{"list":"other","total":63,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"2409.19256","title":"HybridFlow: A Flexible and Efficient RLHF Framework","created":"2024-09-28","cited_by_count":2057},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"2304.11277","title":"PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel","created":"2023-04-21","cited_by_count":660},{"id":"2501.12326","title":"UI-TARS: Pioneering Automated GUI Interaction with Native Agents","created":"2025-01-21","cited_by_count":610},{"id":"2401.10935","title":"SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents","created":"2024-01-17","cited_by_count":567},{"id":"1712.05889","title":"Ray: A Distributed Framework for Emerging AI Applications","created":"2017-12-16","cited_by_count":527},{"id":"2410.05243","title":"Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents","created":"2024-10-07","cited_by_count":382},{"id":"2410.23218","title":"OS-ATLAS: A Foundation Action Model for Generalist GUI Agents","created":"2024-10-30","cited_by_count":378},{"id":"2412.04454","title":"Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction","created":"2024-12-05","cited_by_count":278},{"id":"2504.07981","title":"ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use","created":"2025-04-04","cited_by_count":254},{"id":"2411.17465","title":"ShowUI: One Vision-Language-Action Model for GUI Visual Agent","created":"2024-11-26","cited_by_count":232},{"id":"2509.02544","title":"UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning","created":"2025-09-02","cited_by_count":215},{"id":"2406.03679","title":"On the Effects of Data Scale on UI Control Agents","created":"2024-06-06","cited_by_count":194},{"id":"2508.15144","title":"Mobile-Agent-v3: Fundamental Agents for GUI Automation","created":"2025-08-21","cited_by_count":190},{"id":"2508.09123","title":"OpenCUA: Open Foundations for Computer-Use Agents","created":"2025-08-12","cited_by_count":160},{"id":"2402.17553","title":"OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web","created":"2024-02-27","cited_by_count":157},{"id":"2412.16256","title":"Aria-UI: Visual Grounding for GUI Instructions","created":"2024-12-20","cited_by_count":140},{"id":"2405.05803","title":"Boosting Multimodal Large Language Models with Visual Tokens Withdrawal for Rapid Inference","created":"2024-05-09","cited_by_count":139},{"id":"2505.13227","title":"Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis","created":"2025-05-19","cited_by_count":139},{"id":"2407.17490","title":"AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents","created":"2024-07-03","cited_by_count":113},{"id":"2507.05791","title":"GTA1: GUI Test-time Scaling Agent","created":"2025-07-08","cited_by_count":106},{"id":"2412.13501","title":"GUI Agents: A Survey","created":"2024-12-18","cited_by_count":103},{"id":"2506.03143","title":"GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents","created":"2025-06-03","cited_by_count":95},{"id":"2508.10833","title":"UI-Venus Technical Report: Building High-performance UI Agents with RFT","created":"2025-08-14","cited_by_count":93},{"id":"2512.22047","title":"MAI-UI Technical Report: Real-World Centric Foundation GUI Agents","created":"2025-12-26","cited_by_count":91},{"id":"2504.00587","title":"AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems","created":"2025-04-01","cited_by_count":90},{"id":"2505.12370","title":"Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning","created":"2025-05-18","cited_by_count":81},{"id":"2602.16855","title":"Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents","created":"2026-02-15","cited_by_count":79},{"id":"2503.15661","title":"UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction","created":"2025-03-19","cited_by_count":77},{"id":"2507.19478","title":"MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents","created":"2025-07-25","cited_by_count":67},{"id":"2507.15846","title":"GUI-G$^2$: