{"total":19,"rows":[{"id":"2603.21687","title":"MIRAGE: The Illusion of Visual Understanding","created":"2026-03-23","cited_by_count":65,"area":null},{"id":"2603.20633","title":"Seed1.8 Model Card: Towards Generalized Real-World Agency","created":"2026-03-21","cited_by_count":50,"area":null},{"id":"2603.23523","title":"Do 3D Large Language Models Really Understand 3D Spatial Relationships?","created":"2026-03-06","cited_by_count":9,"area":null},{"id":"2509.25339","title":"VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2602.09475","title":"ArtifactLens: Hundreds of Labels Are Enough for Artifact Detection with VLMs","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2602.11244","title":"Stress Tests REVEAL Fragile Temporal and Visual Grounding in Video-Language Models","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2605.29283","title":"Do Physics Foundation Models Learn Generalizable Physics? A Bias-Aware Benchmark Across Physical Regimes and Distribution Shifts","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2608.00490","title":"Image-Space Rule Discovery","created":"2026-08-01","cited_by_count":1,"area":null},{"id":"2609.35718","title":"Hard Vision, Easy Vision: What GPT-6 Astra Reveals Across Computer Vision","created":"2026-09-28","cited_by_count":1,"area":null},{"id":"2510.21842","title":"Modal Aphasia: Can Unified Multimodal Models Describe Images From Memory?","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2511.15656","title":"INQUIRE-Search: Interactive Discovery in Large-Scale Biodiversity Databases","created":"2025-11-19","cited_by_count":0,"area":null},{"id":"2603.25744","title":"MuRF: Unlocking the Multi-Scale Potential of Vision Foundation Models","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.01973","title":"NearID: Identity Representation Learning via Near-identity Distractors","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.18957","title":"Bridging Foundation Models and ASTM Metallurgical Standards for Automated Grain Size Estimation from Microscopy Images","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.13330","title":"FIND: Toward Multimodal Financial Reasoning and Question Answering for Indic Languages","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.14892","title":"Relational Structural Causal Models","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.08317","title":"Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.16165","title":"An Exam for Active Observers","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2610.00111","title":"A Low Grounding Score Is Not an Ungrounded Judge: Identifying the Perceptibility Confound in Multimodal Oversight","created":"2026-09-09","cited_by_count":0,"area":null}],"next_cursor":null}