Published inVoxel51This Visual Illusions Benchmark Makes Me Question the Power of VLMsExploring how well modern AI systems can spot visual deceptionsMar 3Mar 3
Published inVoxel51Memes Are the VLM Benchmark We DeserveSeriously, Memes Are All We NeedFeb 201Feb 201
Published inVoxel51Can VLMs Hear What They See?Exploring the Intersection of Vision Language Models and Audio DataFeb 20Feb 20
Published inVoxel51WebUOT-1M: A Dataset for Underwater Object TrackingHow 1.1 Million Frames Are Transforming Object TrackingFeb 17Feb 17
Published inVoxel51Beyond the Microscope: Diving into BIOSCAN-5M, a New Dataset for Insect Biodiversity ResearchExploring the World’s Largest Insect Dataset with a Modern Toolkit for Visual AIFeb 13Feb 13
Published inVoxel51AIMv2 Outperforms CLIP on Synthetic Dataset ImageNet-DTesting Vision Model Robustness: A hands-on tutorial for evaluating vision model performance on synthetic data using embedding analysis and…Feb 12Feb 12
Published inVoxel51Visual Understanding with AIMv2Move over, CLIP — you’ve been dethroned!Feb 11Feb 11
Published inVoxel51ImageNet-D: a new synthetic test set designed to rigorously evaluate the robustness of neural…How well does your model understand what it “sees”?Feb 111Feb 111
Published inVoxel51Five Must Read Data-Centric AI Papers from NeurIPS 2024Where Research Meets Real-World Data ChallengesDec 6, 2024Dec 6, 2024
Published inVoxel51More Than Meets the Eye: How Transformations Reveal the Hidden Biases Shaping Our DatasetsReview of a Data-Centric AI Paper from NeurIPS 2024 — Understanding Bias in Large-Scale Visual DatasetsDec 6, 2024Dec 6, 2024