Gaussian Reward Modeling for GUI Grounding","created":"2025-07-21","cited_by_count":63},{"id":"2601.15876","title":"EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience","created":"2026-01-22","cited_by_count":53},{"id":"2602.09082","title":"UI-Venus-1.5 Technical Report","created":"2026-02-09","cited_by_count":41},{"id":"2507.00008","title":"DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoning","created":"2025-06-12","cited_by_count":31},{"id":"2505.00684","title":"Visual Test-time Scaling for GUI Agent Grounding","created":"2025-05-01","cited_by_count":30},{"id":"2508.05731","title":"InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization","created":"2025-08-07","cited_by_count":27},{"id":"2507.23779","title":"Phi-Ground Tech Report: Advancing Perception in GUI Grounding","created":"2025-07-31","cited_by_count":25},{"id":"2510.20286","title":"UI-Ins: Enhancing GUI Grounding with Multi-Perspective Instruction-as-Reasoning","created":"2025-10-23","cited_by_count":22},{"id":"2508.05615","title":"Test-Time Reinforcement Learning for GUI Grounding via Region Consistency","created":"2025-08-07","cited_by_count":21},{"id":"2509.26539","title":"Ferret-UI Lite: Lessons from Building Small On-Device GUI Agents","created":"2025-09-30","cited_by_count":16},{"id":"2510.03853","title":"UGround: Towards Unified Visual Grounding with Unrolled Transformers","created":"2025-10-04","cited_by_count":14},{"id":"2505.15259","title":"ReGUIDE: Data Efficient GUI Grounding via Spatial Reasoning and Search","created":"2025-05-21","cited_by_count":13},{"id":"2512.08529","title":"MVP: Multiple View Prediction Improves GUI Grounding","created":"2025-12-09","cited_by_count":12},{"id":"2509.10345","title":"Towards Understanding Visual Grounding in Visual Language Models","created":"2025-09-12","cited_by_count":10},{"id":"2510.04039","title":"\\textsc{GUI-Spotlight}: Adaptive Iterative Focus Refinement for Enhanced GUI Visual Grounding","created":"2025-10-05","cited_by_count":10},{"id":"2601.09770","title":"GUI-Eyes: Tool-Augmented Perception for Visual Grounding in GUI Agents","created":"2026-01-14","cited_by_count":10},{"id":"2406.13719","title":"GUI Action Narrator: Where and When Did That Action Take Place?","created":"2024-06-19","cited_by_count":9},{"id":"2511.00810","title":"GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding","created":"2025-11-02","cited_by_count":8},{"id":"2512.05941","title":"Zoom in, Click out: Unlocking and Evaluating the Potential of Zooming for GUI Grounding","created":"2025-12-05","cited_by_count":8},{"id":"2604.14113","title":"UI-Zoomer: Uncertainty-Driven Adaptive Zoom-In for GUI Grounding","created":"2026-04-15","cited_by_count":8},{"id":"2508.04389","title":"GuirlVG: Incentivize GUI Visual Grounding via Empirical Exploration on Reinforcement Learning","created":"2025-08-06","cited_by_count":7},{"id":"2512.01979","title":"Chain-of-Ground: Improving GUI Grounding via Iterative Reasoning and Reference Feedback","created":"2025-12-01","cited_by_count":7},{"id":"2508.13634","title":"V2P: Visual Attention Calibration for GUI Grounding via Background Suppression and Center Peaking","created":"2025-08-19","cited_by_count":6},{"id":"2603.17441","title":"AdaZoom-GUI: Adaptive Zoom-based GUI Grounding with Instruction Refinement","created":"2026-03-18","cited_by_count":6},{"id":"2603.14448","title":"Zoom to Essence: Trainless GUI Grounding by Inferring upon Interface Elements","created":"2026-03-15","cited_by_count":5},{"id":"2510.03230","title":"Improving GUI Grounding with Explicit Position-to-Coordinate Mapping","created":"2025-10-03","cited_by_count":4},{"id":"2602.06391","title":"POINTS-GUI-G: GUI-Grounding Journey","created":"2026-02-06","cited_by_count":4},{"id":"2605.12549","title":"What Happens Before Decoding? Prefill Determines GUI Grounding in VLMs","created":"2026-05-10","cited_by_count":4}],"next_cursor":null}