ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citations Paper • 2504.00824 • Published 21 days ago • 40
Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks Paper • 2504.01308 • Published 20 days ago • 13
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization Paper • 2504.00999 • Published 21 days ago • 83