{"list":"other","total":75,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2404.16821","title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","created":"2024-04-25","cited_by_count":1050},{"id":"2106.08265","title":"Towards Total Recall in Industrial Anomaly Detection","created":"2021-06-15","cited_by_count":776},{"id":"2302.00923","title":"Multimodal Chain-of-Thought Reasoning in Language Models","created":"2023-02-02","cited_by_count":752},{"id":"2309.14525","title":"Aligning Large Multimodal Models with Factually Augmented RLHF","created":"2023-09-25","cited_by_count":712},{"id":"2011.08785","title":"PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization","created":"2020-11-17","cited_by_count":594},{"id":"2211.11559","title":"Visual Programming: Compositional visual reasoning without training","created":"2022-11-18","cited_by_count":516},{"id":"2108.07610","title":"DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection","created":"2021-08-17","cited_by_count":514},{"id":"2503.21776","title":"Video-R1: Reinforcing Video Reasoning in MLLMs","created":"2025-03-27","cited_by_count":484},{"id":"2207.14315","title":"SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation","created":"2022-07-28","cited_by_count":400},{"id":"2310.12823","title":"AgentTuning: Enabling Generalized Agent Abilities for LLMs","created":"2023-10-19","cited_by_count":338},{"id":"2303.14814","title":"WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation","created":"2023-03-26","cited_by_count":315},{"id":"1807.02011","title":"Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders","created":"2018-07-05","cited_by_count":264},{"id":"2310.05915","title":"FireAct: Toward Language Agent Fine-tuning","created":"2023-10-09","cited_by_count":256},{"id":"2503.07536","title":"LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL","created":"2025-03-10","cited_by_count":248},{"id":"2111.07677","title":"FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows","created":"2021-11-15","cited_by_count":227},{"id":"2501.07542","title":"Imagine while Reasoning in Space: Multimodal Visualization-of-Thought","created":"2025-01-13","cited_by_count":206},{"id":"2311.05437","title":"LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents","created":"2023-11-09","cited_by_count":193},{"id":"2110.02855","title":"Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection","created":"2021-10-06","cited_by_count":117},{"id":"2507.07998","title":"PyVision: Agentic Vision with Dynamic Tooling","created":"2025-07-10","cited_by_count":79},{"id":"2312.03052","title":"Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models","created":"2023-12-05","cited_by_count":66},{"id":"2403.19646","title":"Change-Agent: Towards Interactive Comprehensive Remote Sensing Change Interpretation and Analysis","created":"2024-03-28","cited_by_count":63},{"id":"2502.12119","title":"PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection","created":"2025-02-17","cited_by_count":61},{"id":"2403.11614","title":"CRS-Diff: Controllable Remote Sensing Image Generation with Diffusion Model","created":"2024-03-18","cited_by_count":55},{"id":"2505.13408","title":"CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning Process","created":"2025-05-19","cited_by_count":51},{"id":"2412.15280","title":"Context-DPO: Aligning Language Models for Context-Faithfulness","created":"2024-12-18","cited_by_count":50},{"id":"2509.19012","title":"Pure Vision Language Action (VLA) Models: A Comprehensive Survey","created":"2025-09-23","cited_by_count":49},{"id":"2501.00895","title":"Text2Earth: Unlocking Text-driven Remote Sensing Image Generation with a Global-Scale Dataset and a Foundation Model","created":"2025-01-01","cited_by_count":48},{"id":"2503.15888","title":"Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models","created":"2025-03-20","cited_by_count":39},{"id":"2003.03972","title":"Cross-View Tracking for Multi-Human 3D Pose Estimation at over 100 FPS","created":"2020-03-09","cited_by_count":36},{"id":"2405.11613","title":"Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts","created":"2024-05-19","cited_by_count":36},{"id":"2411.15497","title":"AeroGen: Enhancing Remote Sensing Object Detection with Diffusion-Driven Data Generation","created":"2024-11-23","cited_by_count":35},{"id":"2504.11914","title":"AnomalyR1: A GRPO-based End-to-end MLLM for Industrial Anomaly Detection","created":"2025-04-16","cited_by_count":28},{"id":"2510.08480","title":"Video-STAR: