{"total":86,"rows":[{"id":"2510.07077","title":"Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications","created":"2025-10-08","cited_by_count":84,"area":"mllm"},{"id":"2506.12723","title":"SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration","created":"2025-06-15","cited_by_count":58,"area":"vla"},{"id":"2509.19012","title":"Pure Vision Language Action (VLA) Models: A Comprehensive Survey","created":"2025-09-23","cited_by_count":49,"area":"mllm"},{"id":"2509.05614","title":"SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning","created":"2025-09-06","cited_by_count":43,"area":"vla"},{"id":"2506.13725","title":"CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding","created":"2025-06-16","cited_by_count":38,"area":"vla"},{"id":"2509.22093","title":"Action-aware Dynamic Pruning for Efficient Vision-Language-Action Manipulation","created":"2025-09-26","cited_by_count":34,"area":"vla"},{"id":"2510.24795","title":"A Survey on Efficient Vision-Language-Action Models","created":"2025-10-27","cited_by_count":34,"area":"vla"},{"id":"2505.21200","title":"Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models","created":"2025-05-27","cited_by_count":30,"area":"vla"},{"id":"2506.17639","title":"RLRC: Reinforcement Learning-based Recovery for Compressed Vision-Language-Action Models","created":"2025-06-21","cited_by_count":23,"area":"vla"},{"id":"2509.02055","title":"Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidance","created":"2025-09-02","cited_by_count":20,"area":"vla"},{"id":"2602.07845","title":"Recurrent-Depth VLA: Implicit Test-Time Compute Scaling of Vision-Language-Action Models via Latent Iterative Reasoning","created":"2026-02-08","cited_by_count":18,"area":"lr"},{"id":"2511.16449","title":"Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference","created":"2025-11-20","cited_by_count":17,"area":"vla"},{"id":"2509.09090","title":"SQAP-VLA: A Synergistic Quantization-Aware Pruning Framework for High-Performance Vision-Language-Action Models","created":"2025-09-11","cited_by_count":15,"area":"vla"},{"id":"2603.07904","title":"DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-Action Models","created":"2026-03-09","cited_by_count":12,"area":"vla"},{"id":"2607.27205","title":"TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM","created":"2026-07-29","cited_by_count":10,"area":"vla"},{"id":"2605.01194","title":"VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model","created":"2026-05-02","cited_by_count":9,"area":"lr"},{"id":"2601.20262","title":"Shallow-{\\pi}: Knowledge Distillation for Flow-based VLAs","created":"2026-01-28","cited_by_count":8,"area":"vla"},{"id":"2604.05672","title":"A1: A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Model","created":"2026-04-07","cited_by_count":8,"area":"vla"},{"id":"2604.24447","title":"Characterizing Vision-Language-Action Models across XPUs: Constraints and Acceleration for On-Robot Deployment","created":"2026-04-27","cited_by_count":7,"area":"vla"},{"id":"2509.23655","title":"Focusing on What Matters: Object-Agent-centric Tokenization for Vision Language Action models","created":"2025-09-28","cited_by_count":6,"area":"vla"},{"id":"2601.19634","title":"AC^2-VLA: Action-Context-Aware Adaptive Computation in Vision-Language-Action Models for Efficient Robotic Manipulation","created":"2026-01-27","cited_by_count":6,"area":"vla"},{"id":"2603.28565","title":"StreamingVLA: Streaming Vision-Language-Action Model with Action Flow Matching and Adaptive Early Observation","created":"2026-03-30","cited_by_count":6,"area":"vla"},{"id":"2603.28740","title":"FocusVLA: Focused Visual Utilization for Vision-Language-Action Models","created":"2026-03-30","cited_by_count":6,"area":"vla"},{"id":"2511.11298","title":"Experiences from Benchmarking Vision-Language-Action Models for Robotic Manipulation","created":"2025-11-14","cited_by_count":5,"area":"vla"},{"id":"2601.14945","title":"TIDAL: Temporally Interleaved Diffusion and Action Loop for High-Frequency VLA Control","created":"2026-01-21","cited_by_count":5,"area":"vla"},{"id":"2602.15882","title":"PACT-WAM: Predicting Actions and Visual Foresight with Compact Temporal Encoding for Robot Manipulation","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2507.15428","title":"EgoPrune: Efficient Token Pruning for Egomotion Video Reasoning in Embodied Agent","created":"2025-07-21","cited_by_count":4,"area":"lr"},{"id":"2603.14371","title":"OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelism","created":"2026-03-15","cited_by_count":4,"area":"inference"},{"id":"2604.24622","title":"CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies","created":"2026-04-27","cited_by_count":4,"area":"vla"},{"id":"2605.01191","title":"Sentinel-VLA: A Metacognitive VLA Model with Active Status Monitoring