Search papers, labs, and topics across Lattice.
Institute of Software Chinese Academy of Sciences
3
0
6
Video-LLMs hallucinate because they fixate on a single "anchor frame," but a simple decoder-side attention fix can dramatically improve grounding without retraining.
Geometric mappings can dramatically improve PINN training, boosting accuracy and stability by aligning input coordinates with the underlying physics of PDEs.
Neural operators get a 30-50% accuracy boost in long-term PDE prediction with a simple, geometrically-principled "plug-in" that barely increases parameter count.
