Search papers, labs, and topics across Lattice.
Affiliation:
3
0
5
Context-Calibrated DPO can cut object hallucination in MLLMs by 36% while maintaining reasoning performance, revealing a critical gap in how existing methods leverage context.
Iterative refinement of search queries in a continuous latent space leads to a dramatic increase in video retrieval accuracy and reasoning efficiency.
COVRAG achieves superior long-term geometric consistency in video generation by intelligently maximizing coverage of target views, outperforming existing methods in both efficiency and effectiveness.
