collaborators

9 papers

cs.NI2026

FedSceneX: Time-to-Target Orchestration for Same-Scene Multimodal Federated Edge Learning

Dhe Yeong Tchalla, Beining Wu, Jun Huang +2

Federated learning at the sensing edge is typically evaluated by communication rounds, yet a round does not represent a fixed amount of work. Even on identical hardware, the method…

cs.AI2026

CrystalMem: Elastic Memory for Self-Evolving LLM Agents via Knowledge Crystallization

Beining Wu, Jun Huang

Memory for self-evolving large language model (LLM) agents is often provisioned as if its byte budget only grows. Cloud platforms, however, adjust quotas with load and cost, and we…

cs.NI2026

When Unlearning Fails: Reliable Data Deletion under Post-Training in Agent Networks

Zihao Ding, Jun Huang, Liang Dong

Self-improving federated agent networks keep training after deployment by collecting new trajectories with the current policy and feeding them back into later rounds. This closed l…

cs.LG2026

Forget to Improve: On-Device LLM-Agent Continual Learning via Budget-Curated Memory

Beining Wu, Zihao Ding, Jun Huang +1

On-device language-model agents improve by accumulating experience in retrieved memory rather than by updating weights. This memory is hard-bounded and exposed: it consumes RAM and…

cs.LG2026

Lifecycle-Aware Federated Continual Learning in Mobile Autonomous Systems

Beining Wu, Jun Huang

Federated continual learning (FCL) allows distributed autonomous fleets to adapt collaboratively to evolving terrain types across extended mission lifecycles. However, current appr…

cs.NI2026

RELIEF: Turning Missing Modalities into Training Acceleration for Federated Learning on Heterogeneous IoT Edge

Beining Wu, Zihao Ding, Jun Huang

Federated learning (FL) over heterogeneous IoT edge devices faces coupled system-modality-data heterogeneity: the lower-cost device carries both fewer sensors and less computationa…