7 papers
FATE: Focal-modulated Attention Encoder for Multivariate Time-series Forecasting
Tajamul Ashraf, Janibul Bashir
Climate change stands as one of the most pressing global challenges of the twenty-first century, with far-reaching consequences such as rising sea levels, melting glaciers, and inc…
Context Aware Grounded Teacher for Source Free Object Detection
Tajamul Ashraf, Rajes Manna, Partha Sarathi Purkayastha +2
Source-free object detection (SFOD) faces persistent challenges due to class imbalance-driven context bias and instability in teacher-student training under noisy pseudo-labels. Ex…
ATR-Bench: A Federated Learning Benchmark for Adaptation, Trust, and Reasoning
Tajamul Ashraf, Mohammed Mohsen Peerzada, Moloud Abdar +5
Federated Learning (FL) has emerged as a promising paradigm for collaborative model training while preserving data privacy across decentralized participants. As FL adoption grows,…
Bolbosh: Script-Aware Flow Matching for Kashmiri Text-to-Speech
Tajamul Ashraf, Burhaan Rasheed Zargar, Saeed Abdul Muizz +5
Kashmiri is spoken by around 7 million people but remains critically underserved in speech technology, despite its official status and rich linguistic heritage. The lack of robust…
Generalizable Federated Learning using Client Adaptive Focal Modulation
Tajamul Ashraf, Iqra Altaf Gillani
Federated learning (FL) has proven essential for privacy-preserving, collaborative training across distributed clients. Our prior work, TransFed, introduced a robust transformer-ba…
TITAN: Query-Token based Domain Adaptive Adversarial Learning
Tajamul Ashraf, Janibul Bashir
We focus on the source-free domain adaptive object detection (SF-DAOD) problem when source data is unavailable during adaptation and the model must adapt to an unlabeled target dom…