arXiv:2410.21582v4 Announce Type: replace-cross Abstract: Large-scale pretrained models are widely leveraged as foundations for learning new specialized tasks via fine-tuning, with the goal of mainta...
arXiv:2608. 05025v1 Announce Type: new Abstract: Joint Energy-Based Models (JEM) unify classification and generation within a single network and support out-of-distribution (OOD) detection.
arXiv:2609.06934v1 Announce Type: cross Abstract: Post-hoc safety training (RLHF, DPO) is the dominant way to align large language models, yet jailbreaks (Zou et al., 2023b), fine-tuning attacks (Qi...
The paper investigates why post‑hoc out‑of‑distribution (OOD) detectors often report inflated gains. It shows that many detectors learn to recognize the specific dataset they were trained on rather than true novelty, a phenomenon called the inflation gap. By holding out entire OOD datasets during evaluation, the authors demonstrate that most reported gains vanish, and they provide a closed‑form method to predict which fits will inflate.
arXiv:2606. 31591v1 Announce Type: cross Abstract: Emergent misalignment (EM) is a recently discovered phenomenon in LLMs where fine-tuning on a narrow misaligned task, such as writing insecure code, leads to broadly misaligned behaviour on unrelated prompts.
The paper introduces PLUS, a detector‑agnostic subspace signal that enhances near‑out‑of‑distribution (near‑OOD) detection. PLUS selects the most class‑active neurons via a sparse autoencoder, orthonormalizes their decoder directions to form a low‑dimensional subspace, and scores inputs using a per‑class whitened squared Mahalanobis distance within that subspace. The resulting signal is fused additively with any calibrated base score using a single global weight, improving near‑OOD AUROC across 126 detector–backbone combinations while largely preserving far‑OOD performance.
Self-supervised pretraining has produced capable time-series foundation models, but its value for Prognostics and Health Management (PHM) has not been measured under leakage-controlled conditions. We...
The study evaluates self‑supervised pretraining for Prognostics and Health Management (PHM) across 47 public datasets, using a compact Transformer encoder trained with masked patch prediction. Transfer performance is highly task‑dependent: it dramatically improves fault‑classification on CWRU and HSG18 but offers no reliable benefit for remaining‑useful‑life estimation on CMAPSS. The authors also compare centralized versus simulated federated pretraining, finding that centralized training generally outperforms federated training under matched budgets, and that the intrinsic SSL loss does not reliably predict downstream performance.
arXiv:2605. 11554v2 Announce Type: replace Abstract: Task-agnostic structure proxies are often used to interpret why one pretraining corpus transfers better than another, but such explanations require the proxy to track the structure that matters for the downstream task.
arXiv:2608. 05025v2 Announce Type: replace Abstract: Joint Energy-Based Models (JEM) unify classification and generation within a single network and support out-of-distribution (OOD) detection.
Post-hoc out-of-distribution (OOD) detection is mature on far-OOD yet remains weak on near-OOD. These two settings differ in their use of class-characteristic feature directions: far-OOD inputs largel...
The paper investigates why the train‑validation performance gap widens during fine‑tuning of pretrained models. It proposes a dynamic structural explanation: as training proceeds, updates shift from broadly reusable features to more example‑specific ones, increasing gradient heterogeneity and the gap. Experiments on synthetic ResMLP hierarchies, NLP models (RoBERTa, DeBERTa, Qwen) across six datasets, and vision models (ResNet‑18) confirm that higher reliance on private features correlates with larger accuracy gaps, supporting the proposed account.