Manipulation, locomotion, sim-to-real transfer and autonomous driving: learning systems that have to survive physics.
arXiv:2609.16864v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have achieved impressive performance in quasi-static manipulation, but struggle in dynamic manipulation tasks bec...
EMODY Flow is a lightweight flow‑matching framework that generates synchronized full‑body motion and facial expressions conditioned on speech and emotion. It attaches to a frozen Qwen‑3 Omni model, reusing its audio codecs to drive two parallel DiT generators for SMPL‑X body pose and FLAME facial expressions. An auxiliary emotion classifier at training time restores emotion sensitivity, enabling EMODY Flow to achieve state‑of‑the‑art gesture quality on BEAT2 and zero‑shot facial animation on TFHP, with significant improvements in FGD, Beat Correlation, and Diversity metrics.
arXiv:2609.16075v1 Announce Type: cross Abstract: Flexible robotic production requires joint decisions on process progression, material routing, resource assignment, temporary cooperation, and simult...
NeuroSymbEAD is a large‑scale neuro‑symbolic caption dataset that builds an ego‑centric knowledge graph of static and dynamic objects on the KITTI‑360 dataset, annotating classes, categories, heading directions, orientations, and distances from the ego‑vehicle. The dataset generates multilevel textual captions that serve as a lightweight representation of an ego‑centric scene map, enabling outdoor scene‑map reconstruction, visual recognition, and object grounding. Baselines for driving common sense and traffic/scene understanding are established, and the dataset is benchmarked using pre‑trained grounding and learned auto‑regressive captioning networks to support vision‑language and foundation models for traffic‑scene explanation, 3D reasoning, and interpretable autonomous‑driving perception.
The article argues that Surprisal Theory, often presented as a computational-level explanation, is not a theory in its own right. It contends that using large language model (LLM) surprisals without considering the underlying representational and algorithmic choices obscures the theory’s commitments. The authors demonstrate through three analyses that algorithm and architecture significantly influence language model probabilities, urging researchers to reassess treating LLM surprisals as interchangeable.
The paper investigates how different 2D image backbones affect indoor semantic occupancy prediction in RGB‑D pipelines. By keeping the projection, depth branch, and occupancy head constant and swapping only the image encoder, the authors find that stronger backbones such as DINOv2 and BLIP2 significantly raise mIoU scores compared to the default ResNet‑50. These results show that the choice of image backbone is a major determinant of 3D occupancy accuracy, outweighing many specialized 3D modules.
arXiv:2609.16737v1 Announce Type: cross Abstract: Generative video models can serve as a promising backbone for robot navigation by predicting future observations as video plans. Recent approaches of...
The paper introduces FastFlowGS, a streaming 4D Gaussian Splatting method that reconstructs fast-moving subjects from a sparse set of external cameras, and Monaco4D, a photorealistic Unreal Engine 5 benchmark featuring Formula 1 sequences with dense ground truth. FastFlowGS combines sparse matches, semi-dense tracks, and dense optical flow using a Kalman-style temporal update, achieving significant performance gains over existing baselines on both CMU-Panoptic and Monaco4D datasets. The benchmark provides varied illumination and viewpoints from trackside, onboard, and drone cameras, enabling evaluation of high-speed outdoor reconstruction.
arXiv:2609.17387v1 Announce Type: new Abstract: Real-time dense SLAM is a core capability for robotics applications that require robust localization and high- quality mapping in dynamic or fast-chang...
arXiv:2609.13083v2 Announce Type: replace-cross Abstract: In urban search and rescue, articulated tracked robots (ATRs) must traverse structured but contact-rich environments such as stairwells and c...
The paper introduces ReImaGin, a method that uses image generation models as a flexible visual reasoning tool for multimodal large language models. Unlike traditional fixed-function vision tools, ReImaGin accepts natural language commands and can perform open-ended visual operations such as removing occlusions or creating floorplans from multiple views. Experiments on six diverse visual reasoning tasks show that ReImaGin outperforms both text-only reasoning and specialist vision-tool baselines, achieving up to a 25% improvement.
