Search papers, labs, and topics across Lattice.
2
0
6
16
Today's best visual coding agents still struggle to build complete websites from scratch, as revealed by a new benchmark spanning UI generation to full-stack development.
A compact 0.9B multimodal model, GLM-OCR, achieves state-of-the-art document understanding by predicting multiple tokens at once, boosting decoding throughput without blowing up memory.
