Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2605.12515v3 Announce Type: replace Abstract: Multilingual large language models (MLLMs) often answer culturally ambiguous questions inconsistently across languages, even for a fixed user perso...
arXiv:2610.23039v1 Announce Type: new Abstract: Feed-forward Gaussian models have made novel view synthesis almost instantaneous. Feed-forward methods predict Gaussians directly, either in two stages...
arXiv:2605.07772v2 Announce Type: replace Abstract: Transformers perform inference by iteratively transforming token representations across layers. This layerwise computation has been studied empiric...
arXiv:2610.22723v1 Announce Type: new Abstract: Large language models exhibit misbehaviors that hinder deployment in high-stakes settings. One approach to monitor such failures is to use an external...
arXiv:2610.22706v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) offer scalable annotations of social and affective content, but their temporal agreement with human judgments...
arXiv:2610.23297v1 Announce Type: cross Abstract: Single-image refocusing changes the focal plane and depth of field of a photograph after capture. It is inherently interactive: users try many focal...
arXiv:2610.23668v1 Announce Type: cross Abstract: Typed decision models often return more than a selected category. They also expose probabilities for each candidate and, sometimes, a separate confid...
arXiv:2609.33543v2 Announce Type: replace Abstract: Coupled rollouts can reduce the noise of counterfactual action comparisons, but two issues prevent standard common-random-number constructions from...
arXiv:2412.07658v3 Announce Type: replace-cross Abstract: Text-to-image diffusion models have rapidly transitioned from research prototypes to widely deployed tools. Along with their impressive capab...
arXiv:2601.19747v2 Announce Type: replace-cross Abstract: In the rapidly evolving field of Electronic Design Automation (EDA), the deployment of Large Language Models (LLMs) for Register-Transfer Lev...
arXiv:2605.22940v2 Announce Type: replace-cross Abstract: Entropy reduction is not a safety criterion: it can leave predictions unchanged or accompany increasing risk for a protected group. We study...
arXiv:2610.22583v1 Announce Type: new Abstract: We show that forced aligners degrade on spontaneous, noisy real-world speech, and that fillers, laughter, and disfluencies corrupt word boundaries, imp...
arXiv:2610.22930v1 Announce Type: cross Abstract: Artificial-intelligence (AI) policies are increasingly used to make consequential decisions in medicine, finance, education, and public services, yet...
arXiv:2610.22618v1 Announce Type: new Abstract: Large language models rely on spurious features in clinical classification: swapping a single gender token in clinical notes alters gender-irrelevant d...
arXiv:2610.23205v1 Announce Type: new Abstract: Large Language Models (LLMs) remain unreliable for extremely low-resource languages whose writing systems conflict with high-resource pretraining prior...
arXiv:2610. 20669v1 Announce Type: new Abstract: Reward-guided discrete diffusion enables test-time alignment with downstream objectives, but applying Sequential Monte Carlo (SMC) guidance at every denoising step is computationally expensive.
The paper introduces GUISE, a benchmark of criminal‑assistance scenarios drawn from real‑world cases and organized using the UNODC International Classification of Crime for Statistical Purposes. It evaluates large language models under three linguistic framings and across five cultures, finding that framing and cultural adaptation significantly increase unsafe compliance rates. The study also shows that unsafe responses from the least‑safe models exhibit strong Anglocentric language, with leakage growing alongside harmfulness.
GeoState introduces a view‑decoupled geometry representation for predictive 3D world modeling, separating scene‑state evolution from camera‑dependent observation. It aggregates multi‑view geometry foundation model features into a scene tokenizer, then uses a geometry decoder to query this state with camera rays. An autoregressive world model predicts future scene states while modeling camera motion independently, enabling consistent decoding under any camera and maintaining a single context‑derived scale throughout rollouts.
PocketTSLM is a mobile-native deployment of the OpenTSLM SoftPrompt time‑series language model that runs entirely on a consumer smartphone. By injecting encoded time‑series windows as embeddings instead of tokenizing them as text, PocketTSLM preserves temporal structure while using far fewer tokens and staying within the device’s context and memory limits. The model has been benchmarked on 30‑second EEG sleep‑staging clips and 10‑second ECG recordings, achieving on‑device inference with no health data transmitted to the cloud.
The paper examines how profit motives influence safety investment in AI, focusing on a supply chain with an upstream large language model (LLM) provider and multiple downstream firms. Using a game‑theoretic model, it shows that downstream competition tends to drive firms to invest more in safety than would maximize industry profit, while the upstream provider may underinvest because it does not capture all the benefits of safer models. The study also explores how regulatory interventions could shift incentives and affect overall model safety.