{"list":"other","total":59,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"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":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2506.15742","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","created":"2025-06-17","cited_by_count":1006},{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897},{"id":"1702.05448","title":"Learning to Detect Human-Object Interactions","created":"2017-02-17","cited_by_count":240},{"id":"2311.05437","title":"LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents","created":"2023-11-09","cited_by_count":193},{"id":"1505.04474","title":"Visual Semantic Role Labeling","created":"2015-05-17","cited_by_count":190},{"id":"2504.02546","title":"GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning","created":"2025-04-03","cited_by_count":150},{"id":"2103.05399","title":"QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information","created":"2021-03-09","cited_by_count":147},{"id":"2007.12407","title":"Visual Compositional Learning for Human-Object Interaction Detection","created":"2020-07-24","cited_by_count":130},{"id":"2203.13954","title":"GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection","created":"2022-03-26","cited_by_count":120},{"id":"2103.08214","title":"Detecting Human-Object Interaction via Fabricated Compositional Learning","created":"2021-03-15","cited_by_count":79},{"id":"2507.07998","title":"PyVision: Agentic Vision with Dynamic Tooling","created":"2025-07-10","cited_by_count":79},{"id":"2403.19646","title":"Change-Agent: Towards Interactive Comprehensive Remote Sensing Change Interpretation and Analysis","created":"2024-03-28","cited_by_count":63},{"id":"2303.15786","title":"HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models","created":"2023-03-28","cited_by_count":61},{"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":"2204.07718","title":"Interactiveness Field in Human-Object Interactions","created":"2022-04-16","cited_by_count":40},{"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":"2304.04997","title":"Relational Context Learning for Human-Object Interaction Detection","created":"2023-04-11","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":"2406.07221","title":"Open-World Human-Object Interaction Detection via Multi-modal Prompts","created":"2024-06-11","cited_by_count":28},{"id":"2410.23904","title":"EZ-HOI: VLM Adaptation via Guided Prompt Learning for Zero-Shot HOI Detection","created":"2024-10-31","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":"2404.06194","title":"Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection","created":"2024-04-09","cited_by_count":25},{"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":"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":"2505.19866","title":"HS-STaR: Hierarchical Sampling for Self-Taught Reasoners via Difficulty Estimation and Budget Reallocation","created":"2025-05-26","cited_by_count":18},{"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":"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":"2505.19503","title":"Locality-Aware Zero-Shot Human-Object Interaction Detection","created":"2025-05-26","cited_by_count":12},{"id":"2508.09822","title":"Physical Autoregressive Model for Robotic Manipulation without Action Pretraining","created":"2025-08-13","cited_by_count":12},{"id":"2408.05974","title":"Unseen No More: Unlocking the Potential of CLIP for Generative Zero-shot HOI Detection","created":"2024-08-12","cited_by_count":11},{"id":"2503.12218","title":"Adaptive Label Correction for Robust Medical Image Segmentation with Noisy Labels","created":"2025-03-15","cited_by_count":8},{"id":"2508.03207","title":"Open-Vocabulary HOI Detection with Interaction-aware Prompt and Concept Calibration","created":"2025-08-05","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":"2507.06510","title":"Bilateral Collaboration with Large Vision-Language Models for Open Vocabulary Human-Object Interaction Detection","created":"2025-07-09","cited_by_count":6},{"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":"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}