{"total":15,"items":[{"citing_arxiv_id":"2606.23431","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"DexTeleop-0: Force-Aware Bimanual Dexterous Teleoperation with Ego-Centric Perception towards Shared Autonomy","primary_cat":"cs.RO","submitted_at":"2026-06-22T14:48:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"DexTeleop-0 adds a tactile-driven adaptation loop to bimanual dexterous teleoperation that estimates contact points and applies localized force-compliant corrections via operational-space Jacobian updates.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.23296","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"IOI: Decoupling Kinematics and Physics for Interactive World Models","primary_cat":"cs.RO","submitted_at":"2026-06-22T13:09:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"IOI decouples deterministic kinematics from stochastic physics in interactive world models by rendering forward-kinematics trajectories into multi-view projections that guide a video generator, achieving SOTA fidelity and OOD generalization on RoboTwin.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.20867","ref_index":70,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"FOCA: Future-Oriented Conditioning for Data-Efficient Vision-Language-Action Adaptation","primary_cat":"cs.CV","submitted_at":"2026-06-18T18:54:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"FOCA improves few-shot VLA adaptation by explicitly predicting future interaction embeddings and implicitly aligning to goal observations, yielding up to 26% gains on real robots with only 20 demonstrations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.17520","ref_index":70,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"GASE: Gaussian Splatting-Based Automated System for Reconstructing Embodied-Simulation Environments","primary_cat":"cs.RO","submitted_at":"2026-06-16T05:00:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"GASE automates high-fidelity simulation scene reconstruction from multi-view panoramic videos via Gaussian splatting, object extraction, and inpainting, yielding robot policies with under 10% performance gap versus real-world training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.09215","ref_index":43,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-Manipulation","primary_cat":"cs.RO","submitted_at":"2026-06-08T08:50:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MotionWAM conditions a policy on intermediate features from a video world model to predict unified whole-body motion tokens, enabling real-time humanoid loco-manipulation that outperforms VLA baselines by over 30% on nine Unitree G1 tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.24934","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos","primary_cat":"cs.RO","submitted_at":"2026-05-24T08:26:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"HumanEgo reports 92.5% average success on four real robot tasks using only 15-30 minutes of human video per task and zero robot data, with zero-shot transfer to new robots and cameras.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18722","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Dexora: Open-source VLA for High-DoF Bimanual Dexterity","primary_cat":"cs.RO","submitted_at":"2026-05-18T17:50:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Dexora is the first open-source VLA system for dual-arm dual-hand high-DoF manipulation, trained on 100K simulated and 10K real teleoperated trajectories with a discriminator-weighted diffusion policy, achieving 66.7% dexterous success versus 51.7% for baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.15949","ref_index":2,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Reproducible and Physically Feasible Dynamic Parameter Identification Framework for a Low-Cost Robot Arm","primary_cat":"cs.RO","submitted_at":"2026-05-15T13:36:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A pipeline reduces a robot arm's rigid-body parameters from 65 to 39 via symmetry, fits them with OLS+SDP+CLIE on hand-designed trajectories, selects a central model via PCA, and audits inertia positive-definiteness to yield a feasible, accurate dynamic model.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.10094","ref_index":30,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs","primary_cat":"cs.RO","submitted_at":"2026-05-11T07:11:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A retrieve-then-steer method stores successful robot actions in memory and uses them to steer a frozen VLA's flow-matching sampler for better test-time reliability without parameter updates.","context_count":1,"top_context_role":"other","top_context_polarity":"unclear","context_text":"[28] Shaopeng Zhai, Qi Zhang, Tianyi Zhang, Fuxian Huang, Haoran Zhang, Ming Zhou, Shengzhe Zhang, Litao Liu, Sixu Lin, and Jiangmiao Pang. A vision-language-action-critic model for robotic real-world reinforcement learning.arXiv preprint arXiv:2509.15937, 2025. [29] Tony Z Zhao, Vikash Kumar, Sergey Levine, and Chelsea Finn. Learning fine-grained bimanual manipula- tion with low-cost hardware.arXiv preprint arXiv:2304.13705, 2023. [30] TZ Zhao, S Schmidgall, JW Kim, A Deguet, M Kobilarov, A Krieger, and C Finn. Aloha 2: An enhanced low-cost hardware for bimanual teleoperation.arXiv preprint arXiv:2405.02292, 2024. [31] Yichen Zhu, Zhicai Ou, Xiaofeng Mou, and Jian Tang. Retrieval-augmented embodied agents. