{"list":"other","total":76,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"2410.24164","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","created":"2024-10-31","cited_by_count":2407},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2504.16054","title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","created":"2025-04-22","cited_by_count":1761},{"id":"2304.13705","title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","created":"2023-04-23","cited_by_count":1568},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2405.12213","title":"Octo: An Open-Source Generalist Robot Policy","created":"2024-05-20","cited_by_count":1484},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2306.03310","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","created":"2023-06-05","cited_by_count":1410},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2503.14734","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","created":"2025-03-18","cited_by_count":1225},{"id":"2506.09985","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","created":"2025-06-11","cited_by_count":809},{"id":"2501.09747","title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","created":"2025-01-16","cited_by_count":665},{"id":"2403.06764","title":"An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models","created":"2024-03-11","cited_by_count":642},{"id":"2506.01844","title":"SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics","created":"2025-06-02","cited_by_count":530},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"2501.15830","title":"SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model","created":"2025-01-27","cited_by_count":519},{"id":"2506.18088","title":"RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation","created":"2025-06-22","cited_by_count":518},{"id":"2411.19650","title":"CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation","created":"2024-11-29","cited_by_count":422},{"id":"2401.02117","title":"Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation","created":"2024-01-04","cited_by_count":391},{"id":"2311.12871","title":"An Embodied Generalist Agent in 3D World","created":"2023-11-18","cited_by_count":365},{"id":"2403.09631","title":"3D-VLA: A 3D Vision-Language-Action Generative World Model","created":"2024-03-14","cited_by_count":328},{"id":"2302.04659","title":"ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills","created":"2023-02-09","cited_by_count":327},{"id":"2412.10345","title":"TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies","created":"2024-12-13","cited_by_count":304},{"id":"2412.14803","title":"Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations","created":"2024-12-19","cited_by_count":289},{"id":"2504.02792","title":"Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets","created":"2025-04-03","cited_by_count":240},{"id":"2503.10631","title":"HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model","created":"2025-03-13","cited_by_count":181},{"id":"2412.15109","title":"Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulation","created":"2024-12-19","cited_by_count":161},{"id":"2505.23705","title":"Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better","created":"2025-05-29","cited_by_count":146},{"id":"2410.11831","title":"CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos","created":"2024-10-15","cited_by_count":128},{"id":"2304.02556","title":"Detecting and Grounding Multi-Modal Media Manipulation","created":"2023-04-05","cited_by_count":99},{"id":"2503.02310","title":"PD-VLA: Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decoding","created":"2025-03-04","cited_by_count":88},{"id":"2506.07961","title":"BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models","created":"2025-06-09","cited_by_count":80},{"id":"2406.08487","title":"Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models","created":"2024-06-12","cited_by_count":76},{"id":"2503.19757","title":"Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy","created":"2025-03-25","cited_by_count":74},{"id":"2508.21046","title":"CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification","created":"2025-08-28","cited_by_count":74},{"id":"2503.20384","title":"MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation","created":"2025-03-26","cited_by_count":70},{"id":"2508.09071","title":"GeoVLA: Empowering 3D Representations in Vision-Language-Action Models","created":"2025-08-12","cited_by_count":70},{"id":"2508.13073","title":"Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey","created":"2025-08-18","cited_by_count":69},{"id":"2503.03663","title":"LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant","created":"2025-03-05","cited_by_count":58},{"id":"2507.00416","title":"Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding","created":"2025-07-01","cited_by_count":58},{"id":"2309.14203","title":"Detecting and Grounding Multi-Modal Media Manipulation and Beyond","created":"2023-09-25","cited_by_count":56},{"id":"2506.22242","title":"4D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration","created":"2025-06-27","cited_by_count":56},{"id":"2411.18623","title":"Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulation","created":"2024-11-27","cited_by_count":46},{"id":"2505.16827","title":"GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent","created":"2025-05-22","cited_by_count":35},{"id":"2503.08950","title":"FP3: A 3D Foundation Policy for Robotic Manipulation","created":"2025-03-11","cited_by_count":32},{"id":"2504.02261","title":"WonderTurbo: Generating Interactive 3D World in 0.72 Seconds","created":"2025-04-03","cited_by_count":32},{"id":"2509.14117","title":"GeoAware-VLA: Implicit Geometry Aware Vision-Language-Action Model","created":"2025-09-17","cited_by_count":26},{"id":"2512.00903","title":"SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead","created":"2025-11-30","cited_by_count":26},{"id":"2502.19902","title":"Optimus-2: Multimodal Minecraft Agent with Goal-Observation-Action Conditioned Policy","created":"2025-02-27","cited_by_count":25},{"id":"2505.17098","title":"TACO: Enhancing Multimodal In-context Learning via Task Mapping-Guided Sequence Configuration","created":"2025-05-21","cited_by_count":23},{"id":"2512.12812","title":"Does Tone Change the Answer? Evaluating Prompt Politeness Effects on Modern LLMs: GPT, Gemini, and LLaMA","created":"2025-12-14","cited_by_count":23},{"id":"2511.10518","title":"SemanticVLA: Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation","created":"2025-11-13","cited_by_count":21},{"id":"2501.16297","title":"FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers","created":"2025-01-27","cited_by_count":20},{"id":"2602.20200","title":"Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation","created":"2026-02-22","cited_by_count":20},{"id":"2507.23372","title":"UniEmo: Unifying Emotional Understanding and Generation with Learnable Expert Queries","created":"2025-07-31","cited_by_count":18},{"id":"2410.10394","title":"PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic Manipulation","created":"2024-10-14","cited_by_count":17},{"id":"2511.17079","title":"H-GAR: A Hierarchical Interaction Framework via Goal-Driven Observation-Action Refinement for Robotic Manipulation","created":"2025-11-21","cited_by_count":17},{"id":"2601.09636","title":"PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records","created":"2026-01-14","cited_by_count":16},{"id":"2506.10357","title":"Optimus-3: Dual-Router Aligned Mixture-of-Experts Agent with Dual-Granularity Reasoning-Aware Policy Optimization","created":"2025-06-12","cited_by_count":13},{"id":"2512.01763","title":"HiconAgent: History Context-aware Policy Optimization for GUI Agents","created":"2025-12-01","cited_by_count":13},{"id":"2507.08064","title":"PUMA: Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning","created":"2025-07-10","cited_by_count":11},{"id":"2603.26746","title":"TDEC: Deep Embedded Image Clustering with Transformer and Distribution Information","created":"2026-03-23","cited_by_count":3},{"id":"2604.03306","title":"Deep Image Clustering Based on Curriculum Learning and Density Information","created":"2026-03-31","cited_by_count":1}],"next_cursor":null}