Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2610.27211v1 Announce Type: new Abstract: Continual vision-language models (VLMs) encounter a stream of environments and must also reject inputs that do not belong to the environment at hand....
arXiv:2610.27952v1 Announce Type: new Abstract: Split Computing (SC) is a distributed inference method designed for balancing computational load and reducing latency by partitioning a neural network...
arXiv:2610.28366v1 Announce Type: new Abstract: Independently trained autoregressive language models often acquire similar capabilities, but it remains unclear whether their internal representations...
arXiv:2610.27789v1 Announce Type: new Abstract: Empirical scaling laws relate validation loss to model size, training exposure and compute, providing a quantitative basis for allocating resources. Th...
arXiv:2510.13003v2 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) enables efficient fine-tuning of large language models but suffers from catastrophic forgetting when learned updates inter...
arXiv:2610.27259v1 Announce Type: cross Abstract: The rapid evolution of Large Language Models is fueled by massive datasets, yet this reliance poses severe privacy risks, as models can inadvertently...
arXiv:2610.27491v1 Announce Type: cross Abstract: Real-world audio typically contains concurrent sound events, yet standard self-supervised methods treat each clip as an isolated training unit withou...
arXiv:2610.27675v1 Announce Type: cross Abstract: The emergence of increasingly sophisticated and evasion-resistant phishing attack strategies represents a significant threat to modern cybersecurity,...
arXiv:2610.28107v1 Announce Type: cross Abstract: Gradient clipping is a key tool for obtaining high-probability convergence guarantees for stochastic first-order methods under heavy-tailed noise. Ex...
arXiv:2610.28187v1 Announce Type: cross Abstract: Testing LLM-based software is expensive: each input needs several sampled responses, each judged by a costly oracle. Further, every prompt or model c...
arXiv:2610.28315v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly use persistent memory to personalize responses, and personal attributes in this memory pose a privacy...
arXiv:2505.19183v4 Announce Type: replace Abstract: This book offers a hands-on introduction to building and understanding federated learning (FL) systems. FL enables multiple devices -- such as smar...
arXiv:2605.22341v2 Announce Type: replace Abstract: Hard-label classification is usually trained with smooth surrogate losses such as softmax cross-entropy. We isolate a mechanism by which this misma...
arXiv:2605.30526v2 Announce Type: replace Abstract: Aligned language models often exhibit a recognizable AI-like style, yet its connection to post-training and internal representations remains poorly...
arXiv:2512.10570v3 Announce Type: replace-cross Abstract: Flexible survival prediction does not by itself ensure valid inference for covariate effects or subject-specific survival probabilities. We d...
arXiv:2610.27269v1 Announce Type: new Abstract: With the widespread adoption of large language models (LLMs) across languages and domains, AI safety has emerged as a critical global concern. However,...
arXiv:2608.25505v2 Announce Type: replace-cross Abstract: Masked diffusion models generate sequences in rounds, predicting several masked positions at once. Fewer rounds can accelerate decoding, but...
arXiv:2610.27800v1 Announce Type: new Abstract: Face presentation attack detection is typically studied under fixed camera or handheld acquisition, whereas smart glass capture introduces a more chall...
arXiv:2610.27874v1 Announce Type: new Abstract: Hyperspectral Image (HSI) reconstruction has made substantial progress with the deep unfolding framework by decomposing the problem into a projection m...
arXiv:2610.28229v1 Announce Type: cross Abstract: Direct Preference Optimization (DPO) minimizes empirical risk over observed preference comparisons, implicitly assuming that the training preference...