Simulation Techniques and Applications

Latest papers

• Counterfactual Generation via Flow Matching: Coupling-Sensitive End-to-End Rates

  Yunrui Guan, Krishnakumar Balasubramanian, Shiva Prasad Kasiviswanathan · 2 October 2026

  Counterfactual generation seeks to sample outcomes under a hypothetical intervention or decision using observational data collected under the factual assignment mechanism. We develop a flow-matching approach that combines a sample-split, doubly robust training objective with a learned coupling betwe…

• Network World Models as Environments for Algorithm Design on Complex Systems

  Rishab Alagharu, Hongji Pu, Zeeshan Memon, Xinyuan Song, Yuntong Hu, Liang Zhao · 2 October 2026

  World models, which simulate an environment and predict how it changes under actions, are increasingly used in real-world applications such as robotics. Complex systems call for the same tool because the effect of an action is not immediate. Seeding nodes for a campaign, or immunizing nodes against …

• Social Choice Foundations for Simulation-Augmented Generation

  Sonja Kraiczy, Smitha Milli, Ratip Emin Berker, Avinandan Bose, Brandon Amos, Jamelle Watson-Daniels, Maximilian Nickel, Edith Elkind, Ariel D. Procaccia · 1 October 2026

  Simulation-augmented generation (SAGE) is a recent technical proposal in which models simulate individuals' viewpoints at inference time in order to provide more representative answers to contentious user queries. A core challenge for SAGE is making inference-time simulation efficient without sacrif…

• SimTrace: Grounded Multimodal User Trajectories Generation for Online User Modeling

  Yunan Lu, Shuang Xie, Meghna Allamudi, Mingyu Zhao, Han Li, Lingyun Wang, Zhou Yu · 1 October 2026

  Virtual clients offer a cost-effective approach to support applications such as A/B testing, recommender system development, and interface evaluation. However, building them requires access to large-scale, semantically faithful, fine-grained online user trajectories. These data are difficult to obta…

• Stochastic World Models for Verifying Vision-Based Neural Feedback Systems

  I. Samuel Akinwande, Mykel J. Kochenderfer, Clark Barrett · 30 September 2026

  Verifying a vision-based neural feedback system requires a model of the observations its controller acts upon. Such a model must capture the variation the sensor produces, while remaining tractable for closed-loop analysis. Generative adversarial networks (GANs) have served as perception surrogates,…

• Accelerated surrogate dynamics for dynamical, stochastic system evolution

  Marco Jochum, Ioannis Kouroudis, Gohar Ali Siddiqui, Taher Amine Hamzaoui, Manuel G\"o{\ss}wein, Alessio Gagliardi · 30 September 2026

  Dynamic simulations are an entrenched way of gaining insight into the evolution of system dynamics. Their computational cost however is often prohibitively high, especially in cases of stochastic frameworks. Machine learning algorithms are especially suited as simulation surrogates. Nevertheless, th…

• World Models with Predictable Long-Horizon Marginals

  Yuhao Du, Shunian Chen · 29 September 2026

  Accurate one-step predictions do not ensure that a world model's rollouts retain the data distribution. We make the model's decoded stationary law explicit by learning a decoder of a fixed Gaussian reference and constraining the behaviour-averaged transition to preserve that reference. For controlle…

• NEMSim: Learning Control-Conditioned Multi-Event Physical Dynamics via Executable Event-Mechanism Priors

  Junsong Yu, Junjie Xie, Pengwei Liu, Dong Ni · 28 September 2026

  High-fidelity simulation of control-conditioned multi-event physical systems is computationally expensive, especially across broad control spaces and long trajectories. In these systems, macroscopic evolution emerges from localized discrete events whose intensities and effects depend on process cont…

• SHRAV: State-Hypothesis-Reason-Action-Verify Framework for Physical Modeling and Inverse Design

  Ziheng Guo, Yang Bu · 25 September 2026

  Physical modeling and inverse design require computation that can continue from reusable state. We introduce SHRAV, an architecture-independent computational framework organized around State, Hypothesis, Reason, Action, and Verify. Its central mechanism is a state-continuation core with declared reu…

• Minimally Invasive Steering of Language Models

  Taha Entesari, Jingyu Zhang, Daniel Khashabi, Mahyar Fazlyab · 25 September 2026

  Pre-logit steering adapts a frozen language model to a test-time reward by adding vectors to its final hidden states. Unregularized reward optimization can substantially alter the output distribution and degrade generation quality. We propose Minimally Invasive Steering Vector Optimization (MISVO), …

• Revalidation Beats Stateful Routing for Scientific Surrogates Under Distribution Shift

  Harshil Lodhiya · 25 September 2026

  Surrogate models are often chosen during development and then left in place as new measurements arrive. That practice becomes risky when noise, input support, or physical parameters change. We asked whether such changes call for a stateful adaptive controller, or whether it is enough to validate the…

• One-Step Generative Surrogate Models via Block-Triangular Joint Drifting

  Nicholas Geissler, Shreya Jha, Ricardo Baptista, Benjamin Peherstorfer · 23 September 2026

  Drifting provides a direct route to one-step generative models, but applying it directly to stochastic transition modeling requires multiple samples of the next state conditioned on the same current state. Standard trajectory data, however, typically provide only one realized next state for each obs…

• OnlineWM: Causality-Aware Active Online Learning for Effective World Modeling

  Yikun Miao, Fangqi Zhu, Quanxin Shou, Xiaoyi Pang, Zhengyang Yan, Junhao Li, Haodong Wang, Zicong Hong, Song Guo · 22 September 2026

