VoxelFix is a graph‑based post‑hoc semantic correction method that refines voxel labels in completed 3D voxel maps while preserving their geometry and occupancy. It learns to correct errors by exploiting local geometry and neighboring semantic information, using training pairs generated by corrupting annotated maps with class confusions from upstream perception pipelines. Experiments on OccuFly maps show consistent improvements of 4.23–5.00 percentage points in mIoU, especially for tree, roof, and wall classes, and the method generalizes to out‑of‑distribution aerial scenes.
By Sunesh Praveen Raja Sundarasami, Taehyoung Kim, Johannes Scherer, Toma\v{z} Coti\v{c}, Sivasubiramaniam Subbiah, Andreas Greiner, Paul Spannaus, Sebastian Houben
The paper examines whether large language models (LLMs) exhibit conspiratorial tendencies, socio-demographic biases in this domain, and how easily they can be conditioned to adopt conspiratorial viewpoints. Using validated psychometric surveys, the authors find that LLMs partially align with conspiracy beliefs, that conditioning with demographic attributes yields uneven effects revealing latent biases, and that targeted prompts can readily shift responses toward conspiratorial stances. These findings underscore the vulnerability of LLMs to manipulation and the potential risks of deploying them in sensitive contexts.
By Francesco Corso, Francesco Pierri, Gianmarco De Francisci Morales
The paper investigates how visuomotor imitation policies fail when visually similar distractors are introduced, framing the issue as conditional visual grounding where the target changes with manipulation phase and task state. Using Action Chunking with Transformers (ACT), the authors systematically vary color and shape similarity of distractors, pinpointing failures to picking and placement stages. They then test distractor augmentation, phase‑dependent attention regularization, and appearance‑based visual prompting, which together significantly improve robustness in simulation and on a physical UR3e robot, and demonstrate similar improvements on a pretrained vision‑language‑action policy for instrument handling.
By Vivek Chavan, Pengtao Xie, Yahuan Shi, Oliver Heimann, Kevin Haninger, J\"org Kr\"uger
The paper introduces a boundary-aware self‑distillation framework for controlled large language model safety refusal, addressing the need for different refusal boundaries within the same topic. It combines controlled topic generation, coverage repair, in‑distribution compensation data, and harmful‑benign pairs to train and evaluate refusal behavior. Experiments on Qwen3‑8B show that escalating retries dramatically improve target‑domain refusal rates while reducing unsafe responses, though they also increase over‑refusal, highlighting the trade‑off between safety and usability.
By Alejo L\'opez-\'Avila, Iker Garc\'ia-Ferrero, Jezabel Garcia, Antonio Tiene, Rom\'an Or\'us
RL-VLA$^3$ is a fully asynchronous distributed reinforcement learning framework designed for Vision‑Language‑Action (VLA) model training. It allows fine‑grained asynchronous interaction between simulation, inference, and training via dynamic batching schedulers and flexible environment sharding, addressing the variable, resource‑intensive latencies of physical simulators. Experiments across multiple simulation backends, VLA architectures, and RL algorithms show throughput gains of up to 85.2% over synchronous baselines while preserving sample efficiency, and the system scales from 8 to 256 GPUs.
By Haoran Sun, Yongjian Guo, Zhong Guan, Shuai Di, Xiaodong Bai, Jing Long, Tianyun Zhao, Mingxi Luo, Hongke Zhao, Likang Wu, Xiaotie Deng, Xu Chu, Xi Xiao, Sheng Wen, Yicheng Gong, Junwu Xiong
The paper introduces ROBORMBENCH, a benchmark comprising 2,390 real‑robot trajectories, 21,673 verified paraphrases, and ground‑truth progress labels, to evaluate paraphrase robustness in vision‑language reward models (VLMs). It demonstrates that current VLMs often give different rewards for semantically equivalent goal descriptions, sometimes flipping a robot’s outcome from failure to success. The study finds that this instability is widespread, worsens with more divergent rewrites, and is not mitigated by model scale or explicit reasoning, though dedicated reward models trained with trajectory‑grounded supervision show greater stability.
By Wonje Jeung, Sangyeon Yoon, Hyesoo Hong, Yoonjun Cho, Dongjae Jeon, Bumjun Kim, Jean Oh, Youngjae Yu, Albert No
The paper introduces a reinforcement learning post‑training scheme that trains robot world models on their own autoregressive rollouts, using a contrastive RL objective adapted from diffusion models. It also proposes a training protocol that compares multiple variable‑length futures, a multi‑view visual fidelity reward, and demonstrates state‑of‑the‑art rollout fidelity on the DROID dataset, outperforming baselines on LPIPS, SSIM, and human preference tests.