for Dynamic Reasoning and Error Recovery","created":"2026-05-02","cited_by_count":4,"area":"vla"},{"id":"2605.02739","title":"Latent Bridge: Feature Delta Prediction for Efficient Dual-System Vision-Language-Action Model Inference","created":"2026-05-04","cited_by_count":4,"area":"vla"},{"id":"2605.11817","title":"See What Matters: Differentiable Grid Sample Pruning for Generalizable Vision-Language-Action Model","created":"2026-05-12","cited_by_count":4,"area":"vla"},{"id":"2608.11671","title":"StellaVLA: In-Context Structured Demonstration for Generalizable Vision-Language-Action Models","created":"2026-08-12","cited_by_count":4,"area":"vla"},{"id":"2608.27384","title":"FlashVLA: Streaming Action Decoding for Fast and Asynchronous VLA Inference","created":"2026-08-27","cited_by_count":4,"area":"vla"},{"id":"2508.17449","title":"Robotic Manipulation via Imitation Learning: Taxonomy, Evolution, Benchmark, and Challenges","created":"2025-08-24","cited_by_count":3,"area":"offlinerl"},{"id":"2605.13548","title":"AttenA+: Rectifying Action Inequality in Robotic Foundation Models","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2605.29662","title":"SAFE-Pruner: Semantic Attention-Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation","created":"2026-05-28","cited_by_count":3,"area":"vla"},{"id":"2606.23581","title":"Kamera: Unified Position-Invariant Multimodal KV Cache for Training-Free Reuse","created":"2026-06-22","cited_by_count":3,"area":"inference"},{"id":"2607.14695","title":"Reflex: Real-Time VLA Control through Streaming Inference","created":"2026-07-16","cited_by_count":3,"area":"vla"},{"id":"2603.20843","title":"HiCI: Hierarchical Construction-Integration for Long-Context Attention","created":"2026-03-21","cited_by_count":2,"area":null},{"id":"2605.02757","title":"Seeing Realism from Simulation: Efficient Video Transfer for Vision-Language-Action Data Augmentation","created":"2026-05-04","cited_by_count":2,"area":"vla"},{"id":"2606.02775","title":"AURA: Action-Gated Memory for Robot Policies at Constant VRAM","created":"2026-06-01","cited_by_count":2,"area":"inference"},{"id":"2606.22540","title":"PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models","created":"2026-06-21","cited_by_count":2,"area":"vla"},{"id":"2606.31382","title":"Revisiting Parameter Redundancy in Vision-Language-Action Models: Insights from VLM-to-VLA Adaptation","created":"2026-06-30","cited_by_count":2,"area":"mllm"},{"id":"2607.02501","title":"Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots","created":"2026-07-02","cited_by_count":2,"area":"wm"},{"id":"2607.06370","title":"ActionCache: Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement","created":"2026-07-07","cited_by_count":2,"area":"vla"},{"id":"2608.00391","title":"The Gate, Not the Cache: Gate Provenance Bounds the Closed-Loop Reliability of Training-Free VLA Token Skipping","created":"2026-08-01","cited_by_count":2,"area":null},{"id":"2609.06079","title":"LayerRoute: Action-Conditioned Mixture-of-Layers Routing for Vision-Language-Action Policies","created":"2026-09-05","cited_by_count":2,"area":"mllm"},{"id":"2609.18374","title":"Decoupling Vision, Language, and Action for Efficient Multi-Task Robot Policies","created":"2026-09-16","cited_by_count":2,"area":"mllm"},{"id":"2603.10469","title":"DepthCache: Depth-Guided Training-Free Visual Token Merging for Vision-Language-Action Model Inference","created":"2026-03-11","cited_by_count":1,"area":"vla"},{"id":"2605.11459","title":"Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models","created":"2026-05-12","cited_by_count":1,"area":"vla"},{"id":"2606.16253","title":"Learned Image Compression for Vision-Language-Action Models","created":"2026-06-15","cited_by_count":1,"area":"vla"},{"id":"2606.20246","title":"Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think","created":"2026-06-18","cited_by_count":1,"area":"vla"},{"id":"2606.28529","title":"The Speedup Paradox: Rethinking Inference Speed-Quality Trade-off in Embodied Tasks","created":"2026-06-26","cited_by_count":1,"area":null},{"id":"2608.01428","title":"When Replanning Becomes the Bottleneck: Budgeted Replanning for Embodied Agents","created":"2026-08-02","cited_by_count":1,"area":"agents"},{"id":"2608.01573","title":"Uncovering and Mitigating Positional Blind Spots in Vision-Language-Action Models","created":"2026-08-03","cited_by_count":1,"area":"vla"},{"id":"2608.03682","title":"PhyAI: Real-Time Physical AI at the Edge, Scalable Rollouts in the Cloud","created":"2026-08-04","cited_by_count":1,"area":"deeprl"},{"id":"2608.10824","title":"Neural Introspection Gating for Adaptive KV-Cache Reuse in Vision-Language-Action Models","created":"2026-08-11","cited_by_count":1,"area":"vla"},{"id":"2604.05323","title":"VLA-InfoEntropy: A Training-Free