Search papers, labs, and topics across Lattice.
4
2
6
5
Credit-addressable reasoning boosts multimodal geometry accuracy by over 8 points, revealing the critical role of structured learning in complex tasks.
Achieving an 86.17% success rate in reproduction test generation, DPIAgent reveals that structured task separation can dramatically enhance performance in automated software engineering.
Image editing gets a reasoning upgrade: a chain-of-thought verifier model beats powerful VLMs at judging edits and boosts editing model performance.
Scaling visual preference optimization hinges on data quality, as a massive, high-resolution dataset renders complex optimization algorithms unnecessary.
