arXiv:2505.11924v4 Announce Type: replace-cross Abstract: Intrinsic moral self-correction refers to the phenomenon where a language model refines its ethical judgments or aligns its outputs purely through prompting. While effective across diverse tasks, its mechanism remains unclear. We hypothesize intrinsic moral…
arXiv:2608.20480v1 Announce Type: new Abstract: Optimal learners are tailored to exploit the i.i.d. data assumption underlying the classic PAC model. What if an i.i.d. training sample were corrupted with correctly labeled examples drawn from an otherwise unrelated, even adversarial source?…
arXiv:2606.02507v2 Announce Type: replace-cross Abstract: Inverse materials design is shifting materials discovery from forward prediction toward targeted proposal of candidates that satisfy objectives under physical constraints. Here, we review advances in generative crystal structure modeling, multimodal learning, and closed-loop design…
arXiv:2608.20488v1 Announce Type: new Abstract: AI tools increasingly support tasks across the scientific research cycle, from experiment design and manuscript preparation to peer review. At the same time, the continuing growth in conference submissions has increased the burden on meta-reviewers,…
arXiv:2608.20532v1 Announce Type: new Abstract: NVIDIA provides a SASS disassembler but no public SASS assembler for recent data-center GPUs, limiting controlled machine-code rewriting. We present F2Asm, which learns exact 128-bit SASS encoders from paired disassembly and original CUBIN instruction words.…
arXiv:2608.21134v1 Announce Type: cross Abstract: Deploying vision-language models (VLMs) on mobile devices is challenging due to their significant memory and compute requirements. We present a framework for quantizing VLMs for efficient inference on resource-constrained hardware. Our approach combines a quantization…
arXiv:2510.12734v2 Announce Type: replace Abstract: Variable importance (VI) methods are often used for hypothesis generation, feature selection, and scientific validation. In the standard VI pipeline, an analyst estimates VI for a single predictive model with only the observed features. However,…
arXiv:2608.20497v1 Announce Type: new Abstract: Deploying high-accuracy neural networks on resource-constrained edge devices remains challenging, as existing approaches treat training, compression, and hardware synthesis as separate stages, leaving a gap between software-trained models and efficient end-to-end deployment with limited support…
arXiv:2608.20566v1 Announce Type: new Abstract: AI agents extend large language models from single prompt-response interactions to long-running, goaldirected workflows that issue many model calls, invoke tools, and interact with external environments. These workflows enable tasks such as software repair, data…
arXiv:2608.21262v1 Announce Type: cross Abstract: Many machine-learning systems set a threshold at a quantile of a calibration set: conformal predictors that promise 90% coverage by drawing their cutoff at the calibration set’s 90th percentile, abstention gates that decline to answer…
