Latest World Models Research Papers

The newest World Models papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks World Models so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.

Recent papers

• OncoTraj: a public benchmark for longitudinal resistance prediction in EGFR-mutant non-small-cell lung cancer on osimertinib
  Abhijoy Sarkar, Aarchi Singh Thakur · arXiv · Jun 9, 2026

  Resistance to first-line osimertinib in EGFR-mutant non-small-cell lung cancer (NSCLC) is the canonical example of predictable clonal evolution under therapeutic pressure, yet no public benchmark exists for training or evaluating computatio…

• Echo-Memory: A Controlled Study of Memory in Action World Models
  Wayne King, Zeyue Xue, Yuxuan Bian, Jie Huang et al. · arXiv · Jun 8, 2026

  We present \textbf{Echo-Memory}, a controlled study of memory mechanisms in action-conditioned world models. These models generate multi-segment videos from a first frame, text prompt, and camera-action sequence, but their central failure i…

• Zero Touch Predictive Orchestration: Automating Time-Series Models for the Cloud-Edge Continuum
  Abd Elghani Meliani, Arora Sagar, Adlen Ksentini, Raymond Knopp · arXiv · Jun 8, 2026

  The Cloud-Edge Continuum (CEC) enables latency-critical applications by distributing resources to the far edge, but its extreme volatility makes proactive Zero Touch Management via time-series forecasting essential. However, orchestrators f…

• Policy and World Modeling Co-Training for Language Agents
  Ning Lu, Baijiong Lin, Shengcai Liu, Jiahao Wu et al. · arXiv · Jun 1, 2026

  Reinforcement learning (RL) improves large language model (LLM) agents by teaching them which actions lead to high rewards, but provides little supervision on what those actions do to the environment. World modeling (WM) can fill this gap, …

• TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks
  Andrej Tschalzev, Nick Erickson, Yuyang Wang, Huzefa Rangwala et al. · arXiv · Jun 1, 2026

  Progress in tabular machine learning has largely focused on increasingly sophisticated model architectures. At the same time, feature engineering remains a critical yet underexplored component of real-world modeling pipelines that is entire…

• Statistical Embeddings for Similarity, Retrieval, and Interpretable Alignment of Numeric Tabular Datasets
  M. Ross Kunz, John Merickel, Keith Wilson · arXiv · May 28, 2026

  Numeric tabular datasets are the dominant data format in scientific practice, yet large language models lack native mechanisms for representing numeric datasets in a meaningful way across heterogeneous feature spaces. Existing approaches ei…

• Affective Music Recommendation: A Rollout-Based World Model for Offline Preference Optimization
  Audrey Chan, Aaron Labbé, Jacob Lavoie, Jordan Bannister et al. · arXiv · May 27, 2026

  Functional music applications, from consumer focus and sleep aids to clinical interventions, share a distinctive recommendation problem: success is defined by the listener's affective state, but online experimentation on emotion is ethicall…

• Remember to be Curious: Episodic Context and Persistent Worlds for 3D Exploration
  Lily Goli, Justin Kerr, Daniele Reda, Alec Jacobson et al. · arXiv · May 21, 2026

  Exploration is a prerequisite for learning useful behaviors in sparse-reward, long-horizon tasks, particularly within 3D environments. Curiosity-driven reinforcement learning addresses this via intrinsic rewards derived from the mismatch be…

• SΔϕ-62 — World Model Kernel: Observed Trace, Inference, UMR, Binding Status, and Revision Path Protocols (v1.1, AI-Readable Kernel Package)
  Sofience · Zenodo (CERN European Organ... · May 13, 2026

  SΔϕ-62 defines the World Model Kernel within the Sofience–Δϕ Formalism Series. The central claim is that AI inference should not collapse observed trace, inference, assumption, unresolved model residue (UMR), binding status, and revision pa…

• SΔϕ-62 — World Model Kernel: Trace–UMR–Binding Protocol for AI Inference
  Sofience · Zenodo (CERN European Organ... · May 9, 2026

