{"list":"other","total":53,"rows":[{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2508.18265","title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","created":"2025-08-25","cited_by_count":1510},{"id":"2503.20783","title":"Understanding R1-Zero-Like Training: A Critical Perspective","created":"2025-03-26","cited_by_count":1345},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897},{"id":"2512.02556","title":"DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models","created":"2025-12-02","cited_by_count":815},{"id":"2501.17811","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","created":"2025-01-29","cited_by_count":812},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"2505.05470","title":"Flow-GRPO: Training Flow Matching Models via Online RL","created":"2025-05-08","cited_by_count":661},{"id":"2410.13848","title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","created":"2024-10-17","cited_by_count":457},{"id":"2311.03356","title":"GLaMM: Pixel Grounding Large Multimodal Model","created":"2023-11-06","cited_by_count":455},{"id":"2306.00968","title":"GRES: Generalized Referring Expression Segmentation","created":"2023-06-01","cited_by_count":254},{"id":"2503.06520","title":"Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement","created":"2025-03-09","cited_by_count":239},{"id":"2105.09451","title":"Anabranch Network for Camouflaged Object Segmentation","created":"2021-05-20","cited_by_count":227},{"id":"2103.04011","title":"Simultaneously Localize, Segment and Rank the Camouflaged Objects","created":"2021-03-06","cited_by_count":198},{"id":"2007.06700","title":"Revisiting Fundamentals of Experience Replay","created":"2020-07-13","cited_by_count":175},{"id":"2312.10103","title":"GSVA: Generalized Segmentation via Multimodal Large Language Models","created":"2023-12-15","cited_by_count":154},{"id":"2203.02688","title":"Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection","created":"2022-03-05","cited_by_count":145},{"id":"2205.11275","title":"RL with KL penalties is better viewed as Bayesian inference","created":"2022-05-23","cited_by_count":135},{"id":"2401.03407","title":"Bilateral Reference for High-Resolution Dichotomous Image Segmentation","created":"2024-01-07","cited_by_count":112},{"id":"2403.14598","title":"PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model","created":"2024-03-21","cited_by_count":101},{"id":"2203.11624","title":"High-resolution Iterative Feedback Network for Camouflaged Object Detection","created":"2022-03-22","cited_by_count":78},{"id":"2312.17240","title":"LISA++: An Improved Baseline for Reasoning Segmentation with Large Language Model","created":"2023-12-28","cited_by_count":71},{"id":"2501.13925","title":"GeoPixel: Pixel Grounding Large Multimodal Model in Remote Sensing","created":"2025-01-23","cited_by_count":57},{"id":"2505.17022","title":"GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning","created":"2025-05-22","cited_by_count":52},{"id":"2409.01686","title":"Frequency-Spatial Entanglement Learning for Camouflaged Object Detection","created":"2024-09-03","cited_by_count":46},{"id":"2505.22596","title":"SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning","created":"2025-05-28","cited_by_count":31},{"id":"2508.04655","title":"X-SAM: From Segment Anything to Any Segmentation","created":"2025-08-06","cited_by_count":30},{"id":"2503.13881","title":"MMR: A Large-scale Benchmark Dataset for Multi-target and Multi-granularity Reasoning Segmentation","created":"2025-03-18","cited_by_count":28},{"id":"2507.19280","title":"RemoteReasoner: Towards Unifying Geospatial Reasoning Workflow","created":"2025-07-25","cited_by_count":28},{"id":"2410.18923","title":"SegLLM: Multi-round Reasoning Segmentation","created":"2024-10-24","cited_by_count":25},{"id":"2205.10579","title":"Boosting Camouflaged Object Detection with Dual-Task Interactive Transformer","created":"2022-05-21","cited_by_count":24},{"id":"2504.00640","title":"POPEN: Preference-Based Optimization and Ensemble for LVLM-Based Reasoning Segmentation","created":"2025-04-01","cited_by_count":22},{"id":"2508.00265","title":"Multimodal Referring Segmentation: A Survey","created":"2025-08-01","cited_by_count":22},{"id":"2506.04277","title":"RSVP: Reasoning Segmentation via Visual Prompting and Multi-modal Chain-of-Thought","created":"2025-06-04","cited_by_count":19},{"id":"2508.14153","title":"LENS: Learning to Segment Anything with Unified Reinforced Reasoning","created":"2025-08-19","cited_by_count":18},{"id":"2509.25027","title":"STAGE: Stable and Generalizable GRPO for Autoregressive Image Generation","created":"2025-09-29","cited_by_count":15},{"id":"2407.13133","title":"FocusDiffuser: Perceiving Local Disparities for Camouflaged Object Detection","created":"2024-07-18","cited_by_count":14},{"id":"2510.11173","title":"CoPRS: Learning Positional Prior from Chain-of-Thought for Reasoning Segmentation","created":"2025-10-13","cited_by_count":9},{"id":"2511.19425","title":"SAM3-Adapter: Efficient Adaptation of Segment Anything 3 for Camouflage Object Segmentation, Shadow Detection, and Medical Image Segmentation","created":"2025-11-24","cited_by_count":7},{"id":"2512.19302","title":"Bridging Semantics and Geometry: A Decoupled LVLM-SAM Framework for Reasoning Segmentation in Optical Remote Sensing","created":"2025-12-22","cited_by_count":6},{"id":"2512.24023","title":"RSAgent: Learning to Reason and Act for Text-Guided Segmentation via Multi-Turn Tool Invocations","created":"2025-12-30","cited_by_count":6},{"id":"2409.11518","title":"Robot Manipulation in Salient Vision through Referring Image Segmentation and Geometric Constraints","created":"2024-09-17","cited_by_count":5},{"id":"2502.11093","title":"Text-Promptable Propagation for Referring Medical Image Sequence Segmentation","created":"2025-02-16","cited_by_count":4},{"id":"2507.20186","title":"SAMwave: Wavelet-Driven Feature Enrichment for Effective Adaptation of Segment Anything Model","created":"2025-07-27","cited_by_count":3},{"id":"2512.15564","title":"On the Effectiveness of Textual Prompting with Lightweight Fine-Tuning for SAM3 Remote Sensing Segmentation","created":"2025-12-17","cited_by_count":3},{"id":"2511.12627","title":"C3Net: Context-Contrast Network for Camouflaged Object Detection","created":"2025-11-16","cited_by_count":2},{"id":"2511.17171","title":"FireScope: Wildfire Risk Raster Prediction with a Chain-of-Thought Oracle","created":"2025-11-21","cited_by_count":2},{"id":"2603.14382","title":"StAR: Segment Anything Reasoner","created":"2026-03-15","cited_by_count":2}],"next_cursor":null}