Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2610.17234v1 Announce Type: new Abstract: Video reward models are trained and evaluated on human preferences between videos that often differ simultaneously on properties such as prompt alignme...
arXiv:2610.14826v1 Announce Type: cross Abstract: Recent alignment-free Text-to-Speech (TTS) models achieve high synthesis quality by removing explicit alignment modules and simplifying training. How...
arXiv:2610.16275v1 Announce Type: cross Abstract: Flow Matching (FM) has recently emerged as a principled and efficient generative modeling framework for reinforcement learning (RL), enabling express...
arXiv:2610.14576v1 Announce Type: new Abstract: As frontier LLMs gain more capabilities, the cost to run them also goes up. At the same time, small language models (SLMs) also gain more capabilities...
arXiv:2610.14980v1 Announce Type: new Abstract: We present a generator of Thai klon pad verse, one stanza from a short topic, and evaluate it against human verse on held-out topics. The generator is...
arXiv:2610.15179v1 Announce Type: cross Abstract: Large language models are increasingly deployed in contexts requiring adherence to ethical and legal norms, yet their alignment with internationally...
arXiv:2610.16329v1 Announce Type: cross Abstract: Accurate breast cancer risk prediction from screening mammography is essential for improved risk stratification and personalized screening. It can be...
arXiv:2610.18108v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as judges to predict which of two candidate answers a human evaluator would prefer, providing a sc...
arXiv:2610.18494v1 Announce Type: cross Abstract: Objective digital measures of depression severity could complement conventional symptom assessments and facilitate more timely clinical evaluation. H...
arXiv:2602.08302v3 Announce Type: replace-cross Abstract: Delayed generalization, where training accuracy becomes nearly perfect substantially before test accuracy, has often been studied in the cont...
arXiv:2603.02022v3 Announce Type: replace-cross Abstract: Speech Bandwidth Extension improves clarity and intelligibility by restoring/inferring appropriate high-frequency content for low-bandwidth s...
arXiv:2604.02341v2 Announce Type: replace-cross Abstract: Mathematical reasoning in large language models has improved substantially with reinforcement learning using verifiable rewards, where final...
arXiv:2604.19734v2 Announce Type: replace-cross Abstract: Scaling humanoid foundation models is bottlenecked by the scarcity of robotic data. While massive egocentric human data offers a scalable alt...
arXiv:2604.23238v3 Announce Type: replace-cross Abstract: Distillation via reasoning traces exposes frontier models to adversarial third parties, who can bypass their guardrails and misappropriate th...
arXiv:2610.19831v1 Announce Type: new Abstract: Although multivariate time series forecasting has broad application prospects, effectively incorporating exogenous variables remains challenging. Preva...
arXiv:2610.18948v1 Announce Type: cross Abstract: Finite safety assessments cannot exclude an adversary that preserves unattacked behavior until certification and activates afterward. We characterize...
arXiv:2610.19344v1 Announce Type: cross Abstract: Layer-ablation studies often perturb early or late layers of a language model, compare the damage to prediction on two corpora, and read a larger ear...
arXiv:2610.19498v1 Announce Type: cross Abstract: Model signing authenticates the full-precision weights W an LLM is released with, yet users run a quantized artifact Q whose producing transformation...
arXiv:2610.19607v1 Announce Type: cross Abstract: Rising privacy concerns around large language models have accelerated research in private Transformer inference (PTI). Synthesizing the empirical cla...
arXiv:2609.32384v2 Announce Type: replace Abstract: Real-world time series are inherently non-stationary, with trends, periodic patterns, and uncertainty evolving over time. While the Fourier domain...