11 papers
From Propagation to Protection: Risk-Aware Diffusion for Harm Minimization in Signed Social Networks
Aaqib Zahoor, Janibul Bashir, Iqra Altaf Gillani
Real-world social relationships are not uniformly supportive. Information through hostile connections can increase resistance, anxiety, or misinformation rather than adoption. Clas…
Repair, Not Improvement: Decomposing Constrained Decoding in Tool-Call Abstention
Janghoon Lee
Function calling is what the recent accounting of constrained generation explicitly sets aside: it finds the decoder's contribution small for format constraints, then warns in its…
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…
Highly Dynamic and Fully Distributed Data Structures
John Augustine, Antonio Cruciani, Iqra Altaf Gillani
We study robust and efficient distributed algorithms for building and maintaining distributed data structures in dynamic Peer-to-Peer (P2P) networks. P2P networks are characterized…
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…