Search papers, labs, and topics across Lattice.
6
0
9
0
Unified image restoration methods can now be rigorously compared across real-world conditions, with 20 teams showcasing innovative solutions that push the boundaries of restoration accuracy.
Bridging the Context Gap in T2I models, Qwen-Image-Agent achieves state-of-the-art performance by intelligently constructing context from user input and external sources.
A novel reward system boosts Qwen-Image-2.0's performance, achieving a 2.61 point increase in overall quality and significant gains in both text-to-image and image editing tasks.
Language-driven video generation in Qwen-RobotWorld achieves unprecedented accuracy in predicting robotic actions, outperforming existing models across key benchmarks.
Rethinking few-step distillation reveals that the training pipeline's organization is as crucial as the distillation objectives themselves.
Robot RL training can be dramatically sped up (3-10x) by decoupling CPU-based simulation from GPU-based learning, challenging the assumption that GPU-resident physics is essential for efficiency.
