{"total":17,"items":[{"citing_arxiv_id":"2607.01658","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Teaching Vision-Language-Action Models What to See and Where to Look","primary_cat":"cs.CV","submitted_at":"2026-07-02T03:34:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DriveTeach-VLA adds Driving-aware Vision Distillation pretraining and 2D Trajectory-Guided Prompts to VLA models, then reports state-of-the-art results on NAVSIM and nuScenes.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.18242","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"EventDrive: Event Cameras for Vision-Language Driving Intelligence","primary_cat":"cs.CV","submitted_at":"2026-06-16T17:58:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"EventDrive supplies a multi-task benchmark and EventDrive-VLM architecture that fuses event data, RGB, and language supervision, reporting gains in temporal precision and motion awareness for driving intelligence.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.02774","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"GeoDrive-Bench: Benchmarking Region-Specific Multimodal Reasoning in Autonomous Driving","primary_cat":"cs.CV","submitted_at":"2026-06-01T18:36:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"GeoDrive-Bench is a new multimodal benchmark and distillation method for testing and improving VLMs on region-specific traffic-rule reasoning in autonomous driving across six countries.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.31572","ref_index":57,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"nuReasoning: A Reasoning-Centric Dataset and Benchmark for Long-Tail Autonomous Driving","primary_cat":"cs.CV","submitted_at":"2026-05-29T17:40:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"nuReasoning is a new real-world dataset and benchmark extending nuScenes/nuPlan with 20k clips and multi-type reasoning annotations to evaluate and improve reasoning in long-tail autonomous driving.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.31041","ref_index":23,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Does Visual Information Play a Decisive Role in Vision-Language-Action Model Driving Behavior?","primary_cat":"cs.CV","submitted_at":"2026-05-29T09:18:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A structured perturbation framework applied to VLA driving models reveals evaluation-dependent visual grounding patterns and uneven dependency across abstraction levels.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21061","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Grounding Driving VLA via Inverse Kinematics","primary_cat":"cs.CV","submitted_at":"2026-05-20T11:45:32+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"By adding future visual state prediction and a dedicated inverse kinematics diffusion network that uses only visual boundary conditions, a 0.5B driving VLA recovers visual grounding and matches 7-8B models on NAVSIM-v2 and nuScenes.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.15120","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CLOVER: Closed-Loop Value Estimation and Ranking for End-to-End Autonomous Driving Planning","primary_cat":"cs.RO","submitted_at":"2026-05-14T17:32:18+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CLOVER is a closed-loop generator-scorer framework that expands proposal coverage with pseudo-expert trajectories and performs conservative self-distillation to achieve state-of-the-art planning scores on NAVSIM and nuScenes.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12624","ref_index":18,"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":"2604.24086","ref_index":21,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"AsyncShield: A Plug-and-Play Edge Adapter for Asynchronous Cloud-based VLA Navigation","primary_cat":"cs.RO","submitted_at":"2026-04-27T06:20:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"AsyncShield restores VLA geometric intent from latency via kinematic pose mapping and uses PPO-Lagrangian to balance tracking with LiDAR safety constraints in a plug-and-play module.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"lead to extremely high inference latency and network jitter. To alleviate the deployment bottleneck at the edge, existing research has primarily evolved along multiple trajectories. One approach lowers the computational threshold through model lightweighting, context compression, or post-training reinforcement learning fine-tuning (e.g., SmolVLA [20], ContextVLA [21], SimpleVLA-RL [22]). Another constructs a \"fast-slow dual-system\" hierarchical architecture (e.g., Mobility VLA [23], IROS Dual-Process [24]), or introduces world models with latent state spaces to enhance generalization (e.g., X-MOBILITY [25]). Particularly in the domain of cross-embodiment navigation, works such as X-Nav [26] explore the end-to-end distillation of"},{"citing_arxiv_id":"2604.22851","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"EgoDyn-Bench: Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving","primary_cat":"cs.CV","submitted_at":"2026-04-22T07:49:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"EgoDyn-Bench reveals a perception bottleneck in vision-centric foundation models: ego-motion logic derives from language while visual input adds negligible signal, with explicit trajectories restoring consistency.","context_count":1,"top_context_role":"baseline","top_context_polarity":"baseline","context_text":"5 42.7 28.7 48.0 99.5 InternVL3.5-8B[37] 100.0 47.0 38.8 30.0 42.7 33.5 48.6 78.0 InternVL3.5-38B[37] 100.0 46.5 37.6 26.8 44.8 27.0 72.6 72.4 Camreasoner-8B[41] 91.1 45.0 36.9 27.4 37.2 28.6 46.3 92.2 Cosmos Reason 2-2B[24] 100.0 46.2 35.1 23.6 39.5 25.8 72.7100.0 Cosmos Reason 2-8B[24] 100.0 48.8 39.9 35.8 41.0 36.7 92.2 80.6 VLA Models ImpromptuVLA[6] 100.0 47.3 37.8 28.9 40.2 29.2 41.1 72.8 RoboTron-Drive[13] 99.4 48.0 38.6 32.0 41.3 31.3 69.8 96.8 (i) Explicit Dynamics Consistently Improve Performance.Integrating explicit dynamics improves performance across all models and metrics, confirm- ing that the failures in Table 3 stem from