{"total":20,"items":[{"citing_arxiv_id":"2607.00666","ref_index":52,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts","primary_cat":"cs.RO","submitted_at":"2026-07-01T09:13:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DART adapts VLA models to environmental shifts with one demonstration using subspace-aligned weight vector arithmetic.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.27268","ref_index":29,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulation","primary_cat":"cs.RO","submitted_at":"2026-06-25T16:50:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"E-TTS introduces a plug-and-play test-time scaling method for embodied tasks that unifies reasoning-action sampling with history buffers and closed-loop refinement to improve performance on manipulation benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.22794","ref_index":31,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"UniFS: Unified Fast-to-Slow Hierarchical Architecture for Vision-Language-Action Models","primary_cat":"cs.RO","submitted_at":"2026-06-22T03:10:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"UniFS achieves 98.3% success on LIBERO with 2.1x lower latency than prior fast-slow VLA models by stratifying VLM layer update frequencies, inverting latent interactions, and applying multi-level supervision.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.20867","ref_index":53,"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":"2606.13497","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SPARC: Reliable Spatial Annotations from Robot Demonstrations at Scale","primary_cat":"cs.RO","submitted_at":"2026-06-11T15:46:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"SPARC generates reliable spatial annotations for robot demonstrations by leveraging spatio-temporal task structure, outperforming detection baselines on localization accuracy while retaining more samples and enabling competitive model performance without manual annotations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.11324","ref_index":51,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models","primary_cat":"cs.RO","submitted_at":"2026-06-09T18:07:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Embodied-R1.5 is an 8B EFM achieving SOTA on 16 of 24 embodied VLM benchmarks, fine-tunable to outperform leading VLAs, with claimed zero-shot real-robot generalization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.08520","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Two Bridges, One Pathway: From VLMs to Generalizable VLAs with Embodied Trajectory-Coupled Data","primary_cat":"cs.RO","submitted_at":"2026-06-07T08:57:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Introduces embodied trajectory-coupled data and a three-stage training recipe to bridge VLMs to generalizable VLAs without steep degradation of pre-trained representations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.03784","ref_index":42,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Revisiting Embodied Chain-of-Thought for Generalizable Robot Manipulation","primary_cat":"cs.RO","submitted_at":"2026-06-02T15:37:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ERVLA trains on a 978k-trajectory embodied CoT corpus using reasoning as supervision with dropout, then predicts actions without CoT at test time, reaching 86.9% on LIBERO-Plus and 53.2% on VLABench.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.02307","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"FATE-VLA:Failue-aware test generation for vision-language-action models","primary_cat":"cs.RO","submitted_at":"2026-06-01T14:27:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FATE-VLA reframes VLA evaluation as active failure discovery and reports uncovering up to 29.7% more failures across four models while revealing diverse failure modes.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.28548","ref_index":57,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"GEM: Generative Supervision Helps Embodied Intelligence","primary_cat":"cs.CV","submitted_at":"2026-05-27T14:39:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"GEM adds generative depth supervision to VLM pre-training and reports improved results on embodied benchmarks plus real-world robot execution.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.25802","ref_index":29,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Rethinking VLM Representation for VLA Initialization","primary_cat":"cs.CV","submitted_at":"2026-05-25T12:51:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Experiments indicate original VLM representations are crucial for VLA performance, LoRA outperforms full finetuning, and staged robot-data pretraining yields the strongest initialization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21414","ref_index":53,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interaction","primary_cat":"cs.RO","submitted_at":"2026-05-20T17:10:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"PointACT proposes a 3D-aware dual-system VLA policy using multi-scale point-action interaction with bottleneck window self-attention, achieving 10% higher success rates on RLBench-10Tasks over prior pretrained VLAs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12624","ref_index":68,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MindVLA-U1: VLA Beats VA with Unified Streaming Architecture for Autonomous Driving","primary_cat":"cs.RO","submitted_at":"2026-05-12T18:09:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MindVLA-U1 is the first unified streaming VLA architecture that surpasses human drivers on WOD-E2E planning metrics while matching VA latency and preserving language interfaces.