{"list":"other","total":72,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"id":"1511.07289","title":"Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)","created":"2015-11-23","cited_by_count":1070},{"id":"2212.04088","title":"LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models","created":"2022-12-08","cited_by_count":462},{"id":"2207.04429","title":"LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action","created":"2022-07-10","cited_by_count":439},{"id":"2210.05714","title":"Visual Language Maps for Robot Navigation","created":"2022-10-11","cited_by_count":365},{"id":"1911.00357","title":"DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames","created":"2019-11-01","cited_by_count":362},{"id":"2410.17434","title":"LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding","created":"2024-10-22","cited_by_count":356},{"id":"2301.04195","title":"Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments","created":"2023-01-10","cited_by_count":295},{"id":"2305.16986","title":"NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models","created":"2023-05-26","cited_by_count":280},{"id":"2310.07896","title":"NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration","created":"2023-10-11","cited_by_count":248},{"id":"2402.15852","title":"NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation","created":"2024-02-24","cited_by_count":233},{"id":"2306.14846","title":"ViNT: A Foundation Model for Visual Navigation","created":"2023-06-26","cited_by_count":222},{"id":"2507.04447","title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge","created":"2025-07-06","cited_by_count":213},{"id":"2412.04453","title":"NaVILA: Legged Robot Vision-Language-Action Model for Navigation","created":"2024-12-05","cited_by_count":211},{"id":"2312.03275","title":"VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation","created":"2023-12-06","cited_by_count":205},{"id":"2210.03370","title":"GNM: A General Navigation Model to Drive Any Robot","created":"2022-10-07","cited_by_count":171},{"id":"2406.04882","title":"InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environment","created":"2024-06-07","cited_by_count":157},{"id":"2412.06224","title":"Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks","created":"2024-12-09","cited_by_count":156},{"id":"2309.11382","title":"Discuss Before Moving: Visual Language Navigation via Multi-expert Discussions","created":"2023-09-20","cited_by_count":110},{"id":"2407.12366","title":"NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models","created":"2024-07-17","cited_by_count":98},{"id":"2303.06594","title":"ChatGPT Asks, BLIP-2 Answers: Automatic Questioning Towards Enriched Visual Descriptions","created":"2023-03-12","cited_by_count":86},{"id":"2309.10309","title":"Bridging Zero-shot Object Navigation and Foundation Models through Pixel-Guided Navigation Skill","created":"2023-09-19","cited_by_count":77},{"id":"2401.17583","title":"Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion","created":"2024-01-31","cited_by_count":73},{"id":"2509.12129","title":"Embodied Navigation Foundation Model","created":"2025-09-15","cited_by_count":72},{"id":"2306.01874","title":"SACSoN: Scalable Autonomous Control for Social Navigation","created":"2023-06-02","cited_by_count":61},{"id":"2407.10943","title":"GRUtopia: Dream General Robots in a City at Scale","created":"2024-07-15","cited_by_count":59},{"id":"2406.20083","title":"PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators","created":"2024-06-28","cited_by_count":58},{"id":"1903.02749","title":"Deep Visual MPC-Policy Learning for Navigation","created":"2019-03-07","cited_by_count":56},{"id":"2505.08712","title":"NavDP: Learning Sim-to-Real Navigation Diffusion Policy with Privileged Information Guidance","created":"2025-05-13","cited_by_count":49},{"id":"2312.02976","title":"SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World","created":"2023-12-05","cited_by_count":48},{"id":"2505.23189","title":"TrackVLA: Embodied Visual Tracking in the Wild","created":"2025-05-29","cited_by_count":47},{"id":"2310.00982","title":"ViPlanner: Visual Semantic Imperative Learning for Local Navigation","created":"2023-10-02","cited_by_count":46},{"id":"2502.13143","title":"SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation","created":"2025-02-18","cited_by_count":46},{"id":"2411.17820","title":"CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos","created":"2024-11-26","cited_by_count":41},{"id":"2410.09874","title":"ImagineNav: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination","created":"2024-10-13","cited_by_count":38},{"id":"2509.19480","title":"OmniVLA: