{"total":15,"rows":[{"id":"2505.21457","title":"ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning","created":"2025-05-27","cited_by_count":43,"area":null},{"id":"2511.20351","title":"Thinking in 360{\\deg}: Humanoid Visual Search in the Wild","created":"2025-11-25","cited_by_count":15,"area":null},{"id":"2511.20460","title":"Look Where It Matters: Training-Free Ultra-HR Remote Sensing VQA via Adaptive Zoom Search","created":"2025-11-25","cited_by_count":11,"area":null},{"id":"2504.01407","title":"ZoomV: Temporal Zoom-in for Efficient Long Video Understanding","created":"2025-04-02","cited_by_count":10,"area":null},{"id":"2509.15532","title":"GUI-ARP: Enhancing Grounding with Adaptive Region Perception for GUI Agents","created":"2025-09-19","cited_by_count":10,"area":null},{"id":"2602.21956","title":"Global-Local Dual Perception for MLLMs in High-Resolution Text-Rich Image Translation","created":"2026-02-25","cited_by_count":3,"area":null},{"id":"2607.09068","title":"OmniMapBench: Benchmarking Visual-Centric Reasoning on Diverse Map Documents","created":"2026-07-10","cited_by_count":2,"area":null},{"id":"2512.24297","title":"Figure It Out: Improve the Frontier of Reasoning with Executable Visual States","created":"2025-12-30","cited_by_count":1,"area":null},{"id":"2609.19745","title":"Region-Level Policy Optimization for Fine-grained MLLM Perception","created":"2026-09-17","cited_by_count":1,"area":null},{"id":"2605.09146","title":"Beyond Thinking: Imagining in 360$^\\circ$ for Humanoid Visual Search","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2607.05467","title":"A Task-Driven Evaluation of UAV Detection and Tracking under Synthetic Fog","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.16514","title":"Matched Outcomes, Divergent Gaze: How Foveated MLLMs Search Compared to Humans","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.29865","title":"ManGo: Manga Active Narrative Grounding Optimization","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.31234","title":"WeaveAgent: A Two-Stage Tool-Routing Agent for Ultra-High-Resolution Remote Sensing Imagery","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.37002","title":"Visual Parallel Search: Learning to Search High-Resolution Images with Parallel Tile Inspection and Adaptive Zoom","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}