  This working paper introduces the World Model Kernel within the Sofience–Δϕ (SΔϕ) Formalism. The paper defines a minimal AI-readable world model: World is not identical to observed data. For any observer X, World_X(t) is modeled as Observed…

• Interpreting Reinforcement Learning Agents with Susceptibilities
  Chris Elliott, Einar Urdshals, David Quarel, Daniel Murfet · arXiv · May 8, 2026

  Susceptibilities are a technique for neural network interpretability that studies the response of posterior expectation values of observables to perturbations of the loss. We generalize this construction to the setting of the regret in deep…

• From Data Lifting to Continuous Risk Estimation: A Process-Aware Pipeline for Predictive Monitoring of Clinical Pathways
  Pasquale Ardimento, Mario Luca Bernardi, Marta Cimitile, Samuele Latorre · arXiv · May 5, 2026

  This paper presents a reproducible and process-aware pipeline for predictive monitoring of clinical pathways. The approach integrates data lifting, temporal reconstruction, event log construction, prefix-based representations, and predictiv…

• Multi-fidelity surrogates for mechanics of composites: from co-kriging to multi-fidelity neural networks
  Haizhou Wen, Elham Kiyani, Gang Li, Srikanth Pilla et al. · arXiv · May 4, 2026

  Composite materials exhibit strongly hierarchical and anisotropic properties governed by coupled mechanisms spanning constituents, plies, laminates, structures, and manufacturing history. This intrinsic complexity makes predictive modeling …

• Temporal Data Requirement for Predicting Unplanned Hospital Readmissions
  Ramin Mohammadi, Vahab vahdat, Sarthak Jain, Amir T. Namin et al. · arXiv · May 1, 2026

  With the proliferation of Electronic Health Records (EHRs), a critical challenge in building predictive models is determining the optimal historical data time window to maximize accuracy. This study investigates the impact of various observ…

• Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spaces
  Andrew Bond, Ilkin Umut Melanlioglu, Erkut Erdem, Aykut Erdem · arXiv · Apr 30, 2026

  Modern visual world modeling systems increasingly rely on high-capacity architectures and large-scale data to produce plausible motion, yet they often fail to preserve underlying 3D geometry or physically consistent camera dynamics. A key l…

• Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models
  Gongbo Zhang, Wen Wang, Ye Tian, Li Yuan · arXiv · Apr 29, 2026

  Diffusion large language models (dLLMs) offer parallel decoding and bidirectional context, but state-of-the-art dLLMs require billions of parameters for competitive performance. While existing distillation methods for dLLMs reduce inference…

• VLA Foundry: A Unified Framework for Training Vision-Language-Action Models
  Jean Mercat, Sedrick Keh, Kushal Arora, Isabella Huang et al. · arXiv · Apr 21, 2026

  We present VLA Foundry, an open-source framework that unifies LLM, VLM, and VLA training in a single codebase. Most open-source VLA efforts specialize on the action training stage, often stitching together incompatible pretraining pipelines…

• World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry
  Yuejiang Liu, Fan Feng, Lingjing Kong, Weifeng Lu et al. · ICLR 2026 Workshop World Models · Mar 2, 2026

  General-purpose world models promise scalable policy evaluation, optimization, and planning, yet achieving the required level of robustness remains challenging. Unlike policy learning which primarily focuses on optimal actions, a world mode…

• Consistent Video World Model With Geometry-Aware Rotary Position Embedding
  Chendong Xiang, Jiajun Liu, Jintao Zhang, Xiao Yang et al. · ICLR 2026 Workshop World Models · Mar 2, 2026

  Predictive world models that simulate future observations under explicit camera control are fundamental to interactive AI. Despite rapid advances, current systems lack spatial persistence: they fail to maintain stable scene structures over …

• Toward World Models for Epidemiology
  Zeeshan Memon, Yiqi Su, Christo Kurisummoottil Thomas, Walid Saad et al. · ICLR 2026 Workshop World Models · Mar 2, 2026

