Digest

Reset

1180 papers

2026-10-05 · arXiv:2608.23927

GlanceWAM: Sparse Test-Time Imagination for World-Action Models

Linhan Wang, Zijian An, Mingyuan Zhang et al.

GlanceWAM is a world-action model that decouples visual imagination from real-time action control. It asynchronously generates a single latent lookahead frame seconds ahead in the background (via a shared video DiT backbone) and keeps it for several 0.8s action chunks. The action head decodes action chunks at control rate in latent space without blocking, enabled by a non-interfering attention mask and staleness-robust horizon training.

DrivingCode availableAI summary
2026-10-05 · arXiv:2610.02274

Awomo-SimDataEngine: Agentic Simulation-ReadyWorld Generation

PhysicalRSI Team, Danjiao Ma, Enhui Ma et al.

Awomo-SimDataEngine is an agentic system for generating simulation-ready worlds and converting them into robot demonstrations. It combines rigid and articulated asset services (ISArt), scene generation from images (Unravel) or text (SimForge), and a Graph-Native Harness for construction, validation, and bounded repair. PolicyForge then produces replayable Isaac Sim demonstrations. On MuJoCo-based LIBERO-Plus, SimData-Ultra co-training improves WAM overall success from 77.17% to 89.43%.

RoboticsAI summary
2026-10-05 · arXiv:2610.02331

World Editing: Intervening on Executable Worlds at Increasing Depth

Max Ku, Nok-Kan Law, Yu-Chien Tang et al.

The authors define world editing as intervening on an existing executable world while preserving unrelated properties, and introduce intervention depth (property→entity→dynamics→system). They build IGMWorld/IGMBench: 110 Minecraft/Terraria modding tasks (over 1.1K executable state/behavior criteria) with executability, behavioral, preservation, and visual checks. Frontier coding agents reach up to 78.2% task success (strict WSR) and 94.8% criterion pass rate (CPR), with reliability decreasing as depth increases.

2026-10-05 · arXiv:2610.02344

Drive vs. Decay: On the Training Dynamics of Joint-Embedding Predictive Architectures

Jos\'e Lucas De Melo Costa, Seong Woo Ahn, Fabrice Popineau et al.

The authors develop a drive–decay stability theory for Joint-Embedding Predictive Architectures (JEPAs), analyzing training dynamics near the trivial fixed point via a per-mode stability ratio μ_i=γ_i/σ_i. They predict a phase boundary (collapse when μ<1, learning when μ>1) and confirm it across 800+ Tabular-JEPA configurations. Theory suggests stabilizers; they propose ResidualPred, an identity-biased transformer predictor, improving effective rank and linear-probe accuracy on tabular and I-JEPA benchmarks.

JEPACode availableAI summary
2026-10-05 · arXiv:2610.02368

Rethinking World-Action Model for Compositional and In-Context Robotic Manipulation

Shukai Gong, Xuanran Zhai, Yintianrun Zhang et al.

ViGAR is a hierarchical world-action model for long-horizon compositional robotic manipulation. It factorizes task progress into a visual subgoal planner (predicts the next subtask goal image) and a subgoal executor (jointly predicts future visual trajectories and actions conditioned on the predicted subgoal). It supports in-context robotic manipulation by using a global goal image as inference-time context, without parameter updates.

RoboticsCode availableAI summary
2026-10-05 · arXiv:2610.02398

Keep the Effect, Drop the Actor: Programmable Effect-to-Execution World-Action Models

Junyi Hu, Zhewen He, Zhenhua Li et al.

The authors propose PEWAM, an actor-free “effect program” world-action model compiled from a demonstration’s object keypoint trajectories, contact points, and terminal state. PEWAM generates effect, robot execution, action, and terminal state as four streams with independent flow-matching times; clamping a program and sampling the execution turns inference into programming. Re-solving from the live scene absorbs pushes and enables editing and multi-arm transfer.

DrivingAI summary
2026-10-05 · arXiv:2610.02508

World Action Modeling with Progressive Visual Planning

Fei Zhang, Zhaochong An, Duncan Frost et al.

