Digest

Reset

1180 papers

2026-09-30 · arXiv:2609.37583

RoboHarn-Evo: Evolving Hierarchical Physical Knowledge for Self-Improving Robotic Manipulation

Shifeng Bao, Fanding Huang, Yihan Lin et al.

RoboHarn-Evo evolves Hierarchical Physical Knowledge (HPK) from physical interaction experience to improve long-horizon robotic manipulation without updating the base vision-language model or low-level executor. It uses dual loops: an inner execution loop that retrieves Task Knowledge and Action Knowledge, and an outer knowledge-update loop that revises entries via task-completion and physical-effect checks. Experiments on RMBench and RoboDojo report large held-out and transfer gains.

DrivingAI summary
2026-09-30 · arXiv:2609.37644

Beyond a single latent space: a dual-latent world model for long-horizon planning

Delin Zhao, Zhengrong Yue, Shaobin Zhuang et al.

The authors report Dual-WM, a dual-latent world model that separates low-level execution from high-level long-range planning using distinct state representations/dynamics and learned macro-actions. They introduce LoRe to supervise self-generated recursive rollouts at both levels with horizon-weighted losses. On five goal-conditioned visual control tasks, the authors report improved long-horizon goal success versus task-wise strongest non-actor-guided baselines.

Latent DynamicsAI summary
2026-09-30 · arXiv:2609.37690

Honeycomb: Constant-Size Scene Memory Representation for Video World Models

Jack Wei Lun Shi, Kaichen Zhou, Haoyu Chen et al.

Honeycomb is a video world model that keeps persistent scene memory in a fixed-size HexMemory. HexMemory stores scene features as six fixed-dimension low-rank planes (three spatial, three spatiotemporal). A feed-forward writer updates only new video chunks by warping prior planes to expanded bounds and fusing with confidence-weighted pooling plus a learned residual. A reader reconstructs latent features from HexMemory to condition generation; the method avoids per-scene optimization and full-history reprocessing.

2026-09-30 · arXiv:2609.37708

Generative Interactions: Weaving Multiparty Human Motion with Bilevel Latent Dynamics

Ojas Shirekar, Yash Surange, Augustinas Ju\v{c}as et al.

BRAID is a hierarchical sequential latent-variable model for generative multi-person social motion. It learns shared group-level interaction dynamics and person-level behavior conditioned on evolving group context, enabling coherent generation under full, sparse, or partial observations. The authors evaluate BRAID on forecasting, tracking/in-filling, and response generation using interaction-structure and distributional/physical metrics, and analyze group/person latent structure.

2026-09-30 · arXiv:2609.37721

CogWAM: Aligning Semantic Cognition with World Action Modeling via Event-Driven Interfaces

Sen Wang, Liu Liu, Xinjiang Wang et al.

CogWAM is a cognition-guided world-action model for language-conditioned long-horizon robot manipulation. It maintains a persistent Semantic State that stores completed task events and the active subtask, updating only on semantic transitions. Progress-conditioned WORLD and ACTION queries use this state to condition future-world prediction (training only) and action generation (inference), aiming to keep predictions and actions aligned with task progress.

RoboticsCode availableAI summary
2026-09-30 · arXiv:2609.37793

MVG-WAM: Multiple View Geometry-Aware World-Action Modeling for Robotic Manipulation

Wenbo Chen, Tianfu Li, Haoxuan Xu et al.

MVG-WAM is a world–action model for robotic manipulation that represents synchronized multi-view observations as geometrically related projections of one physical world. It combines an epipolar-constrained global state with view-indexed geometric states routed to corresponding video regions, and uses multi-horizon future metric-depth supervision for scale grounding without depth decoding at deployment. The authors report average success rates of 99.1% (LIBERO) and 92.07% (RoboTwin 2.0), plus 91.3% success on Cobot Magic.

RoboticsAI summary
2026-09-30 · arXiv:2609.37798

GLaS-JEPA: Gaussian-Regularized Speech SSL without Engineered Prediction Targets

Gaspard Bott\'e, S\'everin Baroudi, Samir Sadok et al.