  Generative world models aim to predict future states conditioned on actions, where action controllability is fundamental for reliable dynamics modeling. While recent efforts leverage simulator-generated data to enhance this capability, existing training pipelines face two fundamental limitations. Fi…

• Conservation Buys Stability and Factoring Buys Counterfactuals in Physical World Models

  Yufeng Wang, Parivesh Priye, Lu Wei, Haibin Ling · 18 September 2026

  A learned simulator can reproduce its training conditions accurately yet fail in two distinct ways once those conditions change. Over long rollouts, small errors accumulate until the trajectory drifts away from physically plausible behavior; under an intervention on a physical parameter, the model m…

• Predict Before You Deploy: Offline Prediction of Quantization-Induced Task Degradation for World Action Models

  Jiuyi Xu, Jinjia Guo, Meida Chen, Jing Du, Yangming Shi · 18 September 2026

  World action models (WAMs) rely on video-generation backbones, requiring substantial memory and compute for deployment. Post-training quantization reduces memory and can accelerate inference, but bit width, grouping, and quantizer choice define a large configuration space. Identifying configurations…

• Online Robust Reinforcement Learning Through Monte-Carlo Planning

  Tuan Dam, Kishan Panaganti, Brahim Driss, Adam Wierman · 17 September 2026

  Monte Carlo Tree Search (MCTS) is a powerful framework for solving complex decision-making problems, yet it often relies on the assumption that the simulator and the real-world dynamics are identical. Although this assumption helps achieve the success of MCTS in games like Chess, Go, and Shogi, the …

• Walking the Score Manifold: Continuous-time Generative Dynamics on Learned Data Manifolds

  Jan Tauberschmidt, Brian B. Moser, Stanislav Frolov, Andreas Dengel, Andrew B. Duncan, Sebastian J. Vollmer · 17 September 2026

  Generative modeling of time-dependent data is typically formulated on a discrete temporal grid, restricting supervision to the observed timestamps in the training data. We instead frame generation as continuous-time evolution on a learned data manifold. To this end, we leverage pretrained score-base…

• Sampling headroom is not selection gain: a compute-value audit of test-time scaling for video world models

  Yuhua Jiang, Junjie Lu, Feifei Gao · 15 September 2026

  Test-time scaling (TTS) can improve generation only when additional compute produces better candidates and the system can reliably identify them. This distinction is especially important for video world models, where a wider sample pool may contain stronger rollouts without improving the output that…

• Online Surrogate Repair: Decoupling High-Fidelity Feedback from Search Length in Closed-Loop Discovery

  Xiaotang Feng, Philip Torr, Bruno Andreis · 9 September 2026

  Closed-loop AI scientists can generate candidate designs at low marginal computational cost, whereas reliable feedback may require wet-lab synthesis, characterization, or high-fidelity computation. Addressing this imbalance through custom laboratory automation remains infrastructure-intensive and co…

• A Constraint-Aware Generative Framework for Synthetic Origin-Destination Demand in Logistics Networks

  Leian Chen · 7 September 2026

  Large-scale logistics networks require synthetic data generation capabilities to support scenario-based planning under novel conditions-such as network reconfiguration and demand shocks. Existing approaches, which rely primarily on historical observations, lack the ability to generate demand pattern…

• Simulation-free Unbalanced Dynamic Optimal Transport with General Growth Penalty

  Junda Ying, Yuxuan Wang, Bowen Yang, Peijie Zhou, Lei Zhang · 7 September 2026

  Inferring cellular dynamics from unpaired single-cell snapshots requires modeling both state transitions and population growth or death. Unbalanced dynamic optimal transport (UDOT) addresses this by penalizing growth along transport paths, making the choice of growth penalty a key way to encode biol…

• LiveSim: Simulating Environment-Shaped Users in Multi-Agent Live-Stream Ecosystems

  Jiaqi Xu, Yiran Qiao, Jing Chen, Qiwei Zhong, Xiang Ao, Xueqi Cheng · 28 August 2026

  User behavior simulation with large language models~(LLMs) is increasingly used to support multi-agent ecosystem simulation. Existing simulators typically rely on static user profiles inferred from historical observations, which become inadequate in socially intensive environments such as live strea…

• Generative Modeling: A Review

  Maria Nareklishvili, Nick Polson, Vadim Sokolov · 27 August 2026

  We organize the generative-modeling literature around three classes of generators, corresponding to three distinct inferential tasks: estimating counterfactual outcome distributions in causal inference, recovering posteriors from simulated parameter--outcome pairs, and forming predictive outcome dis…

• Data-driven Effective Modeling of Stochastic Chemical Reaction Networks

  Yuan Chen, Weize Mao, Dongbin Xiu · 27 August 2026

  The Stochastic Simulation Algorithm (SSA), widely considered an exact algorithm for stochastic chemical reaction networks, suffers from high computational cost. In this work, we propose a data-driven effective model that operates on a user-defined coarse time step independent of the underlying micro…

• Rollout-Decoded Reconstruction for Long-Horizon Prediction in Latent World Models

  Rishi Shah, Rishav Shrestha · 27 August 2026

  A latent world model trains its decoder on latents anchored to observations, then deploys it on the model's own free-running rollout, hundreds of steps past the last observation. Rollout-Decoded Reconstruction (RDR) closes this gap with a single loss term that free-runs the model during training exa…