a misalignment between visual obser- vations and physical motion concepts, not from an absence of physical reasoning"},{"citing_arxiv_id":"2604.18484","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"XEmbodied: A Foundation Model with Enhanced Geometric and Physical Cues for Large-Scale Embodied Environments","primary_cat":"cs.CV","submitted_at":"2026-04-20T16:37:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"XEmbodied is a foundation model that integrates 3D geometric and physical signals into VLMs using a 3D Adapter and Efficient Image-Embodied Adapter, plus progressive curriculum and RL post-training, to improve spatial reasoning and embodied performance on 18 benchmarks.","context_count":1,"top_context_role":"baseline","top_context_polarity":"baseline","context_text":"This improvement fully demonstrates that on the basis of the prior foundation model, our proposed XEmbodied-FT further optimizes the ability to handle downstream planning tasks. This is particularly evident in medium and long-term trajectory predic- tionaccuracyandshort-termdrivingsafety.Comparedwithotheradvancedtext- based models including EMMA+ [42], ImpromptuVLA [17], SOLVE-VLM [14] and FASIONAD [79,80], our XEmbodied-FT model still maintains obvious ad- vantages in long-horizon trajectory prediction at 2s and 3s. Its collision rate is also at a leading level. This confirms that our model can effectively adapt to the complex demands of text-based driving planning downstream tasks. It can understand natural language instructions and generate accurate and safe"},{"citing_arxiv_id":"2604.18483","ref_index":17,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Steadily moving semi-infinite fracture in plane poroelasticity","primary_cat":"physics.geo-ph","submitted_at":"2026-04-20T16:35:57+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":5.0,"formal_verification":"none","one_line_summary":"XEmbodied achieves SOTA on 18 embodied VQA benchmarks by fusing 3D geometric tokens and distilled physical cues into a 30B VLM with progressive curriculum training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.17915","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"OneDrive: Unified Multi-Paradigm Driving with Vision-Language-Action Models","primary_cat":"cs.CV","submitted_at":"2026-04-20T07:50:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"OneDrive unifies heterogeneous decoding in a single VLM transformer decoder for end-to-end driving, achieving 0.28 L2 error and 0.18 collision rate on nuScenes plus 86.8 PDMS on NAVSIM.","context_count":1,"top_context_role":"baseline","top_context_polarity":"baseline","context_text":"Method Reference L2 (m)↓ Col. Rate (%)↓ 1s2s3sAvg. 1s2s3sAvg. T ext-Based Driving Models DriveVLM [42] CoRL 2024 0.18 0.34 0.68 0.40 - - - - DriveVLM-Dual [42] CoRL 2024 0.15 0.29 0.48 0.31 - - - - OmniDrive [47] CVPR 2025 0.14 0.29 0.55 0.33 0.000.13 0.78 0.30 EMMA [22] TMLR 0.14 0.29 0.54 0.32 - - - - EMMA+ [22] TMLR 0.130.27 0.48 0.29 - - - - ImpromptuVLA [11]NeurIPS 2025 0.130.27 0.53 0.30 - - - - SOLVE-VLM [7] CVPR 2025 0.13 0.25 0.47 0.28 0.000.160.43 0.20 VGGDrive [44] CVPR 2026 0.14 0.28 0.51 0.31 0.020.100.55 0.22 Action-Based Driving Models UniAD† [20] CVPR 2023 0.59 1.01 1.48 1.03 0.16 0.51 1.64 0.77 VAD-Base† [26] ICCV 2023 0.69 1.22 1.83 1.25 0.06 0.68 2.52 1.09 BEV-Planner† [31] CVPR 2024 0.30 0."},{"citing_arxiv_id":"2604.09059","ref_index":16,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learning Vision-Language-Action World Models for Autonomous Driving","primary_cat":"cs.CV","submitted_at":"2026-04-10T07:38:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"VLA-World improves autonomous driving by using action-guided future image generation followed by reflective reasoning over the imagined scene to refine trajectories.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Liu, Zhenda Xie, Xingkai Yu, and Chong Ruan. Janus-pro: Unified multimodal understanding and generation with data and model scaling.arXiv preprint arXiv:2501.17811, 2025. 2 [15] Zhili Chen, Maosheng Ye, Shuangjie Xu, Tongyi Cao, and Qifeng Chen. Ppad: Iterative interactions of prediction and planning for end-to-end autonomous driving. InECCV, pages 239-256, 2024. 1 [16] Haohan Chi, Huan-ang Gao, Ziming Liu, Jianing Liu, Chenyu Liu, Jinwei Li, Kaisen Yang, Yangcheng Yu, Zeda Wang, Wenyi Li, et al. Impromptu vla: Open weights and open data for driving vision-language-action models.arXiv preprint arXiv:2505.23757, 2025. 1 [17] Danny Driess, Fei Xia, Mehdi SM Sajjadi, Corey Lynch, Aakanksha Chowdhery, Ayzaan Wahid, Jonathan Tompson,"},{"citing_arxiv_id":"2603.19675","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"DynFlowDrive: Flow-Based Dynamic World Modeling for Autonomous Driving","primary_cat":"cs.CV","submitted_at":"2026-03-20T06:19:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"DynFlowDrive models action-conditioned scene transitions via rectified flow in latent space and adds stability-aware trajectory selection, showing gains on nuScenes and NavSim without added inference cost.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2603.09465","ref_index":3,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"EvoDriveVLA: Evolving Driving VLA Models via Collaborative Perception-Planning Distillation","primary_cat":"cs.CV","submitted_at":"2026-03-10T10:19:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"EvoDriveVLA uses collaborative perception-planning distillation with self-anchor and future-aware teachers to fix perception degradation and long-term instability in driving VLA models, reaching SOTA on nuScenes and NAVSIM.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.00088","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail","primary_cat":"cs.RO","submitted_at":"2025-10-30T01:25:34+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Alpamayo-R1 introduces a VLA model with a Chain of Causation dataset and multi-stage SFT-plus-RL training that reports 12% better planning accuracy and 35% fewer close encounters versus trajectory-only baselines in driving tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}