Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2605. 14252v2 Announce Type: replace-cross Abstract: Spiking neural networks (SNNs), which are brain-inspired and spike-driven, achieve high energy efficiency.
arXiv:2606. 29196v1 Announce Type: new Abstract: Do language models know when they are being tested?
arXiv:2606. 29925v1 Announce Type: new Abstract: As deep learning models are increasingly deployed in high-stakes applications, providing well-calibrated uncertainty estimates has become as critical as achieving high predictive accuracy.
arXiv:2606. 28933v1 Announce Type: cross Abstract: Venture capital (VC) investment decisions face distinct challenges, such as multi-source heterogeneous data, non-stationary time series, and the demand for explainable predictions in high-stakes, low-data settings.
arXiv:2606. 26744v2 Announce Type: replace Abstract: We present HyperDFlash, a block-parallel speculative decoding framework tailored to DeepSeek-V4's Hyper-Connections (HC).
arXiv:2606. 29092v1 Announce Type: cross Abstract: In a changing decision problem, standard dynamic-regret analyses have often equated the cost of non-stationarity to how far loss moves.
arXiv:2603. 00742v2 Announce Type: replace Abstract: While Adam has long been the ubiquitous default optimizer for deep neural networks, Muon has recently seen rapid adoption due to its superior training speed.
arXiv:2606. 28347v1 Announce Type: cross Abstract: Contemporary AI safety spans pre-training interventions, post-training alignment, deployment-time controls, monitoring, and red-teaming.
arXiv:2606. 30372v1 Announce Type: new Abstract: Quantitative research across the social and behavioral sciences depends on human subject experiments that are expensive, slow, and subject to sampling bias.
arXiv:2606. 28330v1 Announce Type: cross Abstract: Embedding-based retrieval systems rely on the assumption that geometric proximity in highdimensional representation spaces reflects semantic relevance.
arXiv:2406. 13944v2 Announce Type: replace-cross Abstract: This paper establishes the generalization error of pooled min-$\ell_2$-norm interpolation in transfer learning, where data from diverse distributions are available.
arXiv:2606. 23129v2 Announce Type: replace-cross Abstract: Implicit Neural Representations (INRs) have been proven successful in encoding continuous signals through coordinate-based networks, yet facing a spectral dilemma: periodic activations capture fine details but act as all-pass filters that memorise noise, while spatially compact activations regularise effectively but suffer from low-frequency bias.
arXiv:2606. 28479v1 Announce Type: cross Abstract: CSIRTs increasingly fine tune language models on vulnerability scan records, but these records expose internal network topology and create privacy risks under regulations such as GDPR and LGPD.
arXiv:2606. 29581v1 Announce Type: cross Abstract: Modern LLM deployments routinely compress models and raise sampling temperature to reduce cost, latency, or repetition, yet safety evaluations usually treat these choices as fixed implementation details.
arXiv:2606. 28425v1 Announce Type: cross Abstract: Increasingly autonomous agentic AI systems pose novel multi-agent risks, such as secret collusion via covert communication channels.
arXiv:2606. 28343v1 Announce Type: cross Abstract: Retrieval-augmented generative agents rely on retrieval for grounding, yet are typically evaluated on a query-by-query basis.
arXiv:2606. 28332v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for medical and health-related questions, yet their safety in high-risk medical scenarios remains poorly understood.
arXiv:2606. 28593v1 Announce Type: cross Abstract: While recent vision-language models (VLMs) have achieved significant improvements on static visual-to-code tasks such as generating code for webpages, charts, or SVGs, it remains unclear whether they can recover temporal dynamics when motion is present.
arXiv:2606. 30219v1 Announce Type: new Abstract: LLM evaluation and AI safety face a shared measurement problem: benchmark scores, reward-model signals, and reported safety metrics can improve while the latent properties they are meant to represent remain difficult to verify.
arXiv:2606. 29522v1 Announce Type: new Abstract: A central hope behind process supervision is that models can expose intermediate variables that matter for their later behavior.