The authors present ProWAM, a world action model that predicts an ordered sequence of sparse, progress-indexed visual sub-goals alongside action chunks. This avoids inefficient dense video rollouts by caching sub-goal features from a single video-backbone forward pass, then using lightweight action denoising during replanning. The authors report improved out-of-distribution robustness on multiple simulation benchmarks and zero-shot real-world experiments.

DrivingAI summary
2026-10-05 · arXiv:2610.02515

IGNITE Tokamak World Model Architecture

Peter Steiner, Azarakhsh Jalalvand, Nathaniel Chen et al.

IGNITE is a generative, multi-modal, actuator-conditioned world foundation model for fusion plasma behavior at the DIII-D tokamak. Trained self-supervised on over a decade of unlabeled experimental data (8000+ discharges), it autoregressively forecasts future diagnostics given initial latent plasma states and actuator trajectories, using spatio-temporal tokenizers with discrete FSQ codes and a transformer dynamics backbone.

DrivingAI summary
2026-10-05 · arXiv:2610.02521

Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory

Ying Yang, Guiyu Zhang, Lianghua Huang et al.

Spatial Memory Intelligence (SMI) is a long-video world-model framework that uses an MLLM to manage long-term spatial memory via four atomic operations: spatial clustering, within-cluster sparsification, action-aware retrieval, and reliability-aware filtering. The authors report comprehensive improvements in memory sparsity, generation stability, and spatial consistency across baselines, benchmarks, and world-model backbones.

2026-10-05 · arXiv:2610.02542

How To Train Your World Model: Fine-tuning vs RAG for LM-based World Modeling

Dhananjay Ashok, Shantanu Agarwal, Vivek Datla et al.

The authors systematically compare fine-tuned vs RAG-based LM world models across five text environments. They report fine-tuning yields higher rewards on 15/20 model-environment combinations, while RAG is more data-efficient and outperforms in Chameleon. They find retrieval often returns suboptimal transitions (recall@5 < 0.7) and propose hierarchical retrieval plus a hybrid approach that combines parametric dynamics with retrieval, outperforming other methods on 17/20 combinations.

Latent DynamicsAI summary
2026-10-05 · arXiv:2610.02580

Physical AI Smart Spaces: A Large-Scale Benchmark for Multi-Camera 3D Perception in Smart Spaces

Yuxing Wang, Yizhou Wang, Anqi Li et al.

Physical AI Smart Spaces (PAISS) is a public benchmark for indoor multi-camera, multi-class 3D perception. It provides synchronized 1080p video (up to 282.5 hours) from 1,799 cameras with automatic multi-camera identities, 2D/3D boxes, camera calibration, and depth where available, spanning synthetic generation (Isaac Sim), Cosmos Transfer 2.5 augmentation, and a hidden real-world Sim2Real target. It introduces a 3D HOTA protocol for 3D tracking evaluation.

DrivingAI summary
2026-10-05 · arXiv:2610.02622

CuBEs: Culturally-Situated Behavioral Evaluations and the Limitations of Culture-Blind LLM Judges

Hoda Ayad, Tanu Mitra, Abhishek Mukherji

The authors propose CuBEs (Culturally-situated Behavioral Evaluations), extending an automated evaluation pipeline to inject cultural context into scenario generation and automated judging. Using a human-labeled dataset across 12 cultures and evaluating 13 LLMs, they report significant cross-cultural variation in the presence of six risky behaviors and show that culturally-agnostic evaluations can miss or invert these effects.

AI summary
2026-10-05 · arXiv:2610.02660

SpectralCache: Accelerating Diffusion-Based World Models via Spectral Feature Caching

Zhendong Mi, Pu Zhao, Ziyu Hu et al.

SpectralCache is a training-free spectral feature caching method for diffusion-based world models. It uses SVD on DiT intermediate features to show stable singular subspaces and predictable singular-value evolution across denoising steps. It reuses cached subspaces and estimates only low-dimensional singular values via linear extrapolation or scaling, skipping expensive Transformer evaluations while preserving generation quality. On HunyuanWorld-Voyager-13B, it reports 5.22× acceleration and WorldScore 65.90 for static scenes.

2026-10-05 · arXiv:2610.02691

DeltaWorld: Physically Consistent Interactive World Simulators via Action-Conditioned Latent Increment Learning

Boyuan Hou, Xiaoge Cao, Chaofan Zhang et al.

