RefVNLI: Towards Scalable Evaluation of Subject-driven Text-to-image Generation Paper • 2504.17502 • Published 4 days ago • 52 • 2
Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs Paper • 2504.17432 • Published 4 days ago • 36 • 4
QuaDMix: Quality-Diversity Balanced Data Selection for Efficient LLM Pretraining Paper • 2504.16511 • Published 5 days ago • 20 • 2
Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning Paper • 2504.17192 • Published 4 days ago • 90 • 5
Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Models Paper • 2504.17789 • Published 4 days ago • 19 • 3
DyMU: Dynamic Merging and Virtual Unmerging for Efficient VLMs Paper • 2504.17040 • Published 5 days ago • 11 • 2