{"total":28,"items":[{"citing_arxiv_id":"2606.30552","ref_index":34,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Training Vision-Language-Action Models with Dense Embodied Chain-of-Thought Supervision","primary_cat":"cs.RO","submitted_at":"2026-06-29T16:48:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ZR-0 is a dual-stream VLA model trained with dense ECoT supervision on 60M frames from 400K trajectories to enable cross-embodiment transfer in simulation and real-world settings.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.30686","ref_index":48,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Position: Vision-Language-Action Models Cannot Be Verified to Perform Physical Reasoning","primary_cat":"cs.RO","submitted_at":"2026-06-28T14:03:57+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"VLA benchmark success rates cannot distinguish semantic generalization from physical reasoning due to an identifiability gap in current evaluation protocols.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.23685","ref_index":36,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LaST-HD: Learning Latent Physical Reasoning from Scalable Human Data for Robot Manipulation","primary_cat":"cs.RO","submitted_at":"2026-06-22T17:59:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"LaST-HD creates a shared latent dynamics space via a world model to transfer physical reasoning from scalable human-hand demonstrations to robots, achieving over 90% accuracy with 20 minutes of new data after mixed training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.13102","ref_index":59,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"FTP-1: A Generalist Foundation Tactile Policy Across Tactile Sensors for Contact-Rich Manipulation","primary_cat":"cs.RO","submitted_at":"2026-06-11T09:30:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"FTP-1 is the first foundation tactile policy pretrained on ~3000 hours of data from 26 sources across 21 sensors that improves performance on seen setups by 17.2% and transfers to unseen sensors with 31% success rate gain.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.12475","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learning to Assist: Collaborative VLAs for Implicit Human-Robot Collaboration","primary_cat":"cs.RO","submitted_at":"2026-06-10T05:42:49+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"VLA models with inference-time steering mitigate action leakage in implicit human-robot collaboration, supporting longer horizons and yielding faster, more reliable assembly than shorter-horizon baselines in a 16-person study.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.07100","ref_index":18,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LARA: Latent Action Representation Alignment for Vision-Language-Action Models","primary_cat":"cs.CV","submitted_at":"2026-06-05T09:51:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LARA jointly optimizes LAM and VLA models via representation alignment to improve robotic manipulation performance using human videos.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.30877","ref_index":86,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Wall-OSS-0.5 Technical Report","primary_cat":"cs.RO","submitted_at":"2026-05-29T06:04:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Wall-OSS-0.5 is a 4B VLA model pretrained across many embodiments that achieves zero-shot real-robot performance on a 17-task suite and outperforms π_0.5 after fine-tuning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.22816","ref_index":27,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation","primary_cat":"cs.RO","submitted_at":"2026-05-21T17:58:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"AwareVLN introduces a structural reasoning module and automatic data engine with progress division to equip VLN agents with self-awareness of agent state and task progress, outperforming prior methods on Habitat datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.22812","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"GesVLA: Gesture-Aware Vision-Language-Action Model Embedded Representations","primary_cat":"cs.RO","submitted_at":"2026-05-21T17:57:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"GesVLA encodes gesture features directly into the latent space of VLA models using a dual-VLM architecture and a rendering-based data pipeline, yielding improved target grounding in real robotic tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.10942","ref_index":34,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Models","primary_cat":"cs.RO","submitted_at":"2026-05-11T17:59:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"HarmoWAM unifies predictive and reactive control in world action models via an adaptive gating mechanism to deliver improved zero-shot generalization and precision in robotic manipulation.