By Jai Bardhan, Patrik Drozdik, Josef Sivic, Vladimir Petrik
The paper introduces Post Fusion Stabilizer (PFS), a lightweight module that refines intermediate bird’s‑eye view (BEV) feature maps in existing camera‑LiDAR fusion detectors. PFS stabilizes feature statistics under domain shift, suppresses regions affected by sensor degradation, and adaptively restores weakened cues via residual correction, acting as a near‑identity transformation. On the nuScenes benchmark, PFS achieves state‑of‑the‑art robustness, notably improving camera dropout robustness by +1.2% and low‑light performance by +4.4% mAP while adding only 3.3 M parameters.
By Trung Tien Dong, Dev Thakkar, Arman Sargolzaei, Xiaomin Lin
The paper reviews how large language models have evolved into agents that can influence external environments through tool use, interface operation, delegation, state retention, virtual world inhabitation, and robotic control. It critiques the narrative of a single march toward autonomy, distinguishing model competence from system integration, persistence, and safe authority. The authors find that action-interface expansion is well documented, while robust completion, recovery, authorization, and independent verification remain less proven, and they propose a framework of justified delegation to guide future research.
By Linsen Zhu, Mengqing Cai
The paper addresses performance discrepancy in cross-domain 3D class‑incremental learning, where 3D point clouds from heterogeneous sources cause varying degrees of performance loss beyond catastrophic forgetting. The authors introduce the Domain3D‑CIL protocol and adapt existing CIL methods to 3D, showing consistent discrepancy across baselines. They propose PolyMem, an exemplar‑free approach that models high‑order feature statistics to improve cross‑domain robustness and reduce performance discrepancy.
By Jinge Ma, Gautham Vinod, Bruce Coburn, Jui-Feng Chi, Siddeshwar Raghavan, Fengqing Zhu
The paper introduces Linguistic Trajectory Encoding (LTE), a hybrid representation that compresses dynamic object motion histories using natural language descriptions, sparse spatial anchors, and visual anchors. LTE adapts compression to motion complexity by anchoring periods without reliable observations to the last seen location while preserving accuracy with geometric waypoints and linguistic descriptions. Evaluated on the newly constructed Spatial Memory Benchmark (SMB) from EgoLife multi‑day recordings, LTE achieves 45.3 % success in semantic trajectory retrieval and 48.7 % in long‑horizon object retrieval, outperforming prior structured‑memory and VLM baselines, and compresses trajectories 8.7×–26.1× with sub‑second query latency on 24‑hour video.
By Tianyidan Xie, Shenyi Wang, Qiang Tang, Mingjie Wang, Zhicheng Qiu, Xuanfu Li, Zhan Xu, Jian Yang, Lanjun Wang, Zili Yi
SocioGesture is a real‑time, adaptive system for recognizing social gestures in human‑robot interaction. It employs a compact, confidence‑aware body‑hand skeleton representation and a lightweight dual‑stream model that fuses body motion with hand articulation, enabling low‑latency onboard recognition. The model is trained with occlusion‑aware skeleton corruption to handle missing hands, occluded arms, and unstable keypoints, and it can expand its gesture vocabulary during deployment by saving uncertain interaction segments for offline labeling.
By Wenjin Fu, Li-Fan Wu, Jerin Peter, Chip Huyen, Boyuan Chen, Jan Liphardt
CoLMIN is an LLM-based framework for cooperative autonomous driving that addresses premature convergence to suboptimal solutions in multi-solution traffic scenarios. It introduces a Multi-Intent Negotiation module that generates multiple candidate driving intentions, an Evaluation-based Shallow Reflection Module that provides feedback to accelerate consensus, and a Deep Reflection Module that mitigates cognitive fixation by reflecting on negotiation histories. Experiments in the CARLA simulation show that CoLMIN outperforms existing methods in challenging interactive driving scenarios.
