Search papers, labs, and topics across Lattice.
Nanyang Technological University
5
0
11
Pre-trained Softmax ViTs can directly bootstrap linear-attention models without expensive pre-training from scratch: simply copy the operator-agnostic MLP weights and distill the attention routing behavior.
Optimizing inspection strategies in reverse logistics can yield significant financial gains, with one method adding nearly $54k per batch in aircraft maintenance alone.
Video-OPSD reveals that focusing on privileged visual evidence can drastically improve the efficiency and effectiveness of self-distillation in Video-LLMs.
LambdaMART can boost supply chain recovery by up to 16% compared to static benchmarks, but complexity doesn't always guarantee better outcomes.
Suppressing certain clinical covariates can actually improve the predictive power of prostate MRI grading models, revealing hidden dependencies that could mislead performance assessments.