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[32] Junbang Liang, Pavel Tokmakov, Ruoshi Liu, Sruthi Sudhakar, Paarth Shah, Rares Ambrus, and Carl V ondrick. Video generators are robot policies, 2025. [33] Yue Liao, Pengfei Zhou, Siyuan Huang, Donglin Yang, Shengcong Chen, Yuxin Jiang, Yue Hu, Jingbin Cai, Si Liu, Jianlan Luo, Liliang Chen, Shuicheng Yan, Maoqing Yao, and Guanghui Ren. Genie envisioner: A unified world foundation platform for robotic manipulation, 2025. [34] Fanqi Lin, Ruiqian Nai, Yingdong Hu, Jiacheng You, Junming Zhao, and Yang Gao. Onet- wovla: A unified vision-language-action model with adaptive reasoning.arXiv preprint arXiv:2505.11917, 2025. [35] Jiaming Liu, Hao Chen, Pengju An, Zhuoyang Liu, Renrui Zhang, Chenyang Gu, Xiaoqi Li, Ziyu Guo, Sixiang Chen, Mengzhen Liu, et al. Hybridvla: Collaborative diffusion and"},{"citing_arxiv_id":"2605.07381","ref_index":23,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation","primary_cat":"cs.RO","submitted_at":"2026-05-08T07:35:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Anchor-Centric Adaptation escapes the diversity trap by prioritizing repeated demonstrations at core anchors over broad coverage, yielding higher success rates under fixed data budgets in robotic manipulation.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Extensions beyond this surrogate require additional stability assumptions and are discussed below. A.2.1. COVERAGE-DENSITYDECOMPOSITION Proposition A.3(Coverage-density decomposition).Suppose Assumptions A.1 and A.2 hold. Then for any evaluation distributionνover(z, t), sup p∈P E(z,t)∼ν,ξ \u0002 ∥ ˆf(z, p, t)−f ⋆(z, p, t)∥ \u0003 ≤max 1≤i≤K E(z,t)∼ν,ξ \u0002 ∥ ˆf(z, p i, t)−f ⋆(z, pi, t)∥ \u0003 +Lh K.(23) The same inequality also holds pointwise for any fixed(z, t)if the expectation over(z, t)∼νis removed. Proof.Fix anyp∈ Pand any(z, t). By Assumption A.2, ˆf(z, p, t) = ˆf(z, p i(p), t).(24) The triangle inequality gives ∥ ˆf(z, p, t)−f ⋆(z, p, t)∥ ≤ ∥ ˆf(z, p i(p), t)−f ⋆(z, pi(p), t)∥(25) +∥f ⋆(z, pi(p), t)−f ⋆(z, p, t)∥.(26) Assumption A.1 and the definition ofh K imply"},{"citing_arxiv_id":"2605.07308","ref_index":31,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"AT-VLA: Adaptive Tactile Injection for Enhanced Feedback Reaction in Vision-Language-Action Models","primary_cat":"cs.RO","submitted_at":"2026-05-08T06:17:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"AT-VLA proposes adaptive tactile injection and a dual-stream tactile reaction mechanism to enhance VLA models for contact-rich robotic manipulation with real-time responses.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Pattern Recognition, pages 18061-18070, 2024. [30] Xiaoqi Li, Jingyun Xu, Mingxu Zhang, Jiaming Liu, Yan Shen, Iaroslav Ponomarenko, Jiahui Xu, Liang Heng, Siyuan Huang, Shanghang Zhang, et al. Object-centric prompt-driven vision-language-action model for robotic manipulation. In Proceedings of the IEEE/CVF Conference on Computer Vi- sion and Pattern Recognition, pages 27638-27648, 2025. [31] Fanqi Lin, Ruiqian Nai, Yingdong Hu, Jiacheng You, Jun- ming Zhao, and Yang Gao. Onetwovla: A unified vision- language-action model with adaptive reasoning.arXiv preprint arXiv:2505.11917, 2025. [32] Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. Visual instruction tuning.Advances in neural information processing systems, 36:34892-34916, 2023."},{"citing_arxiv_id":"2605.02600","ref_index":16,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CoRAL: Contact-Rich Adaptive LLM-based Control for Robotic Manipulation","primary_cat":"cs.RO","submitted_at":"2026-05-04T13:49:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"CoRAL lets LLMs act as adaptive cost designers for motion planners while using VLM priors and online identification to handle unknown physics, achieving over 50% higher success rates than baselines in unseen contact-rich robotic scenarios.