Rafid Mahmood

Assistant Professor@University of Ottawa·加拿大·OpenReview

研究方向

visual language models · revenue management and pricing · social issues of AI · neural scaling laws · data collection · active learning · integer programming · convex optimization · GANs · error correction codes

5.5

Routing, Cascades, and User Choice for LLMs

ICLR 2026Poster

一作

3.6

AdaDeDup: Adaptive Hybrid Data Pruning for Efficient Object Detection Training

ICLR 2026Withdrawn

5.5

AutoScale: Automatic Prediction of Compute-optimal Data Compositions for Training LLMs

合作者 (18)

Rafid Mahmood

Routing, Cascades, and User Choice for LLMs

AdaDeDup: Adaptive Hybrid Data Pruning for Efficient Object Detection Training

AutoScale: Automatic Prediction of Compute-optimal Data Compositions for Training LLMs

AutoScale: Scale-Aware Data Mixing for Pre-Training LLMs

Uncertainty Estimation for 3D Object Detection via Evidential Learning

Can Large Vision-Language Models Correct Grounding Errors By Themselves?