Reinforcing Open-Vocabulary Action Recognition with Tools","created":"2025-10-09","cited_by_count":26},{"id":"2503.11892","title":"DecAlign: Hierarchical Cross-Modal Alignment for Decoupled Multimodal Representation Learning","created":"2025-03-14","cited_by_count":24},{"id":"2509.04338","title":"From Editor to Dense Geometry Estimator","created":"2025-09-04","cited_by_count":24},{"id":"2604.18037","title":"HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrieval","created":"2026-04-20","cited_by_count":24},{"id":"2504.10358","title":"FingER: Content Aware Fine-grained Evaluation with Reasoning for AI-Generated Videos","created":"2025-04-14","cited_by_count":22},{"id":"2511.12344","title":"Reward and Guidance through Rubrics: Promoting Exploration to Improve Multi-Domain Reasoning","created":"2025-11-15","cited_by_count":21},{"id":"2310.04148","title":"Self-Supervised Neuron Segmentation with Multi-Agent Reinforcement Learning","created":"2023-10-06","cited_by_count":19},{"id":"2412.12704","title":"MapExpert: Online HD Map Construction with Simple and Efficient Sparse Map Element Expert","created":"2024-12-17","cited_by_count":17},{"id":"2507.03253","title":"RefineX: Learning to Refine Pre-training Data at Scale from Expert-Guided Programs","created":"2025-07-04","cited_by_count":17},{"id":"2604.20358","title":"ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval","created":"2026-04-22","cited_by_count":17},{"id":"2601.15224","title":"PROGRESSLM: Towards Progress Reasoning in Vision-Language Models","created":"2026-01-21","cited_by_count":15},{"id":"2604.21806","title":"TEMA: Anchor the Image, Follow the Text for Multi-Modification Composed Image Retrieval","created":"2026-04-23","cited_by_count":15},{"id":"2511.19912","title":"Reasoning-VLA: A Fast and General Vision-Language-Action Reasoning Model for Autonomous Driving","created":"2025-11-25","cited_by_count":14},{"id":"2501.02519","title":"Layout2Scene: 3D Semantic Layout Guided Scene Generation via Geometry and Appearance Diffusion Priors","created":"2025-01-05","cited_by_count":13},{"id":"2508.09822","title":"Physical Autoregressive Model for Robotic Manipulation without Action Pretraining","created":"2025-08-13","cited_by_count":12},{"id":"2503.12218","title":"Adaptive Label Correction for Robust Medical Image Segmentation with Noisy Labels","created":"2025-03-15","cited_by_count":8},{"id":"2603.00141","title":"From Scale to Speed: Adaptive Test-Time Scaling for Image Editing","created":"2026-02-24","cited_by_count":8},{"id":"2605.15153","title":"Pelican-Unify 1.0: A Unified Embodied Intelligence Model for Understanding, Reasoning, Imagination and Action","created":"2026-05-14","cited_by_count":8},{"id":"2511.19914","title":"CoC-VLA: Delving into Adversarial Domain Transfer for Explainable Autonomous Driving via Chain-of-Causality Visual-Language-Action Model","created":"2025-11-25","cited_by_count":7},{"id":"2508.17703","title":"EMPOWER: Evolutionary Medical Prompt Optimization With Reinforcement Learning","created":"2025-08-25","cited_by_count":6},{"id":"2510.27237","title":"Fusion of Multi-scale Heterogeneous Pathology Foundation Models for Whole Slide Image Analysis","created":"2025-10-31","cited_by_count":5},{"id":"2602.22963","title":"FactGuard: Agentic Video Misinformation Detection via Reinforcement Learning","created":"2026-02-26","cited_by_count":5},{"id":"2605.11723","title":"CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating","created":"2026-05-12","cited_by_count":5},{"id":"2512.13671","title":"AgentIAD: Agentic Industrial Anomaly Detection via Adaptive Memory Augmentation","created":"2025-12-15","cited_by_count":4},{"id":"2603.03143","title":"Edit in 2D, Verify in 3D: Reinforcement Learning for Multi-view Consistent Scene Editing","created":"2026-03-03","cited_by_count":4},{"id":"2603.14935","title":"Video-CoE: Reinforcing Video Event Prediction via Chain of Events","created":"2026-03-16","cited_by_count":4},{"id":"1711.11473","title":"Spatially-Adaptive Filter Units for Deep Neural Networks","created":"2017-11-30","cited_by_count":3},{"id":"2505.01948","title":"Multi-Scale Graph Learning for Anti-Sparse Downscaling","created":"2025-05-03","cited_by_count":3},{"id":"2510.13253","title":"End-to-End Multi-Modal Diffusion Mamba","created":"2025-10-15","cited_by_count":3},{"id":"2511.18929","title":"Human-Centric Open-Future Task Discovery: Formulation, Benchmark, and Scalable Tree-Based Search","created":"2025-11-24","cited_by_count":3}],"next_cursor":null}