Search papers, labs, and topics across Lattice.
4
0
6
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 not only rivals but surpasses real-robot data in pretraining embodied models, achieving a staggering 90% improvement in out-of-distribution task success rates.
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.
