Search papers, labs, and topics across Lattice.
8
0
15
4
MedUP reveals that integrating visual perception and language understanding in a single token space can dramatically enhance performance in medical vision-language tasks.
Re-ranking control alone boosts key performance metrics by over 2%, but extending this control to fine ranking yields even greater gains without compromising system stability.
Most LLMs fail to design high-quality experiments, revealing a critical gap in AI's role in scientific research.
By cutting end-to-end serving resource consumption by over 50% while boosting user engagement metrics, RecGPT-V3 redefines efficiency in large-scale recommender systems.
GGR transforms the landscape of open-set semi-supervised learning by ensuring that auxiliary gradients enhance rather than conflict with supervised updates.
Full-duplex dialogue systems are often mischaracterized, with many claiming capabilities they cannot deliver due to training limitations.
Stop relying on significance tests that only find differences: this Bayesian framework tells you if your synthetic data is *practically equivalent* to real-world data for your specific safety assessment task.
Train smarter, not bigger: LoopCTR unlocks state-of-the-art CTR prediction by decoupling computation from parameter growth through recursive layer reuse.
