{"list":"other","total":78,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"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":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"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":"1807.03888","title":"A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks","created":"2018-07-10","cited_by_count":1485},{"id":"2306.03310","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","created":"2023-06-05","cited_by_count":1410},{"id":"2503.14734","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","created":"2025-03-18","cited_by_count":1225},{"id":"2601.03267","title":"OpenAI GPT-5 System Card","created":"2025-12-19","cited_by_count":989},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819},{"id":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751},{"id":"2501.09747","title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","created":"2025-01-16","cited_by_count":665},{"id":"2304.13734","title":"The Internal State of an LLM Knows When It's Lying","created":"2023-04-26","cited_by_count":659},{"id":"2204.06507","title":"Out-of-Distribution Detection with Deep Nearest Neighbors","created":"2022-04-13","cited_by_count":600},{"id":"1801.04264","title":"Real-world Anomaly Detection in Surveillance Videos","created":"2018-01-12","cited_by_count":577},{"id":"2501.15830","title":"SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model","created":"2025-01-27","cited_by_count":519},{"id":"2602.15922","title":"World Action Models are Zero-shot Policies","created":"2026-02-17","cited_by_count":465},{"id":"2402.00253","title":"A Survey on Hallucination in Large Vision-Language Models","created":"2024-02-01","cited_by_count":357},{"id":"2402.03744","title":"INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection","created":"2024-02-06","cited_by_count":323},{"id":"2310.00754","title":"Analyzing and Mitigating Object Hallucination in Large Vision-Language Models","created":"2023-10-01","cited_by_count":316},{"id":"2502.02013","title":"Layer by Layer: Uncovering Hidden Representations in Language Models","created":"2025-02-04","cited_by_count":311},{"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":"2511.14759","title":"$\\pi^{*}_{0.6}$: a VLA That Learns From Experience","created":"2025-11-18","cited_by_count":303},{"id":"2209.15558","title":"Out-of-Distribution Detection and Selective Generation for Conditional Language Models","created":"2022-09-30","cited_by_count":197},{"id":"2412.18194","title":"VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks","created":"2024-12-24","cited_by_count":175},{"id":"1612.03365","title":"Multiple Instance Learning: A Survey of Problem Characteristics and Applications","created":"2016-12-11","cited_by_count":164},{"id":"2411.16724","title":"Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens","created":"2024-11-23","cited_by_count":143},{"id":"2506.19850","title":"Unified Vision-Language-Action Model","created":"2025-06-24","cited_by_count":134},{"id":"2507.05331","title":"A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulation","created":"2025-07-07","cited_by_count":129},{"id":"2410.00371","title":"AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation","created":"2024-10-01","cited_by_count":125},{"id":"1704.00138","title":"Multiple Instance Detection Network with Online Instance Classifier Refinement","created":"2017-04-01","cited_by_count":117},{"id":"1807.08364","title":"EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning","created":"2018-07-22","cited_by_count":100},{"id":"2409.17504","title":"HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection","created":"2024-09-26","cited_by_count":99},{"id":"2104.07918","title":"Weakly Supervised Object Localization and Detection: A Survey","created":"2021-04-16","cited_by_count":84},{"id":"2511.17502","title":"RynnVLA-002: A Unified Vision-Language-Action and World Model","created":"2025-11-21","cited_by_count":74},{"id":"2411.11919","title":"VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimation","created":"2024-11-18","cited_by_count":73},{"id":"1904.05647","title":"C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection","created":"2019-04-11","cited_by_count":71},{"id":"2410.04640","title":"Unpacking Failure Modes of Generative Policies: Runtime Monitoring of Consistency and Progress","created":"2024-10-06","cited_by_count":69},{"id":"2407.08735","title":"Real-Time Anomaly Detection and Reactive Planning with Large Language Models","created":"2024-07-11","cited_by_count":68},{"id":"2510.20328","title":"MemER: Scaling Up Memory for Robot Control via Experience