DeltaWorld is an action-conditioned interactive world simulator for robotic manipulation that predicts action-induced latent increments rather than the full next latent state. It uses Delta-LTM to add predicted latent feature changes to the current latent state for long-horizon rollouts, and Interaction-aware Latent Alignment to supervise counterfactual interaction regions to reduce physically implausible outcomes.

DrivingAI summary
2026-10-05 · arXiv:2610.02717

RoboBridge: A Self-Evolving Embodied Agent Framework for Sim-to-Real Transfer

Chenxi Li, Zhangrui Zhao, Rui Li et al.

RoboBridge treats sim-to-real transfer as continual adaptation of explicit, executable task skills. It stores task knowledge as procedures linking intent, observations, tool operations, and outcome verification. Interaction feedback generates candidate skill revisions that are validated before persistence or rejection. It uses a frozen pretrained vision-language-action policy as a reusable action tool, adding inference-time reward guidance without updating policy parameters, and evaluates transfer on LIBERO-PRO and corresponding real-robot tasks.

DrivingAI summary
2026-10-05 · arXiv:2610.02726

SymRegFlow: Symmetry-Regularized Flow Matching for Video World Models

Xi Ye, Yuzhu Wang, Xiaoyang Liu et al.

SymRegFlow is a symmetry-regularized flow-matching fine-tuning framework for cross-view-consistent video generation over continuously varying camera poses without ground-truth novel-view RGB supervision. It warps source views into noisy anchors and uses masked dual-anchor supervision plus cross-anchor denoising-output consistency, with directed cross-view attention to preserve observed-view fidelity.

2026-10-05 · arXiv:2610.02788

Skill2Real: Agentic Skill Learning for Zero-Shot Sim-to-Real Robot Manipulation

Xincheng He, Siyu Ma, Chang Yu et al.

Skill2Real learns transferable, executable robot skills in simulation via an asymmetric Proposer–Verifier–Governor (PVG) loop and transfers frozen Cerebellum (local manipulation) and Brain (task-level composition) skills to real robots through a shared code-based API. The authors report LIBERO-Pro Long zero-shot transfer improvements and real UR5e results without real-world task-policy fine-tuning or skill-memory updates.

RoboticsAI summary
2026-10-05 · arXiv:2610.02801

VIGOR: Zero-Shot Visual Generalization via Latent-Space Consistency in Model-Based Reinforcement Learning

Mingyu Park, Samyeul Noh, Hyun Myung et al.

VIGOR tackles a two-level failure in model-based RL under unseen visual distractions: distractions push latent encodings out of distribution, and these errors compound through recursive latent rollouts. VIGOR enforces latent-space consistency using asymmetric weak-to-strong augmentation, dynamics-level consistency via latent regression, and encoder-level stabilization to prevent drift. The authors report improved zero-shot generalization on DMC and Robosuite with TD-MPC2 and DreamerV3 backbones.

Latent DynamicsAI summary
2026-10-05 · arXiv:2610.02828

FSPO: Policy-Consistent Risk and Pareto-Feasible Control for Budgeted LLM RL Post-Training

Miaobo Hu, Shuhao Hu, Xiaobo Guo et al.

FSPO is a feedback-state controller for budgeted LLM RL post-training that jointly handles (i) policy-induced risk shift via a policy-consistent risk-to-go Bellman target using the frozen deployment controller, (ii) selection-induced calibration shift via decision-conditioned trajectory calibration (DCTC) with cross-fitted trajectories, and (iii) multi-resource feasibility via a Pareto resource continuation certificate (PRCC). Under a matched GRPO resource envelope it reports 66.11% held-out and 59.43% OOD accuracy.

DrivingAI summary
2026-10-05 · arXiv:2610.02832

FastOPD: On-Policy Distillation for Lightweight VLA Deployment

Yoojin Oh, Jeongsol Kim, Yeonwoo Seo et al.

FastOPD is an on-policy distillation framework to deploy lightweight Vision-Language-Action (VLA) models by transferring dynamics from a large flow-map teacher using only single-state teacher supervision plus a self-consistency objective. The authors claim theory that minimizing the objective recovers the few-step distribution induced by the teacher’s ideal shortcut model. They evaluate in simulation and on a real robot.

DrivingAI summary