MEgoVista is an offline pipeline that converts a single unprepared egocentric video into metric two‑hand and head motion within a gravity‑aligned world frame. It uniquely reconstructs motion in environments beyond studio volumes, uses calibrated stereo for absolute scale, and evaluates its outputs against independent optical capture to audit accuracy. The system thus expands the settings where high‑fidelity hand‑motion labels can be generated from natural, head‑worn recordings.
GeoLAM is a framework that learns geometry‑grounded latent actions from unlabeled human videos. It uses future‑frame reconstruction with a frozen geometric feature hierarchy and motion supervision from a 4D geometry teacher to capture 3D displacement, image‑plane motion, and surface‑orientation changes. After pretraining, the representation serves as transition targets for a world‑action model trained on robot demonstrations, enabling denoised latent actions and executable action chunks without requiring hand‑pose annotations or future‑video generation during deployment.
The paper introduces the Neverwhere Visual Parkour Benchmark Suite, a collection of over sixty hyper‑photo‑realistic 3D Gaussian Splatting reconstructions of urban indoor and outdoor scenes designed to evaluate visual locomotion controllers in closed‑loop, continuous testing setups. It aims to bridge the gap between training and real‑world evaluation by providing reproducible environments and policy checkpoints trained across multiple scenes, while highlighting the risks of relying solely on 3D Gaussian‑generated data. The authors offer code and data on their project page for easy integration into robotic evaluation pipelines.
Intrinsic Robot Rewarding (IRR) leverages existing vision‑language‑action (VLA) systems to evaluate a robot’s own outcomes and provide feedback for policy improvement. By using successful demonstration endpoints as task‑specific references and the policy’s frozen visual encoder as the feature space, IRR adds a reference bank and scoring operation to the current pipeline without requiring a separate evaluator or additional perception backbone. The approach aims to reduce integration effort, reward computation cost, and human outcome scoring while enabling learning from the data already available in industrial robot systems.
The paper proposes a Friedkin‑Johnsen based framework to identify influential users in online social networks and assess how they shape community opinion. By manipulating initial opinions in experiments, the authors show that top influencers can significantly shift overall community sentiment, and their influence extends beyond direct neighbors to second‑degree contacts. The framework is validated on a tweet dataset from the U.S. presidential election, illustrating the power of digital influencers to alter public opinion.
arXiv:2609.16852v1 Announce Type: new Abstract: Industrial IoT environments increasingly deploy autonomous mobile robots for tasks such as material handling, product assembly, or infrastructure inspe...
SafeFlow is a real‑time, text‑driven humanoid control framework that blends physics‑guided motion generation with a three‑stage safety gate. It uses Physics‑Guided Rectified Flow Matching in a VAE latent space to produce physically executable trajectories, accelerates sampling with Reflow, and filters unsafe outputs via semantic OOD detection, directional sensitivity checks, and hard kinematic constraints before handing them to a motion‑tracking controller. Experiments on the Unitree G1 show that SafeFlow achieves higher success rates, better physical compliance, and faster inference than diffusion‑ and retargeting‑based baselines while maintaining motion diversity.
arXiv:2609.17141v1 Announce Type: cross Abstract: Traversability prediction is a critical component of autonomous navigation in unstructured environments, where complex and uncertain robot-terrain in...
The paper introduces CTAN, a Cycle-Temporal Attention Network for audio‑visual embodied navigation. It proposes an Audio‑Visual Reconstruction Cross‑Attention module that uses bidirectional cycle‑consistency to strengthen spatial semantics across visual and acoustic modalities, and a Temporal Cross‑Modal Memory to fuse real‑time multimodal features with historical context. Experiments on Replica and Matterport3D show that CTAN outperforms prior methods in success rate, SPL, and scene navigation accuracy.