Search papers, labs, and topics across Lattice.
Baidu Inc
3
0
7
Achieving a 5x speedup in document parsing without sacrificing accuracy could redefine efficiency benchmarks in Vision-Language Models.
Unlimited OCR can transcribe dozens of pages in one go, overcoming the memory bottlenecks that plague traditional OCR models.
LLMs can beat state-of-the-art tensor compilers on individual subgraphs, but struggle with consistency, revealing a path to unlock their full potential through targeted training.