Vision-Attention Information Entropy Approach for Vision-Language-Action Models Inference Acceleration and Success","created":"2026-04-07","cited_by_count":0,"area":"vla"},{"id":"2604.09244","title":"2D or 3D: Who Governs Salience in VLA Models? -- Tri-Stage Token Pruning Framework with Modality Salience Awareness","created":"2026-04-10","cited_by_count":0,"area":"vla"},{"id":"2608.12932","title":"FlashDrive: Flash Vision-Language-Action Inference for Autonomous Driving","created":"2026-08-13","cited_by_count":0,"area":"vla"},{"id":"2608.15636","title":"Algorithm-Architecture Co-Design for Efficient VLA Inference via Speculative Inference and Verification","created":"2026-08-16","cited_by_count":0,"area":"vla"},{"id":"2608.16074","title":"US-VLA: An Ultrasound Vision-Language-Action Model for Embodied Abdomina","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.21247","title":"Just Noticeable Difference Modeling for Token Compression in Vision-Language-Action Models","created":"2026-08-21","cited_by_count":0,"area":"mllm"},{"id":"2608.25308","title":"V-Link: Recovering Lost Visual Representations in Action DiT for Vision-Language-Action Models","created":"2026-08-26","cited_by_count":0,"area":"vla"},{"id":"2608.27079","title":"GRAFT: Grounded and Efficient Online Reinforcement Adaptation for Fine-Grained Robot Manipulation","created":"2026-08-27","cited_by_count":0,"area":"vla"},{"id":"2609.12075","title":"Efficient Vision-Language-Action Management and Serving for Robot Factories","created":"2026-09-10","cited_by_count":0,"area":"mllm"},{"id":"2609.16503","title":"Dense to MoE Adaptation for Compact Vision Language Action Policies","created":"2026-09-15","cited_by_count":0,"area":"vla"},{"id":"2609.18663","title":"VLA-ULAP: Interleaving Cloud VLA Calls with Ultra-Lightweight Local Action Prediction at the Edge","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.19104","title":"rMuscle: Robotic Muscle Memory for Efficient Vision-Language-Action Model Inference","created":"2026-09-16","cited_by_count":0,"area":"vla"},{"id":"2609.22335","title":"KerColle: Unlocking Fine-Grained GPU Concurrency in Vision-Language-Action Models","created":"2026-09-16","cited_by_count":0,"area":"vla"},{"id":"2609.22684","title":"StateMem: Single-State Residual Memory with Adaptive Inference for Vision-Language-Action Policies","created":"2026-09-19","cited_by_count":0,"area":"vla"},{"id":"2609.29382","title":"Decoupled Early Exits for Task-Dependent Compute Allocation in Flow-Matching VLAs","created":"2026-09-24","cited_by_count":0,"area":"mllm"},{"id":"2609.33007","title":"CAPEX: Efficiently Distilling Foundation Model Behavior into Deployable Robot Policies through Experience-Adaptive Reasoning","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.34175","title":"FailPatch: Failure Residual Patching for Vision-Language-Action Models","created":"2026-09-28","cited_by_count":0,"area":"vla"},{"id":"2609.34319","title":"Text-Vision Synergistic Token Caching: A Training-Free Framework for Efficient Vision-Language-Action Inference","created":"2026-09-28","cited_by_count":0,"area":"vla"},{"id":"2609.34911","title":"Don't Throw Away the Tail: Action Upcycling for Policy Acceleration","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36934","title":"VLALight: A Vision-Language-Action Model for Traffic Signal Control","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.36967","title":"Beyond Token Importance: Preserving Spatial Scaffolds for Efficient Vision-Language-Action Inference","created":"2026-09-29","cited_by_count":0,"area":"vla"},{"id":"2609.38984","title":"Sparse-WAM: Accelerating World Action Models via Action-Guided Sparse Imagination","created":"2026-09-30","cited_by_count":0,"area":"wm"},{"id":"2610.02666","title":"CHASE-VLA: Post-Training Quantization Framework for Vision-Language-Action Models with Chunk-Aware Scale Estimation","created":"2026-10-02","cited_by_count":0,"area":"vla"},{"id":"2610.05273","title":"When and What to Prune? Stage-Aware Visual Token Pruning for Efficient VLA","created":"2026-10-04","cited_by_count":0,"area":"mllm"},{"id":"2610.08444","title":"ActTune: Action-Aware Precision and GPU Operating-Point Adaptation for Energy-Efficient Vision-Language-Action Inference","created":"2026-10-06","cited_by_count":0,"area":"vla"},{"id":"2610.11401","title":"WAM-Cache: Staleness-Bounded KV Reuse for Efficient World Action Models","created":"2026-10-08","cited_by_count":0,"area":"wm"},{"id":"2610.17141","title":"MARS: Systematic Multi-Level Acceleration for World Action Models","created":"2026-10-12","cited_by_count":0,"area":"wm"},{"id":"2610.17540","title":"TacitVLA: Reasoning Vision-Language-Action Models Without Reasoning Latency","created":"2026-10-13","cited_by_count":0,"area":"vla"}],"next_cursor":null}