works on

From the 1 of 48 linked papers with an AI index.

activity
20242026
collaborators

48 papers

cs.LG2026

FedLNS: Leverage LayerNorm Signature Modeling to Mitigate Adversarial Manipulation in Federated LLMs

Kai Li, Jong-Ik Park, Carlee Joe-Wong +2

Federated training enables language models to learn from distributed private text, but the server cannot directly verify the local supervision or optimization process that produces…

cs.LG2026

MultiPathFormer: Towards a Foundation Model for Multipath Wireless Propagation

Blessed Guda, Kayley Sze, Carlee Joe-Wong

Recent advances in machine learning have enabled training of wireless foundation models, which aim to support tasks such as channel estimation, beam prediction, and localization ba…

cs.MA2026

Auditing Emergent LLM-Agent Collaboration through Cooperation-Obligation Coupling

Zuyuan Zhang, Hanqing Yang, Carlee Joe-Wong +1

The paper proposes iCORE, a unified representation that combines a cooperation graph, an obligation graph, and an audit map to let auditors verify that each step of an LLM‑agent wo…

eess.AS2026

Representation Matters in Randomized Smoothing for Audio Classification

Jong-Ik Park, Shreyas Chaudhari, José M. F. Moura +1

Randomized smoothing (RS) certifies robustness in the vector space where Gaussian noise is added. In audio classification, this space is often not uniquely defined as standard pipe…

cs.LG2026

FedSteer: Taming Extreme Gradient Staleness in Federated Learning with Corrective Projections and Caching

Haoran Zhang, Cainã Figueiredo Pereira, Marie Siew +3

Federated learning (FL) is often subject to aggregation variance if clients do not consistently participate in training rounds. While reusing stale model updates from inactive clie…

cs.LG2026

Federated Large Language Models: Current Progress and Future Directions

Yuhang Yao, Jianyi Zhang, Junda Wu +11

Large Language Models have achieved impressive performance across diverse applications, yet their training typically depends on centralized data collection, raising serious privacy…