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"dependent and often brittle in novel physical scenarios in- volving complex contact dynamics. To overcome this, emerg- ing frameworks decouple high-level reasoning from low-level control. ThinkAct [8], Inner Monologue [9], and ECoT [32] leverage LLMs to generate reasoning steps guiding separate, learned policies. Similarly, MolmoAct [15] produces mid- level spatial plans, while OneTwoVLA [16] formalizes this as System 1 (acting) and System 2 (reasoning). CoRAL aligns with this decoupling but takes a distinct neuro-symbolic path: we ground LLM reasoning directly in a controller rather than a learned model. Integrating Foundation Models with Motion Planners and Controllers.Alternatively, foundation models can guide traditional motion planners using semantic understanding."},{"citing_arxiv_id":"2605.01194","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model","primary_cat":"cs.RO","submitted_at":"2026-05-02T02:13:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"VLA-ATTC equips VLA models with adaptive test-time compute via an uncertainty clutch and relative action critic, cutting failure rates by over 50% on LIBERO-LONG.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"The RAC is a Transformer of depth L, matching the VLM backbone's depth. Each layer l∈[1, L] of the RAC up- dates its input X l−1 through a sophisticated three-branch attention block, as depicted in Fig. 4. 1.Self-Attention (SA):The first branch computes self- attention over the RAC's own representations: Ol sa =Attention(Q(X l−1), K(X l−1), V(X l−1))(13) 2.Raw Cross-Attention:The second branch injects broad contextual information by attending to raw features of the corresponding layerlin the VLM backbone,F l vlm: Ol raw =Attention(Q(X l−1), K(F l vlm), V(F l vlm))(14) 3.Query Cross-Attention:The third branch attends to the specialized, distilled context features from the VLM's learnable query tokens from the same layerl,F l"},{"citing_arxiv_id":"2605.00438","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Thinking in Text and Images: Interleaved Vision--Language Reasoning Traces for Long-Horizon Robot Manipulation","primary_cat":"cs.AI","submitted_at":"2026-05-01T06:15:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A multimodal transformer generates and caches interleaved text-image traces to guide closed-loop actions, achieving 92.4% success on LIBERO-Long and 95.5% average on LIBERO.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Jieyu Zhang, Yi Ru Wang, Sangho Lee, et al. Molmoact: Action reasoning models that can reason in space. arXiv preprint arXiv:2508.07917, 2025. [14] Xuanlin Li, Kyle Hsu, Jiayuan Gu, Karl Pertsch, Oier Mees, Homer Rich Walke, Chuyuan Fu, Ishikaa Lunawat, Isabel Sieh, Sean Kirmani, et al. Evaluating real-world robot manipulation policies in simulation. arXiv preprint arXiv:2405.05941, 2024. [15] Fanqi Lin, Ruiqian Nai, Yingdong Hu, Jiacheng Y ou, Junming Zhao, and Y ang Gao. Onet- wovla: A unified vision-language-action model with adaptive reasoning. arXiv preprint arXiv:2505.11917, 2025. [16] Bo Liu, Yifeng Zhu, Chongkai Gao, Yihao Feng, Qiang Liu, Y uke Zhu, and Peter Stone. Libero: Benchmarking knowledge transfer for lifelong robot learning."},{"citing_arxiv_id":"2604.28192","ref_index":14,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoning","primary_cat":"cs.RO","submitted_at":"2026-04-30T17:59:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LaST-R1 introduces a RL post-training method called LAPO that optimizes latent Chain-of-Thought reasoning in vision-language-action models, yielding 99.9% success on LIBERO and up to 22.5% real-world gains.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[12] Angen Ye, Zeyu Zhang, Boyuan Wang, Xiaofeng Wang, Dapeng Zhang, and Zheng Zhu. Vla-r1: Enhancing reasoning in vision-language-action models.arXiv preprint arXiv:2510.01623, 2025. [13] Chi-Pin Huang, Yueh-Hua Wu, Min-Hung Chen, Yu-Chiang Frank Wang, and Fu-En Yang. Thinkact: Vision-language-action reasoning via reinforced visual latent planning.arXiv preprint arXiv:2507.16815, 2025. [14] Fanqi Lin, Ruiqian Nai, Yingdong Hu, Jiacheng You, Junming Zhao, and Yang Gao. Onet- wovla: A unified vision-language-action model with adaptive reasoning.arXiv preprint arXiv:2505.11917, 2025. [15] Michał Zawalski, William Chen, Karl Pertsch, Oier Mees, Chelsea Finn, and Sergey Levine. Robotic control via embodied chain-of-thought reasoning.arXiv preprint arXiv:2407."},{"citing_arxiv_id":"2605.00078","ref_index":45,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Being-H0.7: A Latent World-Action Model from Egocentric Videos","primary_cat":"cs.RO","submitted_at":"2026-04-30T14:16:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Being-H0.7 adds future-aware latent reasoning to direct VLA policies via dual-branch alignment on latent queries, matching world-model benefits at VLA efficiency.