Search papers, labs, and topics across Lattice.
5
0
9
MLLMs excel at precision but falter dramatically in extracting complete product specifications from multiple images, with a mere 49.9% recovery rate.
C-DIC stabilizes long-horizon dialogue generation by effectively managing context without sacrificing fidelity, outperforming existing methods in both efficiency and performance.
RLVR's reasoning gains hinge on high-entropy tokens, revealing a critical inefficiency in uniform reward broadcast that EAPO effectively addresses.
Navigate sprawling, multi-floor environments without drowning in grid maps: osmAG-Nav slashes planning latency by up to 7816x using a hierarchical semantic approach.
Achieve up to 102% Sharpe Ratio improvement and 17.5% directional accuracy gain by unifying event-centric data construction and decision-oriented fine-tuning with a hierarchical gated reward model.
