Search papers, labs, and topics across Lattice.
Affiliation:
2
0
5
0
By jointly optimizing distillation and quantization within a unified teacher-anchored framework, this method ensures consistent training under quantization, suppressing hard negatives and enlarging decision margins, and designs a lightweight cross-attention adapter that enhances non-RGB representations through RGB-guided semantic transfer, narrowing the modality gap.
AETDICE resolves the long-standing divide in nonlinear multi-objective RL, enabling nuanced trade-off optimization that previous methods overlooked.
