Hybrid-Policy Self-Editing for Composable Unstructured Knowledge Editing

Large language models (LLMs) achieve remarkable performance across natural language tasks, yet they are trained on static corpora and their knowledge quickly becomes outdated in a fast-changing world. This motivates knowledge editing (KE), which updates specific knowledge in an LLM without changing unrelated others. Recent works move from structured knowledge triples toward unstructured KE (UKE), where the edit is a free-form passage that may state multiple facts at once. Nonetheless, existing editors inject such a passage yet fail to use it: the edited model can recall the passage, but can neither answer atomic questions about its facts nor compose them into multi-hop reasoning. We attribute this missing property, which we term composability, to editors' passive reliance on the fixed passage as the sole learning source. In response, we cast editing as a proactive self-distillation from a privileged in-context state of the same model, which requires no external supervision. We further reveal that due to the novelty of the injected knowledge, the pre-edited model's own rollouts rarely cover it, which limits the effectiveness of pure on-policy distillation. To close this gap, we propose HPSE, which builds a hybrid rollout that steps in to place missing facts onto the student's own trajectory precisely where its coverage fails, while staying on-policy elsewhere. We theoretically analyze HPSE's advantage over pure on-policy distillation, and empirically establish its plug-and-play improvements across four LLM backbones and two KE editors under various scenarios.

mmSimPrior: Learning Simulation Priors for Data-Efficient Real-World Generalizable Radar-Based Human Motion Reconstruction

Millimeter-wave (mmWave) radar offers privacy-preserving and lighting-robust sensing for human motion reconstruction, but learning models that generalize across real deployments require diverse paired radar-motion data that are costly to collect. Simulation provides scalable supervision, yet models trained on clean synthetic signals transfer poorly because of multipath, clutter, response statistics, and resolution degradation. We present mmSimPrior, a simulation-pretrained framework that factorizes transferable knowledge into signal, motion, and radar-to-motion mapping priors. A multi-modal signal encoder is pretrained with a physics-informed domain-randomization curriculum that emulates propagation- and acquisition-level variations, while a joint-temporal tokenizer learns a discrete prior over plausible human motion. A shared mapping prior supports classification over a learned motion codebook for constrained zero-shot reconstruction and continuous regression for flexible limited-data adaptation. We further construct a 4.2M-frame, 31K-sequence dataset suite and introduce a No-Overlap Setting that excludes repeated complete subject-environment-location-motion configurations across adaptation and test. Experiments on mmSimPrior-Real and RT-Pose demonstrate consistent gains: with only 24 paired real sequences, mmSimPrior-Reg reduces MPJPE by 24.7% to 39.0% over the strongest baseline across the three environments, while mmSimPrior-Cls reduces zero-shot MPJPE by 8.5% without finetuning.

Towards Privacy-Preserving and Heterogeneity-aware Split Federated Learning via Probabilistic Masking

Split Federated Learning (SFL) has emerged as an efficient alternative to traditional Federated Learning (FL) by reducing client-side computation through model partitioning. However, exchanging of intermediate activations and model updates introduces significant privacy risks, especially from data reconstruction attacks that recover original inputs from intermediate representations. Existing defenses using noise injection often degrade model performance. To overcome these challenges, we present PM-SFL, a scalable and privacy-preserving SFL framework that incorporates Probabilistic Mask training to add structured randomness without relying on explicit noise. This mitigates data reconstruction risks while maintaining model utility. To address data heterogeneity, PM-SFL employs personalized mask learning that tailors submodel structures to each client's local data. For system heterogeneity, we introduce a layer-wise knowledge compensation mechanism, enabling clients with varying resources to participate effectively under adaptive model splitting. Theoretical analysis confirms its privacy protection, and experiments on image and wireless sensing tasks demonstrate that PM-SFL consistently improves accuracy, communication efficiency, and robustness to privacy attacks, with particularly strong performance under data and system heterogeneity.