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[43] Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. Chain-of-thought prompting elicits reasoning in large language models.Advances in neural information processing systems, 35:24824-24837, 2022. [44] Michał Zawalski, William Chen, Karl Pertsch, Oier Mees, Chelsea Finn, and Sergey Levine. Robotic control via embodied chain-of-thought reasoning.arXiv preprint arXiv:2407.08693, 2024. [45] Fanqi Lin, Ruiqian Nai, Yingdong Hu, Jiacheng You, Junming Zhao, and Yang Gao. Onetwovla: A unified vision-language-action model with adaptive reasoning.arXiv preprint arXiv:2505.11917, 2025. [46] Jaden Clark, Suvir Mirchandani, Dorsa Sadigh, and Suneel Belkhale. Action-free reasoning for policy generaliza- tion.arXiv preprint arXiv:2502.03729, 2025."},{"citing_arxiv_id":"2604.20834","ref_index":27,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PokeVLA: Empowering Pocket-Sized Vision-Language-Action Model with Comprehensive World Knowledge Guidance","primary_cat":"cs.RO","submitted_at":"2026-04-22T17:58:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"PokeVLA is a lightweight VLA model pre-trained on 2.4M samples for spatial grounding and reasoning, then adapted via multi-view semantics and geometry alignment to achieve state-of-the-art robot manipulation performance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.15483","ref_index":32,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"${\\pi}_{0.7}$: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities","primary_cat":"cs.LG","submitted_at":"2026-04-16T19:18:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"π₀.₇ is a steerable generalist robotic model that uses rich multimodal prompts including language, subgoal images, and performance metadata to achieve out-of-the-box generalization across tasks and robot bodies.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Memer: Scaling up memory for robot control via experience retrieval.arXiv preprint arXiv:2510.20328, 2025. [31] Hao Shi, Bin Xie, Yingfei Liu, Lin Sun, Fengrong Liu, Tiancai Wang, Erjin Zhou, Haoqiang Fan, Xi- angyu Zhang, and Gao Huang. Memoryvla: Perceptual- cognitive memory in vision-language-action models for robotic manipulation.arXiv preprint arXiv:2508.19236, 2025. [32] Fanqi Lin, Ruiqian Nai, Yingdong Hu, Jiacheng You, Junming Zhao, and Yang Gao. Onetwovla: A unified vision-language-action model with adaptive reasoning. arXiv preprint arXiv:2505.11917, 2025. [33] Haoquan Fang, Markus Grotz, Wilbert Pumacay, Yi Ru Wang, Dieter Fox, Ranjay Krishna, and Jiafei Duan. Sam2act: Integrating visual foundation model with a"},{"citing_arxiv_id":"2604.09330","ref_index":39,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"VAG: Dual-Stream Video-Action Generation for Embodied Data Synthesis","primary_cat":"cs.RO","submitted_at":"2026-04-10T13:59:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"VAG is a synchronized dual-stream flow-matching framework that generates aligned video-action pairs for synthetic embodied data synthesis and policy pretraining.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"21998, 2026. 2 [37] Shuang Li, Yihuai Gao, Dorsa Sadigh, and Shuran Song. Unified video action model.arXiv preprint arXiv:2503.00200, 2025. 2, 3 [38] Wei Li, Renshan Zhang, Rui Shao, Jie He, and Liqiang Nie. Cogvla: Cognition-aligned vision-language-action model via instruction-driven routing & sparsification.arXiv preprint arXiv:2508.21046, 2025. 2 [39] Fanqi Lin, Ruiqian Nai, Yingdong Hu, Jiacheng You, Jun- ming Zhao, and Yang Gao. Onetwovla: A unified vision- language-action model with adaptive reasoning.arXiv preprint arXiv:2505.11917, 2025. 2 [40] Yaron Lipman, Ricky TQ Chen, Heli Ben-Hamu, Maximil- ian Nickel, and Matt Le. Flow matching for generative mod- eling.arXiv preprint arXiv:2210.02747, 2022."},{"citing_arxiv_id":"2602.19710","ref_index":22,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Universal Pose Pretraining for Generalizable Vision-Language-Action Policies","primary_cat":"cs.CV","submitted_at":"2026-02-23T11:00:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Pose-VLA uses a decoupled two-stage pre-training with discrete pose tokens to extract universal 3D spatial priors from 3D datasets and robotic trajectories, achieving 79.5% success on RoboTwin 2.0 and 96.0% on LIBERO.