{"total":46,"rows":[{"id":"2406.06525","title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","created":"2024-06-10","cited_by_count":777,"area":null},{"id":"2502.20321","title":"UniTok: A Unified Tokenizer for Visual Generation and Understanding","created":"2025-02-27","cited_by_count":153,"area":null},{"id":"2510.12798","title":"Detect Anything via Next Point Prediction","created":"2025-10-14","cited_by_count":73,"area":null},{"id":"2409.18111","title":"E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding","created":"2024-09-26","cited_by_count":70,"area":null},{"id":"2411.10332","title":"Number it: Temporal Grounding Videos like Flipping Manga","created":"2024-11-15","cited_by_count":65,"area":null},{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52,"area":null},{"id":"2504.21530","title":"RoboGround: Robotic Manipulation with Grounded Vision-Language Priors","created":"2025-04-30","cited_by_count":51,"area":null},{"id":"2411.15539","title":"Large Language Model with Region-guided Referring and Grounding for CT Report Generation","created":"2024-11-23","cited_by_count":28,"area":null},{"id":"2412.15321","title":"Next Patch Prediction for Autoregressive Visual Generation","created":"2024-12-19","cited_by_count":26,"area":null},{"id":"2503.08507","title":"Referring to Any Person","created":"2025-03-11","cited_by_count":21,"area":null},{"id":"2407.16696","title":"PartGLEE: A Foundation Model for Recognizing and Parsing Any Objects","created":"2024-07-23","cited_by_count":15,"area":null},{"id":"2504.04716","title":"On the Robustness of GUI Grounding Models Against Image Attacks","created":"2025-04-07","cited_by_count":14,"area":null},{"id":"2512.12309","title":"WeDetect: Fast Open-Vocabulary Object Detection as Retrieval","created":"2025-12-13","cited_by_count":14,"area":null},{"id":"2407.07412","title":"Pseudo-RIS: Distinctive Pseudo-supervision Generation for Referring Image Segmentation","created":"2024-07-10","cited_by_count":13,"area":null},{"id":"2503.11093","title":"OmniDiff: A Comprehensive Benchmark for Fine-grained Image Difference Captioning","created":"2025-03-14","cited_by_count":12,"area":null},{"id":"2504.13621","title":"Visual Intention Grounding for Egocentric Assistants","created":"2025-04-18","cited_by_count":11,"area":null},{"id":"2505.23179","title":"DIP-R1: Deep Inspection and Perception with RL Looking Through and Understanding Complex Scenes","created":"2025-05-29","cited_by_count":11,"area":null},{"id":"2502.20104","title":"New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration","created":"2025-02-27","cited_by_count":7,"area":null},{"id":"2509.22228","title":"UrbanFeel: A Comprehensive Benchmark for Temporal and Perceptual Understanding of City Scenes through Human Perspective","created":"2025-09-26","cited_by_count":7,"area":null},{"id":"2506.07643","title":"Synthetic Visual Genome","created":"2025-06-09","cited_by_count":6,"area":null},{"id":"2509.23724","title":"Video Panels for Long Video Understanding","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2503.10781","title":"Large-scale Pre-training for Grounded Video Caption Generation","created":"2025-03-13","cited_by_count":5,"area":null},{"id":"2503.11129","title":"Direction-Aware Diagonal Autoregressive Image Generation","created":"2025-03-14","cited_by_count":5,"area":null},{"id":"2511.16937","title":"OmniGround: A Comprehensive Spatio-Temporal Grounding Benchmark for Real-World Complex Scenarios","created":"2025-11-21","cited_by_count":5,"area":null},{"id":"2502.13898","title":"GroundCap: A Visually Grounded Image Captioning Dataset","created":"2025-02-19","cited_by_count":4,"area":null},{"id":"2503.20871","title":"VinaBench: Benchmark for Faithful and Consistent Visual Narratives","created":"2025-03-26","cited_by_count":4,"area":null},{"id":"2506.04650","title":"Neural Network Reprogrammability: A Unified Theme on Model Reprogramming, Prompt Tuning, and Prompt Instruction","created":"2025-06-05","cited_by_count":4,"area":null},{"id":"2405.16071","title":"DynRefer: Delving into Region-level Multimodal Tasks via Dynamic Resolution","created":"2024-05-25","cited_by_count":3,"area":null},{"id":"2504.05305","title":"URECA: Unique Region Caption Anything","created":"2025-04-07","cited_by_count":2,"area":null},{"id":"2505.03334","title":"OS-W2S: An Automatic Labeling Engine for Language-Guided Open-Set Aerial Object Detection","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2506.13552","title":"A Comprehensive Survey on Video Scene Parsing:Advances, Challenges, and Prospects","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2505.24466","title":"SA-Person: Text-Based Person Retrieval with Scene-aware Re-ranking","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2506.11261","title":"Gondola: Grounded Vision Language Planning for Robotic Manipulation","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2510.09110","title":"Synthetic Object Compositions for Scalable and Accurate Learning in Detection, Segmentation, and Grounding","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2603.06973","title":"T2SGrid: Temporal-to-Spatial Gridification for Video Temporal Grounding","created":"2026-03-07","cited_by_count":1,"area":null},{"id":"2405.16401","title":"Understanding the Effect of using Semantically Meaningful Tokens for Visual Representation Learning","created":"2024-05-26","cited_by_count":0,"area":null},{"id":"2411.07584","title":"Grounded Video Caption Generation","created":"2024-11-12","cited_by_count":0,"area":null},{"id":"2509.20841","title":"ImaginationPolicy: Towards Generalizable, Precise and Reliable End-to-End Policy for Robotic Manipulation","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2509.23955","title":"ColLab: A Collaborative Spatial Progressive Data Engine for Referring Expression Comprehension and Generation","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2605.14923","title":"SceneParser: Hierarchical Scene Parsing for Visual Semantics Understanding","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.05635","title":"ShotCrop$^3$: Cropping Human-Centric Images into Cinematic Triple-Shot Compositions","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2607.04638","title":"Learning Structured Visual Compositional Representations for Weakly Supervised Referring Expression Comprehension","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.28192","title":"Locate Anything in Videos: Rethinking Efficient Generative Spatio-Temporal Video Grounding","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.19143","title":"PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.24409","title":"DeCo: Efficient Decouple-to-Couple Learning for Multi-Task Visual Grounding","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2610.05274","title":"Answer with Evidence: Consistency-Aware Grounded Visual Question Answering for Roadside Traffic Scenes","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}