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 17985-"},{"citing_arxiv_id":"2604.05831","ref_index":1,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"BiCoord: A Bimanual Manipulation Benchmark towards Long-Horizon Spatial-Temporal Coordination","primary_cat":"cs.RO","submitted_at":"2026-04-07T13:02:17+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"BiCoord is a new benchmark for long-horizon tightly coordinated bimanual manipulation that includes quantitative metrics and shows existing policies like DP, RDT, Pi0 and OpenVLA-OFT struggle on such tasks.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"RDT [37] unifies the action representations of different robots. Pi0 [2] combines a flow matching head with a pre-trained vision-language model to inherit Internet-scale seman- tic knowledge. OpenVLA-OFT [24] displaces the diffusion head in VLAs with a parallel decoder, improving the efficiency of action gen- eration. Meanwhile, some works are focused on bimanual manipu- lation [1, 13, 14, 16, 17, 19, 21, 29, 34-36, 38, 39, 47, 58, 60, 62, 64, 65]. Table 1: Comparison of bimanual manipulation benchmarks. All metrics are averaged on trajectories within the dataset. SMP, MAD, AAD, STI are presented in percentage (%). TL reflects the timesteps that required to complete a task. SN is the number of stages in a task. ON shows the number of objects that need to be manipulated or focused in a task."},{"citing_arxiv_id":"2601.20239","ref_index":1,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TouchGuide: Inference-Time Steering of Visuomotor Policies via Touch Guidance","primary_cat":"cs.RO","submitted_at":"2026-01-28T04:22:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"TouchGuide improves contact-rich robot manipulation by steering diffusion or flow-matching visuomotor policies with tactile feasibility scores from a contrastively trained Contact Physical Model.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2509.21723","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"VLBiMan: Vision-Language Anchored One-Shot Demonstration Enables Generalizable Bimanual Robotic Manipulation","primary_cat":"cs.RO","submitted_at":"2025-09-26T00:47:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"VLBiMan framework enables generalizable bimanual manipulation from single human demonstrations via vision-language anchored task decomposition and adaptation without retraining.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2503.14734","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","primary_cat":"cs.RO","submitted_at":"2025-03-18T21:06:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"GR00T N1 is a new open VLA foundation model for humanoid robots that outperforms imitation learning baselines in simulation and shows strong performance on real-world bimanual manipulation tasks.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Tengda Han, Zhitao Gong, Sina Samangooei, Marianne Monteiro, Jacob L Menick, Sebastian Borgeaud, Andy Brock, Aida Nematzadeh, Sahand Sharifzadeh, Mikoł aj Bińkowski, Ricardo Barreira, Oriol Vinyals, Andrew Zisserman, and Karén Simonyan. Flamingo: a visual language model for few-shot learning. In S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh, editors,Advances in Neural Information Processing Systems, 2022. 5 [4] Jorge Aldaco, Travis Armstrong, Robert Baruch, Jeff Bingham, Sanky Chan, Kenneth Draper, Debidatta Dwibedi, Chelsea Finn, Pete Florence, Spencer Goodrich, et al. Aloha 2: An enhanced low-cost hardware for bimanual teleoperation.arXiv preprint arXiv:2405.02292, 2024. 17 [5] Loubna Ben Allal, Anton Lozhkov, Elie Bakouch, Gabriel Martín Blázquez, Guilherme Penedo, Lewis"},{"citing_arxiv_id":"2410.24164","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","primary_cat":"cs.LG","submitted_at":"2024-10-31T17:22:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"π₀ is a vision-language-action flow model trained on diverse multi-platform robot data that supports zero-shot task performance, language instruction following, and efficient fine-tuning for dexterous tasks.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"camera images and a 7-dimensional configuration and action space. Bimanual UR5e.Two UR5e setups, for a total of three camera images and a 14-dimensional configuration and action space. Franka.The Franka setup has two cameras and an 8- dimensional configuration and action space. Bimanual Trossen.This setup has two 6-DoF Trossen ViperX arms in a configuration based on the ALOHA setup [4, 57], with two wrist cameras and a base camera, and a 14- dimensional configuration and action space. Bimanual ARX & bimanual AgileX.This setup uses two 6-DoF arms, and supports either ARX or AgileX arms, with three cameras (two wrist and one base) and a 14-dimensional configuration and action space. This class encompasses two distinct platforms, but we categorize them together because of"},{"citing_arxiv_id":"2409.12514","ref_index":25,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation","primary_cat":"cs.RO","submitted_at":"2024-09-19T07:10:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"TinyVLA achieves faster inference and higher data efficiency than OpenVLA on robotic manipulation tasks by initializing from high-speed multimodal models and adding a diffusion policy decoder, without any pre-training phase.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}