Softpick: No Attention Sink, No Massive Activations with Rectified Softmax Paper • 2504.20966 • Published 4 days ago • 21
SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages Paper • 2406.10118 • Published Jun 14, 2024 • 33
CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark Paper • 2406.05967 • Published Jun 10, 2024 • 6
MLKV: Multi-Layer Key-Value Heads for Memory Efficient Transformer Decoding Paper • 2406.09297 • Published Jun 13, 2024 • 6