Pretraining A Large Language Model using Distributed GPUs: A Memory-Efficient Decentralized Paradigm Paper • 2602.11543 • Published Feb 12 • 6
OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration Paper • 2602.05400 • Published Feb 5 • 352
CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation Paper • 2603.08652 • Published Mar 9 • 40
Proact-VL: A Proactive VideoLLM for Real-Time AI Companions Paper • 2603.03447 • Published Mar 3 • 37
GEBench: Benchmarking Image Generation Models as GUI Environments Paper • 2602.09007 • Published Feb 9 • 39
Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis Paper • 2602.03139 • Published Feb 3 • 44
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features Paper • 2502.14786 • Published Feb 20, 2025 • 164
LLM2CLIP Collection LLM2CLIP makes SOTA pretrained CLIP modal more SOTA ever. • 10 items • Updated Mar 2 • 67