GLaS-JEPA is a speech SSL framework that predicts the current encoder’s continuous representations at masked positions, without contrastive learning, discrete targets, or a separate EMA target encoder. It prevents representation collapse using SIGReg representation-space regularization. Pretrained on 960h LibriSpeech, the 57M model achieves 6.89% WER on frozen-encoder SUPERB ASR and 25.87% CER on slot filling, outperforming listed non-distilled sub-90M baselines.

JEPAAI summary
2026-09-30 · arXiv:2609.37810

Explore, Execute, Evolve: A Skill Acquisition and Reuse Loop for Embodied Agents

Sicheng Xie, Yitong Chen, Haidong Cao et al.

The authors introduce RoboSkill, a skill acquisition-and-reuse framework organized as an Explore–Execute–Evolve loop for embodied agents. The agent explores to gather missing task information, executes tasks with visual and tactile feedback while running reusable code, then evolves a skill library from session records. On LIBERO-10, they report higher first-episode success and lower runtime, and similar gains on real robots.

RoboticsCode availableAI summary
2026-09-30 · arXiv:2609.37970

PhysWAM: Physically Consistent World Action Model for Autonomous Driving

Dhruv Parikh, Fengcheng Yu, Quankai Gao et al.

PhysWAM is a unified world-action model for autonomous driving that co-denoises multiview video, metric depth, and ego motion within a single flow-matching transformer. It introduces Coupled Point Projection (CPP) to unproject generated depth into 3D, transform it using generated SE(3) ego motion, and penalize the distance to LiDAR-transformed points using recorded ego motion, promoting physical consistency. Trajectory selection uses label-free consensus.

DrivingAI summary
2026-09-30 · arXiv:2609.38028

doPlan: A Variable-Horizon Dataset for Multi-Stage Language-Conditioned Planning in Autonomous Driving

Parthib Roy, Yash Tandon, Marcus Blennemann et al.

doPlan is a publicly available real-world autonomous driving dataset with 5,154 human-written passenger instructions aligned to variable-duration nuPlan contexts (30.0–508.8 s). The authors report that language-conditioned models may change predictions without reliably improving directional instruction following, and that the maneuver referenced by passenger instructions often occurs far beyond common 5 s prediction horizons.

DrivingCode availableAI summary
2026-09-30 · arXiv:2609.38057

EVO-WAM: Evolving World Action Models through Video-Action Verification

Shiyang Zhou, Xionghao Wu, Wenbo Li et al.

EVO-WAM adapts world action models to unseen tasks using self-generated video-action trajectories without external action execution. It enables complete autoregressive rollouts via state prediction and anchored multi-frame context, then selects reliable prefixes using a vision-language model for task-completing visuals and an inverse dynamics model to verify video-action consistency. Iteratively training on verified prefixes improves success on unseen RoboTwin 2.0 tasks and real-world long-horizon composites.

DrivingAI summary
2026-09-30 · arXiv:2609.38059

WorldLine: Action-Driven Visual Simulation for Robotic Manipulation

Shenghe Zheng, Wenbo Li, Jiyao Zhang et al.

WorldLine is an action-driven visual simulator for robotic manipulation. It learns transferable robot–object dynamics from 10,000+ hours of action-free robot videos, then grounds heterogeneous actions using 2,000+ hours of action trajectories across 10+ embodiments via an image-space action interface and multi-view/failure-enriched relational training. A robot-focused few-step distillation enables efficient causal rollout for policy evaluation and planning.

RoboticsAI summary
2026-09-30 · arXiv:2609.38120

Stochastic World Models for Verifying Vision-Based Neural Feedback Systems

I. Samuel Akinwande, Mykel J. Kochenderfer, Clark Barrett

The authors train stochastic, physically grounded perception surrogates (world models) for verifying vision-based neural feedback systems. Their verification procedure combines falsification, adaptive refinement, symbolic, and backward analyses. On an emergency braking benchmark, they report resolving the entire state space (38% previously unresolved) with a GAN surrogate, and resolving over 80% of the state space on the RGB benchmark with a world-model surrogate.