By Zhe Huang, Zhaoxin Fan, Shuo Wang, Wenjun Wu, Xuan Zhao, Min Liu
The paper introduces a CAD‑free 3D shape prior that enhances object recognition by reconstructing each object with 3D Gaussian Splatting (3DGS) from short RGB‑D scans and fusing the resulting shape prototype with frozen DINOv2 image features. Experiments on T‑LESS and HOPE datasets show that geometry alone can match or exceed CAD‑based recognition, and that the combined approach improves performance, especially on shape‑distinctive or partially occluded objects. The study demonstrates that the benefit comes from the geometric information rather than rendered pixels, and that the prior is complementary to frozen vision features.
By Chenxi Tao, Seung-Kyum Choi
The paper introduces a resilient remote robotic control framework that couples control and wireless world models using a Joint Embedding Predictive Architecture (JEPA). By learning latent representations from visual observations and radio frequency (RF) data, the system predicts future robot states and wireless conditions to schedule uplink transmissions efficiently. An adaptive resilience mechanism adjusts perception embeddings when prediction errors arise, enabling robust operation without retraining the entire control policy.
By H. P. Madushanka, Sumudu Samarakoon, Mehdi Bennis
AquaBEV is a monocular underwater occupancy model that predicts local bird’s‑eye‑view (BEV) occupancy from a single RGB image. It uses paired 3D imaging sonar data as geometric supervision during training, mapping visual features into a calibration‑free polar representation and decoding along the range dimension before reconstructing Cartesian BEV coordinates. In a controlled underwater occupancy benchmark, AquaBEV outperforms the strongest transferred baseline with 31.4 % Visible IoU and 38.6 % Observed IoU, achieving 4.0 % and 4.3 % relative improvements respectively.
By Trung Tien Dong, Shengji Jin, Chen Chen, Yi Sheng, Xiaomin Lin
The paper introduces Out-of-Distribution Semantic Occupancy Prediction, a task that focuses on detecting unknown objects in 3D voxel space for autonomous driving. It proposes Realistic Anomaly Augmentation to create two new datasets, VAA-KITTI and VAA-KITTI-360, and presents the OccOoD framework, which uses Cross‑Space Semantic Refinement to improve OoD detection while maintaining semantic occupancy accuracy. Experiments show OccOoD achieves an AuROC of 65.50% and an AuPRCr of 31.83% within a 1.2 m radius, demonstrating strong generalization to real‑world urban scenes.
By Yuheng Zhang, Mengfei Duan, Kunyu Peng, Yuhang Wang, Ruiping Liu, Fei Teng, Kai Luo, Zhiyong Li, Kailun Yang
RoboSPA is a large-scale robotic manipulation dataset and benchmark designed to evaluate Vision‑Language‑Action models on fine‑grained spatial reasoning and long‑horizon procedural planning. It contains 10 task categories, 56 base tasks, and 280 variants across five difficulty levels, with 527K trajectories collected from multiple embodiments and scenes. The benchmark introduces diagnostic metrics beyond binary success, revealing that current VLA models struggle with complex spatial relations, precise execution, and memory‑intensive planning.
By Zhenxuan Fan, Bo Zhang, Yutong Lin, Yuqian Yuan, Juekai Lin, Liang Liang, Zhuoyi Huang, Wenqiao Zhang, Juncheng Li, Siliang Tang, Jun Xiao, Yueting Zhuang
The paper reports the first empirical study comparing how humans and large language models (LLMs) evaluate perceived moral agency (PMA) in both human and autonomous artificial agents within smart city scenarios. Using a validated PMA scale, 190 human participants and various LLMs were assessed, revealing that humans are perceived to have higher moral agency than artificial agents. When confronted with moral dilemmas, LLMs focus on situational factors such as harm severity and urgency, mirroring the context‑sensitivity observed in human raters.
By Fernanda Mansilla, Aloysius Tok, Bahia Guella\"i, Farah Benamara, Nancy F. Chen
MultihopSpatial is a new benchmark for Vision‑Language Models that focuses on multi‑hop, compositional spatial reasoning with queries ranging from 1 to 3 hops across varied spatial perspectives. It introduces the Acc@50IoU metric, which jointly evaluates answer selection and precise bounding‑box prediction, and provides a large‑scale training corpus, MultihopSpatial‑Train, to improve spatial intelligence. Evaluation of 37 state‑of‑the‑art VLMs shows that compositional spatial reasoning remains a significant challenge, and reinforcement learning fine‑tuning on the corpus boosts both intrinsic spatial reasoning and downstream embodied manipulation performance.
By Youngwan Lee, Soojin Jang, Yoorhim Cho, Seunghwan Lee, Yong-Ju Lee, Sung Ju Hwang