Retrieval","created":"2025-10-23","cited_by_count":67},{"id":"2603.03596","title":"MEM: Multi-Scale Embodied Memory for Vision Language Action Models","created":"2026-03-04","cited_by_count":61},{"id":"1910.13601","title":"Deep Weakly-supervised Anomaly Detection","created":"2019-10-30","cited_by_count":59},{"id":"2405.02917","title":"Overconfidence is Key: Verbalized Uncertainty Evaluation in Large Language and Vision-Language Models","created":"2024-05-05","cited_by_count":54},{"id":"2503.08558","title":"Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning Policies","created":"2025-03-11","cited_by_count":52},{"id":"2503.01917","title":"Steer LLM Latents for Hallucination Detection","created":"2025-03-01","cited_by_count":50},{"id":"2510.09459","title":"Failure Prediction at Runtime for Generative Robot Policies","created":"2025-10-10","cited_by_count":42},{"id":"2601.03309","title":"VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Models","created":"2026-01-06","cited_by_count":39},{"id":"2310.17552","title":"Model-Based Runtime Monitoring with Interactive Imitation Learning","created":"2023-10-26","cited_by_count":38},{"id":"2410.22689","title":"Multi-Task Interactive Robot Fleet Learning with Visual World Models","created":"2024-10-30","cited_by_count":36},{"id":"2505.00779","title":"Uncertainty-aware Latent Safety Filters for Avoiding Out-of-Distribution Failures","created":"2025-05-01","cited_by_count":33},{"id":"2101.01364","title":"Run-Time Monitoring of Machine Learning for Robotic Perception: A Survey of Emerging Trends","created":"2021-01-05","cited_by_count":26},{"id":"2510.05681","title":"Verifier-free Test-Time Sampling for Vision-Language-Action Models","created":"2025-10-07","cited_by_count":23},{"id":"2302.04549","title":"Weakly Supervised Anomaly Detection: A Survey","created":"2023-02-09","cited_by_count":22},{"id":"2202.05894","title":"Failure Prediction with Statistical Guarantees for Vision-Based Robot Control","created":"2022-02-11","cited_by_count":21},{"id":"2504.00907","title":"Grounding Multimodal LLMs to Embodied Agents that Ask for Help with Reinforcement Learning","created":"2025-04-01","cited_by_count":21},{"id":"2602.05073","title":"Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities","created":"2026-02-04","cited_by_count":20},{"id":"2504.07863","title":"Robust Hallucination Detection in LLMs via Adaptive Token Selection","created":"2025-04-10","cited_by_count":19},{"id":"2102.06746","title":"The Importance of Being a Band: Finite-Sample Exact Distribution-Free Prediction Sets for Functional Data","created":"2021-02-12","cited_by_count":16},{"id":"2502.11948","title":"HalluEntity: Benchmarking and Understanding Entity-Level Hallucination Detection","created":"2025-02-17","cited_by_count":13},{"id":"2508.19972","title":"GLSim: Detecting Object Hallucinations in LVLMs via Global-Local Similarity","created":"2025-08-27","cited_by_count":11},{"id":"2603.11106","title":"RC-NF: Robot-Conditioned Normalizing Flow for Real-Time Anomaly Detection in Robotic Manipulation","created":"2026-03-11","cited_by_count":8},{"id":"2307.16415","title":"DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action Localization","created":"2023-07-31","cited_by_count":7},{"id":"2602.12405","title":"Self-Refining Vision Language Model for Robotic Failure Detection and Reasoning","created":"2026-02-12","cited_by_count":7},{"id":"2205.10906","title":"Monitoring of Perception Systems: Deterministic, Probabilistic, and Learning-based Fault Detection and Identification","created":"2022-05-22","cited_by_count":6},{"id":"2102.07165","title":"Corrective Shared Autonomy for Addressing Task Variability","created":"2021-02-14","cited_by_count":5},{"id":"2602.21054","title":"VAUQ: Vision-Aware Uncertainty Quantification for LVLM Self-Evaluation","created":"2026-02-24","cited_by_count":5},{"id":"2602.22474","title":"When to Act, Ask, or Learn: Uncertainty-Aware Policy Steering","created":"2026-02-25","cited_by_count":5},{"id":"2509.15061","title":"Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue","created":"2025-09-18","cited_by_count":4},{"id":"2512.11362","title":"An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges","created":"2025-12-12","cited_by_count":4},{"id":"2504.09243","title":"REALM: Real-Time Estimates of Assistance for Learned Models in Human-Robot Interaction","created":"2025-04-12","cited_by_count":3},{"id":"2512.21430","title":"EVE: A Generator-Verifier System for Generative Policies","created":"2025-12-24","cited_by_count":3},{"id":"2503.07317","title":"Self-Corrective Task Planning by Inverse Prompting with Large Language Models","created":"2025-03-10","cited_by_count":2}],"next_cursor":null}