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00438","ref_index":20,"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":"closed-loop action decoding. Relation to concurrent structured VLA reasoning. Several recent systems expose intermediate reasoning or perceptual tokens. CoT-VLA emphasizes visual chain-of-thought for action reason- ing [ 31]; dVLA and UniVLA unify multimodal and action token streams [ 25, 24]; EO-1 studies interleaved vision-text-action pretraining [ 20]; MolmoAct uses depth-aware perception tokens and editable spatial plans [ 13]. Table 1 abstracts these systems by design axis rather than ranking them by capability. IVLR is distinguished along four dimensions: it generates a full-horizon trace rather than only local intermediate cues; it interleaves text subgoals with RGB visual keyframes rather"},{"citing_arxiv_id":"2604.18000","ref_index":46,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Unmasking the Illusion of Embodied Reasoning in Vision-Language-Action Models","primary_cat":"cs.RO","submitted_at":"2026-04-20T09:25:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"State-of-the-art vision-language-action models catastrophically fail dynamic embodied reasoning due to lexical-kinematic shortcuts, behavioral inertia, and semantic feature collapse caused by architectural bottlenecks, as shown by the new BeTTER benchmark with real-world validation.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Mimicgen: A data generation system for scalable robot learning using human demonstrations.arXiv preprint arXiv:2310.17596, 2023. [45] Xinyi Chen, Yilun Chen, Yanwei Fu, Ning Gao, Jiaya Jia, Weiyang Jin, Hao Li, Yao Mu, Jiangmiao Pang, Yu Qiao, et al. Internvla-m1: A spatially guided vision-language-action framework for generalist robot policy. arXiv preprint arXiv:2510.13778, 2025. [46] Delin Qu, Haoming Song, Qizhi Chen, Zhaoqing Chen, Xianqiang Gao, Xinyi Ye, Qi Lv, Modi Shi, Guanghui Ren, Cheng Ruan, et al. Eo-1: Interleaved vision-text-action pretraining for general robot control.arXiv preprint arXiv:2508.21112, 2025. [47] BAAI RoboBrain Team, Mingyu Cao, Huajie Tan, Yuheng Ji, Xiansheng Chen, Minglan Lin, Zhiyu Li, Zhou Cao,"},{"citing_arxiv_id":"2604.12273","ref_index":42,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SubFlow: Sub-mode Conditioned Flow Matching for Diverse One-Step Generation","primary_cat":"cs.LG","submitted_at":"2026-04-14T04:36:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"SubFlow restores full mode coverage in one-step flow matching by conditioning on sub-modes from semantic clustering, yielding higher diversity on ImageNet-256 while preserving FID.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"truncation trick explicitly trades sample variety for fidelity [2]. In diffusion models, strong classifier-free guidance (CFG) sharpens im- age quality at the expense of mode coverage [18, 23, 57]. A common thread in prior work is to attribute this degradation toinference-time design choices and to propose inference-time remedies accordingly, such as condition-annealed sampling [42]. In contrast, the diversity loss we study is rooted in thetraining objectiveitself: when the target distribution is multi-modal, class-conditional MSE regres- sion produces a velocity field inherently biased toward dominant sub-modes, regardless of the number of sampling steps. Meanwhile, clustering and mixture decompositions have been incorporated into generative modeling in various forms, including"},{"citing_arxiv_id":"2604.03181","ref_index":20,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Multi-View Video Diffusion Policy: A 3D Spatio-Temporal-Aware Video Action Model","primary_cat":"cs.RO","submitted_at":"2026-04-03T16:57:06+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MV-VDP jointly predicts multi-view RGB and heatmap videos via diffusion to achieve data-efficient, robust robotic manipulation policies.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[18] Tianhe Yu, Deirdre Quillen, Zhanpeng He, Ryan Julian, Karol Hausman, Chelsea Finn, and Sergey Levine. Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning. InConference on robot learning, pages 1094-1100. PMLR, 2020. [19] Spirit AI Team. Spirit-v1.5: Clean data is the enemy of great robot foundation models.Spirit AI Blog, 2026. https://www.spirit-ai.com/en/blog/spirit-v1-5. [20] Delin Qu, Haoming Song, Qizhi Chen, Zhaoqing Chen, Xianqiang Gao, Xinyi Ye, Qi Lv, Modi Shi, Guanghui Ren, Cheng Ruan, et al. Eo-1: Interleaved vision-text-action pretraining for general robot control.arXiv preprint arXiv:2508.21112, 2025. [21] Xinghang Li, Peiyan Li, Minghuan Liu, Dong Wang, Jirong Liu, Bingyi Kang, Xiao Ma, Tao Kong, Hanbo Zhang, and Huaping Liu."},{"citing_arxiv_id":"2602.19710","ref_index":32,"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":30,"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":"2511.14148","ref_index":54,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Models","primary_cat":"cs.RO","submitted_at":"2025-11-18T05:21:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"AsyncVLA adds asynchronous flow matching and a confidence rater to VLA models so they can generate actions on flexible schedules and selectively refine low-confidence tokens before execution.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}