DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and Inference Paper • 2602.18846 • Published 14 days ago • 3
DL-QAT: Weight-Decomposed Low-Rank Quantization-Aware Training for Large Language Models Paper • 2504.09223 • Published Apr 12, 2025
AMD-Hummingbird: Towards an Efficient Text-to-Video Model Paper • 2503.18559 • Published Mar 24, 2025 • 5