3 papers
cs.CV2026
Asleep at the Wheel: JEPA's Limitations in Evaluating Novel Driving Data
Advait Pavuluri, Shamik Karkhanis, Uzma Mushtaque
Modern autonomous-driving fleets record far more video than human reviewers can inspect. This motivates the need for an automatic clip triage mechanism, to surface rare and review-…
cs.IR2026
On the Efficiency of Sequentially Aware Recommender Systems: Cotten4Rec
Shankar Veludandi, Gulrukh Kurdistan, Uzma Mushtaque
Sequential recommendation (SR) models predict a user's next interaction by modeling their historical behaviors. Transformer-based SR methods, notably BERT4Rec, effectively capture…
cs.IR2025
An Efficient Attention Mechanism for Sequential Recommendation Tasks: HydraRec
Uzma Mushtaque
Transformer based models are increasingly being used in various domains including recommender systems (RS). Pretrained transformer models such as BERT have shown good performance a…