arXiv:2606.11063v1 Announce Type: cross Abstract: AI control protocols oversee untrusted models by monitoring their actions and modifying potentially unsafe steps, often using a trusted model. This partially tampers with the untrusted model’s trajectory. If the trusted model detects such an…
arXiv:2606.09877v1 Announce Type: new Abstract: LLM wiki systems compile knowledge into pre-filled KV caches for efficient inference, but assume a static corpus — an assumption that fails whenever the underlying information landscape evolves. We formalize Streaming Knowledge Compilation: given a…
arXiv:2502.07027v4 Announce Type: replace Abstract: Molecular Relational Learning (MRL) is widely applied in natural sciences to predict relationships between molecular pairs by extracting structural features. The representational similarity between substructure pairs determines the functional compatibility of molecular binding sites. Nevertheless,…
arXiv:2606.09878v1 Announce Type: new Abstract: Standard benchmarks report aggregate accuracy, but practitioners need to know which specific capabilities a model lacks. We introduce FailureScope, a behavioral-diagnosis method that clusters evaluation probes by their cross-model pass/fail patterns (leave-one-model-out, LOMO), and show…
arXiv:2511.10234v3 Announce Type: replace Abstract: While promising, graph reasoners based on Large Language Models (LLMs) lack built-in invariance to symmetries in graph representations. Operating on sequential graph serializations, LLMs can produce different outputs under node reindexing, edge reordering, or formatting…
arXiv:2606.09879v1 Announce Type: new Abstract: This study addresses on-device inference bottlenecks of Transformer models on Tenstorrent’s Tensix architecture and proposes an operator fusion strategy that enhances data locality. RMSNorm is fused with matrix multiplication in self-attention and in the FFN,…
arXiv:2602.12542v2 Announce Type: replace Abstract: Deep learning models for clinical event prediction on electronic health records (EHR) often suffer performance degradation when deployed under different data distributions. While domain adaptation (DA) methods can mitigate such shifts, their “black-box” nature prevents…
arXiv:2606.09880v1 Announce Type: new Abstract: Large-scale dynamic weighted directed networks (DWDNs) are widely used to model time-varying interactions among nodes. Latent factorization of tensors (LFT) extracts target knowledge from DWDNs via low-rank embedding. However, similar to many machine learning models,…
arXiv:2605.03217v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in settings that require nuanced ethical reasoning, yet existing bias evaluations treat model outputs as simply “biased” or “unbiased.” This binary framing misses the gradual, context-sensitive way bias…
arXiv:2606.09881v1 Announce Type: new Abstract: Deepfake detectors show large performance gaps across demographic groups. Existing fairness approaches require demographic labels, retraining, or sacrifice accuracy. We introduce Face-Fairness (FF), a plug-and-play framework for bias mitigation. Our primary contribution, Face-Feature Tuning (FFT),…
