PaperBench: Evaluating AI's Ability to Replicate AI Research Paper • 2504.01848 • Published 21 days ago • 36
Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks Paper • 2504.01308 • Published 22 days ago • 13
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization Paper • 2504.00999 • Published 22 days ago • 83
TinyEmo: Scaling down Emotional Reasoning via Metric Projection Paper • 2410.07062 • Published Oct 9, 2024 • 4
Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning Paper • 2410.06373 • Published Oct 8, 2024 • 34