Search papers, labs, and topics across Lattice.
9
0
10
22
Large-scale structured academic visual data can transform image generation from mere aesthetic appeal to verifiable knowledge-grounded creation.
No single memory architecture is best for all tasks; performance hinges on how well memory structures align with specific workload challenges.
Current slide generation models miss critical audience-specific information, with DeepPresenter only achieving 71.4% coverage of essential content for specialists and decision-makers.
LLM agents can now achieve a 92% success rate in complex code repository setup by learning from past failures, a 19% improvement over existing methods.
Today's AI agents are surprisingly inept at navigating the messy reality of digital workspaces, failing to reach even 70% accuracy on tasks that require understanding file dependencies.
LLMs can now cook up database-native functions with 34% higher accuracy, even creating entirely new functions missing from current database versions.
Current image editing models stumble when domain-specific knowledge is required, as revealed by a new benchmark spanning disciplines from natural science to social science.
A principled framework for General World Models reveals the limitations of current systems and the architectural requirements for future progress.
LLMs can now more accurately answer questions on complex documents thanks to a new system that understands layout and hierarchical relationships between document components.