  World models have emerged as a unifying paradigm for learning latent dynamics, simulating counterfactual futures, and supporting planning under uncertainty. In this paper, we argue that computational epidemiology is a natural and underdevel…

• Computer-Using World Model
  Yiming Guan, Rui Yu, John Zhang, Lu Wang et al. · ICLR 2026 Workshop World Models · Mar 2, 2026

  Agents operating in complex software environments benefit from reasoning about the consequences of their actions, as even a single incorrect user interface (UI) operation can derail long, artifact-preserving workflows. This challenge is par…

• Action Shapley: A training data selection metric for Training World Models for Reinforcement Learning
  Rajat Ghosh, Debojyoti Dutta · ICLR 2026 Workshop World Models · Mar 2, 2026

  World models are central to model-based reinforcement learning, enabling agents to predict environment dynamics and reason about future outcomes. In real-world settings, however, training high-fidelity world models is often constrained by l…

• Ctrl-World: A Controllable Generative World Model for Robot Manipulation
  Yanjiang Guo, Lucy Xiaoyang Shi, Jianyu Chen, Chelsea Finn · ICLR 2026 Workshop World Models · Mar 2, 2026

  Generalist robot policies can now perform a wide range of manipulation skills, but evaluating and improving their ability with unfamiliar objects and instructions remains a significant challenge. Rigorous evaluation requires a large number …

• Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action Models
  Zhilong Zhang, Haoxiang Ren, Yihao Sun, Yifei Sheng et al. · ICLR 2026 Workshop World Models · Mar 2, 2026

  Vision-Language-Action (VLA) models show strong generalization for robotic control, but finetuning them with reinforcement learning (RL) is constrained by the high cost and safety risks of real-world interaction. Training VLA models in inte…

• Ctrl-World: A Controllable Generative World Model for Robot Manipulation
  Yanjiang Guo, Lucy Xiaoyang Shi, Jianyu Chen, Chelsea Finn · ICLR 2026 Poster · Jan 26, 2026

  Generalist robot policies can now perform a wide range of manipulation skills, but evaluating and improving their ability with unfamiliar objects and instructions remains a significant challenge. Rigorous evaluation requires a large number …

• Remote Sensing-Oriented World Model
  Yuxi Lu, Biao Wu, Zhidong Li, Kunqi Li et al. · Submitted to ICLR 2026 · Sep 12, 2025

  World models have shown potential in artificial intelligence by predicting and reasoning about world states beyond direct observations. However, existing approaches are predominantly evaluated in synthetic environments or constrained scene …

• Utilizing World Models for Adaptively Covariate Acquisition Under Limited Budget for Causal Decision Making Problem
  Haocheng Yang · ICLR 2025 Workshop World Models · Mar 6, 2025

  Treatment effect estimation from observational data faces critical challenges when covariates are partially observed due to resource constraints or privacy concerns. This study introduces a novel framework leveraging world models (e.g., Dee…

• Text2World: Benchmarking Large Language Models for Symbolic World Model Generation
  Mengkang Hu, Tianxing Chen, Yude Zou, Yuheng Lei et al. · ICLR 2025 Workshop World Models · Mar 6, 2025

  Recently, there has been growing interest in leveraging large language models (LLMs) to generate symbolic world models from textual descriptions. Although LLMs have been extensively explored in the context of world modeling, prior studies …

• Recurrent world model with tokenized latent states
  Guangyao Zhai, Xingyuan Zhang, Nassir Navab · ICLR 2025 Workshop World Models · Mar 6, 2025

  World models are getting more and more popular in recent years. We introduce a new architecture -- TokenWM, that maintains the recurrent nature of state-space models while incorporating tokenized latent states and a memory-augmented attenti…

• Revisiting the Othello World Model Hypothesis
  Yifei Yuan, Anders Søgaard · ICLR 2025 Workshop World Models · Mar 6, 2025

  Li et al. (2023) used the Othello board game as a test case for the ability of GPT-2 to induce world models, and were followed up by Nanda et al. (2023b). We briefly discuss the original experiments, expanding them to include more language …