31 citations · 47 across the 3 of their papers we have counts for
3 papers
cs.CL2026
TukaBench: A Culturally Grounded Jailbreak Benchmark for African Languages
Victor Akinode, Senyu Li, Wassim Hamidouche +3
Safety evaluation of Large Language Models (LLMs) remains heavily English-centric, leaving Low-Resource Languages (LRLs), particularly African ones, critically underexplored. We in…
cs.CV2019★ 16 cited
Max-margin Class Imbalanced Learning with Gaussian Affinity
Munawar Hayat, Salman Khan, Waqas Zamir +2
Real-world object classes appear in imbalanced ratios. This poses a significant challenge for classifiers which get biased towards frequent classes. We hypothesize that improving t…
cs.CV2019★ 31 cited
Striking the Right Balance with Uncertainty
Salman Khan, Munawar Hayat, Waqas Zamir +2
Learning unbiased models on imbalanced datasets is a significant challenge. Rare classes tend to get a concentrated representation in the classification space which hampers the gen…