An Omni-Modal Vision-Language-Action Model for Robot Navigation","created":"2025-09-23","cited_by_count":38},{"id":"1909.12329","title":"Scaling Local Control to Large-Scale Topological Navigation","created":"2019-09-26","cited_by_count":37},{"id":"2302.11434","title":"iPlanner: Imperative Path Planning","created":"2023-02-22","cited_by_count":37},{"id":"2411.02530","title":"A Comprehensive Study on Quantization Techniques for Large Language Models","created":"2024-10-30","cited_by_count":36},{"id":"2509.25687","title":"OmniNav: A Unified Framework for Prospective Exploration and Visual-Language Navigation","created":"2025-09-30","cited_by_count":36},{"id":"2410.03603","title":"LeLaN: Learning A Language-Conditioned Navigation Policy from In-the-Wild Videos","created":"2024-10-04","cited_by_count":32},{"id":"2502.14254","title":"Mem2Ego: Empowering Vision-Language Models with Global-to-Ego Memory for Long-Horizon Embodied Navigation","created":"2025-02-20","cited_by_count":30},{"id":"2508.10416","title":"CorrectNav: Self-Correction Flywheel Empowers Vision-Language-Action Navigation Model","created":"2025-08-14","cited_by_count":27},{"id":"2409.15634","title":"NavRL: Learning Safe Flight in Dynamic Environments","created":"2024-09-24","cited_by_count":26},{"id":"2506.00411","title":"LoHoVLA: A Unified Vision-Language-Action Model for Long-Horizon Embodied Tasks","created":"2025-05-31","cited_by_count":26},{"id":"2507.13019","title":"Rethinking the Embodied Gap in Vision-and-Language Navigation: A Holistic Study of Physical and Visual Disparities","created":"2025-07-17","cited_by_count":25},{"id":"2509.10813","title":"InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts","created":"2025-09-13","cited_by_count":20},{"id":"2412.14401","title":"The One RING: a Robotic Indoor Navigation Generalist","created":"2024-12-18","cited_by_count":16},{"id":"2409.15783","title":"AnyCar to Anywhere: Learning Universal Dynamics Model for Agile and Adaptive Mobility","created":"2024-09-24","cited_by_count":13},{"id":"2505.05592","title":"Learning to Drive Anywhere with Model-Based Reannotation","created":"2025-05-08","cited_by_count":13},{"id":"2507.22028","title":"From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning","created":"2025-07-29","cited_by_count":12},{"id":"2509.17430","title":"EmbodiedSplat: Personalized Real-to-Sim-to-Real Navigation with Gaussian Splats from a Mobile Device","created":"2025-09-22","cited_by_count":12},{"id":"2504.19322","title":"Learned Perceptive Forward Dynamics Model for Safe and Platform-aware Robotic Navigation","created":"2025-04-27","cited_by_count":11},{"id":"2508.14466","title":"LookOut: Real-World Humanoid Egocentric Navigation","created":"2025-08-20","cited_by_count":9},{"id":"2502.16372","title":"COMPASS: Cross-embodiment Mobility Policy via Residual RL and Skill Synthesis","created":"2025-02-22","cited_by_count":8},{"id":"2503.18525","title":"RoboTron-Nav: A Unified Framework for Embodied Navigation Integrating Perception, Planning, and Prediction","created":"2025-03-24","cited_by_count":8},{"id":"2505.19214","title":"Omni-Perception: Omnidirectional Collision Avoidance for Legged Locomotion in Dynamic Environments","created":"2025-05-25","cited_by_count":8},{"id":"2407.11487","title":"PRET: Planning with Directed Fidelity Trajectory for Vision and Language Navigation","created":"2024-07-16","cited_by_count":7},{"id":"2507.08831","title":"View Invariant Learning for Vision-Language Navigation in Continuous Environments","created":"2025-07-05","cited_by_count":6},{"id":"2508.05634","title":"Towards Generalizable Safety in Crowd Navigation via Conformal Uncertainty Handling","created":"2025-08-07","cited_by_count":6},{"id":"2411.14770","title":"Aim My Robot: Precision Local Navigation to Any Object","created":"2024-11-22","cited_by_count":5},{"id":"2507.14731","title":"X-Nav: Learning End-to-End Cross-Embodiment Navigation for Mobile Robots","created":"2025-07-19","cited_by_count":5},{"id":"2508.01539","title":"HALO: Human Preference Aligned Offline Reward Learning for Robot Navigation","created":"2025-08-03","cited_by_count":5},{"id":"2407.14758","title":"DISCO: Embodied Navigation and Interaction via Differentiable Scene Semantics and Dual-level Control","created":"2024-07-20","cited_by_count":4}],"next_cursor":null}