DrivingAI summary
2026-09-30 · arXiv:2609.38123

HelixWorld: A Real-time Interactive Audio-Visual World Model

Lei Ke, Jiahao Pan, Zeyue Tian et al.

HelixWorld is a real-time interactive audio-visual world model where visual scenes and camera-grounded stereo sound co-evolve under user interaction. It trains a bidirectional teacher on a curated high-fidelity stereo spatial audio-visual dataset with metric camera poses, then distills it into a few-step causal streaming student using online trajectory distillation and streaming fine-tuning for 24 FPS on a single NVIDIA H800 GPU.

DrivingCode availableAI summary
2026-09-30 · arXiv:2609.38140

Breaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE

Yu Xu, Yuxin Zhang, Xiao Yang et al.

The authors argue that token-wise load-balanced MoE routing forms a “uniformity trap” for video, scattering coherent spatiotemporal tokens across experts and causing fragmentation and distortion. They propose SplitMoE, splitting experts into semantic and generic roles with prototype-guided semantic routing and pull-push regularization, reporting faster convergence and improved routing coherence and video generation quality under matched activated-parameter budgets.

2026-09-30 · arXiv:2609.38154

LongLive-Plug: Once-for-All Distillation for Video Generation

Shuai Yang, Luozhou Wang, Wei Huang et al.

LongLive-Plug introduces a once-for-all distillation framework that learns reusable LoRA adapters on a base video diffusion model. The adapters cover single-pass classifier-free guidance, few-step (four-step) sampling, and long-context error correction for causal autoregressive generation, enabling training-free plug-and-play deployment across compatible downstream models.

2026-09-30 · arXiv:2609.38163

Rethinking Representations for World-Action Modeling

Haoyi Jiang, Liu Liu, Xinjiang Wang et al.

ReWAM is a representation-centric world-action model that uses frozen pre-trained DINO features and builds compact temporal world states via a Temporal Representation Bottleneck (TRB). Action-Grounded Representation Shaping (AGRS) routes only action-loss gradients to the TRB, letting the policy shape what the representation encodes. The authors report 93.6% success on RoboTwin 2.0 without generative video pre-training; on RoboDojo they report average score 9.42 and success rate 5.82% without embodied pre-training and 12.29 and 8.28% with ~600 hours.

DrivingCode availableAI summary
2026-09-30 · arXiv:2609.38164

Rho: A Foundation for Efficiently Adaptable VLA Models

Rho Team, Simran Bagaria, Daphne Chen et al.

Rho is an open-weights family of 5B-parameter vision-language-action (VLA) models for bimanual robotic manipulation across three embodiments (YAM Box, UR AI Trainer, FR3 Duo). The authors design regularized progressive adaptation with embodiment midtraining, and show improved downstream adaptation in simulation and physical-robot experiments. They also add online latent adaptation that learns from corrective feedback using as few as 15 corrected episodes.

DrivingAI summary
2026-09-30 · arXiv:2609.38169

STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization

Bingchen Yao, Haobo Xu, Haokun Lin et al.

STEPQuant is a spatial-temporal post-training quantization method for Delta-rule linear-attention recurrent states. It allocates quantization precision using lifetime-aware bit allocation (memory error persistence) and key-row-aware dual-axis fitting (key-row impact and row/column magnitude structure). On Qwen3.8-27B and Kimi-Linear-48B-A3B-Instruct, it matches FP32-state accuracy under a nominal 6-bit budget and outperforms uniform INT8 at 4-bit, with large serving memory reductions.

DrivingCode availableAI summary
2026-09-30 · arXiv:2609.38172

Counterfactual Video Generation Enables Scalable Humanoid Loco-Manipulation

Zihan Wang, Zhen Wu, Pieter Abbeel et al.

PRISM uses grounded video-to-video (V2V) generation to create hundreds of counterfactual human–object interaction videos from four real seed videos. A contact-anchored real-to-sim pipeline reconstructs and retargets monocular videos into physically plausible robot–object trajectories. A single depth-based humanoid policy is trained and deployed on a real robot zero-shot (no real-world fine-tuning) using onboard depth for pick–carry–drop on diverse objects.

DrivingAI summary