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.12978","ref_index":22,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learning Native Continuation for Action Chunking Flow Policies","primary_cat":"cs.RO","submitted_at":"2026-02-13T14:56:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Legato trains flow-based VLA policies with schedule-shaped action-noise mixtures and randomized conditions to achieve smoother trajectories and ~10% faster task completion than real-time chunking across five real-world manipulation tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.09725","ref_index":45,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Efficient Remote KV Cache Reuse with GPU-native Video Codec","primary_cat":"cs.DC","submitted_at":"2026-02-10T12:29:02+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"KVCodec uses GPU-native video codecs and pipelined fetching to compress and transmit KV caches, delivering up to 3.51x faster TTFT than prior methods while preserving accuracy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.09023","ref_index":31,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TwinRL: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulation","primary_cat":"cs.RO","submitted_at":"2026-02-09T18:59:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"TwinRL expands RL exploration via digital twin reconstruction and twin RL warm-up to guide real-world learning, reaching near-100% success with 20 minutes of on-robot time across four tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.15669","ref_index":22,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models","primary_cat":"cs.LG","submitted_at":"2025-10-31T05:26:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DeepThinkVLA shows CoT improves VLA models only under decoding and causal alignment, delivering 97% success on LIBERO and 21.7-point gains via hybrid attention and SFT-RL training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2510.13778","ref_index":23,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy","primary_cat":"cs.RO","submitted_at":"2025-10-15T17:30:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"InternVLA-M1 uses spatially guided pre-training on 2.3M examples followed by action post-training to deliver up to 17% gains on robot manipulation benchmarks and 20.6% on unseen objects.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2508.13073","ref_index":139,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey","primary_cat":"cs.RO","submitted_at":"2025-08-18T16:45:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"This survey organizes large VLM-based VLA models for robotic manipulation into monolithic and hierarchical paradigms, reviews their integrations and datasets, and outlines future directions.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Its backbone weights are initialized from a pre- trained VLM. To handle robot-specific inputs and action generation, a second set of independent weights, the flow- matching-based action expert, is introduced and trained from scratch. ForceVLA [138] uses π0 [29] as the base model, the FVLMoE module with MoE is used to introduce the force modality into VLA. OneTwoVLA [139] is based on π0 [29] and can switch between two modes: explicitly reasoning and generating actions based on the most recent reasoning. This architecture makes it easier for the two systems to operate asynchronously and further improves efficiency. Many innovations are built upon this. π0.5 [30] builds on π0 [29] by introducing an additional step. The VLA"},{"citing_arxiv_id":"2507.04447","ref_index":99,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge","primary_cat":"cs.CV","submitted_at":"2025-07-06T16:14:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DreamVLA uses dynamic-region-guided world knowledge prediction, block-wise attention to disentangle information types, and a diffusion transformer for actions, reaching 76.7% success on real robot tasks and 4.44 average length on CALVIN ABC-D.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Open-sora: Democratizing efficient video production for all. arXiv preprint arXiv:2412.20404, 2024. 3 [98] Zhongyi Zhou, Yichen Zhu, Minjie Zhu, Junjie Wen, Ning Liu, Zhiyuan Xu, Weibin Meng, Ran Cheng, Yaxin Peng, Chaomin Shen, et al. Chatvla: Unified multimodal understanding and robot control with vision-language-action model. arXiv preprint arXiv:2502.14420, 2025. 3 [99] Fanqi Lin, Ruiqian Nai, Yingdong Hu, Jiacheng You, Junming Zhao, and Yang Gao. Onet- wovla: A unified vision-language-action model with adaptive reasoning. arXiv preprint arXiv:2505.11917, 2025. [100] Lucy Xiaoyang Shi, Brian Ichter, Michael Equi, Liyiming Ke, Karl Pertsch, Quan Vuong, James Tanner, Anna Walling, Haohuan Wang, Niccolo Fusai, et al."}],"limit":50,"offset":0}