weiyang Liu