Search papers, labs, and topics across Lattice.
6
0
9
4
DanceOPD reveals a novel approach to harmonizing conflicting image generation capabilities, enhancing T2I and editing performance simultaneously.
CARE transforms the approach to reasoning length in video-MLLMs, enabling models to adaptively balance exploration and efficiency based on their evolving competence.
Egocentric human video can outperform traditional teleoperated robot data, achieving superior performance in embodied model pretraining with lower costs and greater diversity.
MAFP reveals that treating stakeholder stances as agents in a game-theoretic framework can drastically improve decision quality in complex scenarios.
VideoCFR not only boosts performance in video reasoning tasks but also reveals the critical visual evidence driving model decisions without relying on human annotations.
Species identification and discovery, traditionally treated as separate problems, can be unified into a single framework that leverages retrieval-augmented reasoning for improved accuracy and interpretability.
