Search papers, labs, and topics across Lattice.
Affiliation:
5
0
7
0
Transferring frozen memory between models can yield substantial performance gains, but only if the target model's reader is properly aligned.
Motion-as-Prompt reveals that enhancing motion reasoning in MLLMs can lead to substantial accuracy gains without altering model architecture or requiring retraining.
HUGIN boosts vision-language model accuracy for logistics sorting by over 15 percentage points, showcasing a significant leap in performance through innovative training techniques.
Teacher-student mismatch can lead to flawed outputs, but TIDE's innovative correction method boosts reasoning accuracy by over 200% in challenging scenarios.
Local Margin Restoration not only shields VLMs from bias but also preserves their semantic integrity, leading to superior performance in dynamic environments.
