pith. sign in

Multi-task learning using uncertainty to weigh losses for scene geometry and semantics

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

method 2

citation-polarity summary

fields

cs.CL 1 cs.LG 1

years

2026 2

verdicts

UNVERDICTED 2

roles

method 2

polarities

use method 2

representative citing papers

MELD: Multi-Task Equilibrated Learning Detector for AI-Generated Text

cs.CL · 2026-05-07 · unverdicted · novelty 6.0

MELD is a multi-task AI-text detector using auxiliary heads, uncertainty-weighted losses, EMA distillation, and pairwise ranking that reaches 99.9% TPR at 1% FPR on a new held-out benchmark while remaining competitive on the RAID leaderboard.

citing papers explorer

Showing 2 of 2 citing papers.