{"total":22,"rows":[{"id":"2405.08813","title":"CinePile: A Long Video Question Answering Dataset and Benchmark","created":"2024-05-14","cited_by_count":114,"area":null},{"id":"2312.08578","title":"A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions","created":"2023-12-14","cited_by_count":108,"area":null},{"id":"2506.09849","title":"IntPhys 2: Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments","created":"2025-06-11","cited_by_count":52,"area":null},{"id":"2502.03566","title":"CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally","created":"2025-02-05","cited_by_count":31,"area":null},{"id":"2311.09215","title":"ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy","created":"2023-11-15","cited_by_count":19,"area":null},{"id":"2311.18113","title":"Back to 3D: Few-Shot 3D Keypoint Detection with Back-Projected 2D Features","created":"2023-11-29","cited_by_count":17,"area":null},{"id":"2507.07102","title":"Does Data Scaling Lead to Visual Compositional Generalization?","created":"2025-07-09","cited_by_count":13,"area":null},{"id":"2402.19472","title":"Efficient Lifelong Model Evaluation in an Era of Rapid Progress","created":"2024-02-29","cited_by_count":10,"area":null},{"id":"2403.04701","title":"ObjectCompose: Evaluating Resilience of Vision-Based Models on Object-to-Background Compositional Changes","created":"2024-03-07","cited_by_count":5,"area":null},{"id":"2505.03132","title":"VISLIX: An XAI Framework for Validating Vision Models with Slice Discovery and Analysis","created":"2025-05-06","cited_by_count":5,"area":null},{"id":"2309.11077","title":"Weak Supervision for Label Efficient Visual Bug Detection","created":"2023-09-20","cited_by_count":4,"area":null},{"id":"2410.05869","title":"Believing is Seeing: Unobserved Object Detection using Generative Models","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2411.01948","title":"Learning Where to Edit Vision Transformers","created":"2024-11-04","cited_by_count":4,"area":null},{"id":"2607.06701","title":"SPEAR: A Simulator for Photorealistic Embodied AI Research","created":"2026-07-07","cited_by_count":4,"area":null},{"id":"2406.02535","title":"Enhancing 2D Representation Learning with a 3D Prior","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2406.16935","title":"Benchmarking Out-of-Distribution Generalization Capabilities of DNN-based Encoding Models for the Ventral Visual Cortex","created":"2024-06-16","cited_by_count":3,"area":null},{"id":"2512.08854","title":"Is Generation Required for Data-Efficient Perception?","created":"2025-12-09","cited_by_count":1,"area":null},{"id":"2404.07045","title":"Identification of Fine-grained Systematic Errors via Controlled Scene Generation","created":"2024-04-10","cited_by_count":0,"area":null},{"id":"2409.07940","title":"Control+Shift: Generating Controllable Distribution Shifts","created":"2024-09-12","cited_by_count":0,"area":null},{"id":"2503.13058","title":"Do Vision Models Develop Human-Like Progressive Difficulty Understanding?","created":"2025-03-17","cited_by_count":0,"area":null},{"id":"2604.25065","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.20549","title":"MAPS: A Synthetic Dataset for Probing Vision Models in a Controlled 3D Scene Space","created":"2026-05-19","cited_by_count":0,"area":null}],"next_cursor":null}