Search papers, labs, and topics across Lattice.
MAIS, Institute of Automation of Chinese Academy of Sciences, School of Artificial Intelligence, University of Chinese Academy of Sciences
5
0
9
Unlock geometric reasoning in MLLMs by parsing diagrams into a unified formal language that spans both 2D and 3D geometry.
Stop sacrificing subject fidelity for editability: DisCo lets you have both in text-to-image generation by disentangling and recoupling visual and textual information.
LLMs still fail to follow complex instructions that entangle content, formatting, control flow, and real-world constraints, despite progress on simpler benchmarks.
Current subject-driven text-to-image models struggle with specific subject categories and prompt scenarios, a problem exposed by a new benchmark that also offers actionable insights for improvement.
Achieve zero-collision embedding tables in production recommenders without sacrificing training speed, unlocking better personalization via fresher and higher-quality item embeddings.
