Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2609.23935v1 Announce Type: new Abstract: Post-training turns a general next-token predictor into a chat model with a persistent assistant persona. If that persona is a character the model play...
arXiv:2609.24821v1 Announce Type: new Abstract: The Linear Representation Hypothesis associates high-level concepts with directions in language models, but it remains unclear how these concept-relate...
arXiv:2609.22102v1 Announce Type: cross Abstract: Large Language Models (LLMs) are widely used as programming assistants, yet it remains unclear whether and how user's demographic information impacts...
arXiv:2410.17021v2 Announce Type: replace Abstract: Large Language Models with chain-of-thought prompting, such as OpenAI-o1, have shown impressive capabilities in natural language inference tasks. H...
arXiv:2604.08974v2 Announce Type: replace Abstract: Uncertainty quantification techniques measure confidence in language model outputs to support critical applications like hallucination detection an...
arXiv:2605.00468v2 Announce Type: replace Abstract: Plain Language Summaries (PLS) aim to make research accessible to lay readers, but they are typically written in a one-size-fits-all style that ign...
arXiv:2510.22172v2 Announce Type: replace-cross Abstract: The Continuous Integrate-and-Fire (CIF) mechanism provides effective alignment for non-autoregressive (NAR) speech recognition. This mechanis...
arXiv:2605.27110v2 Announce Type: replace-cross Abstract: In this work, we propose BAIT (Boundary-Aware Iterative Trap), a three-step jailbreak framework that elicits malicious information through in...
arXiv:2609.23561v1 Announce Type: new Abstract: Deploying efficient neural networks is essential in resource-constrained environments, yet compact models often sacrifice interpretability - a critical...
arXiv:2609.24075v1 Announce Type: new Abstract: Computer-vision systems used for construction monitoring can degrade under adverse environmental and visual conditions, yet such conditions remain unde...
arXiv:2609.24210v1 Announce Type: new Abstract: Building strong chart-to-code systems increasingly relies on reinforcement learning, whose effectiveness depends critically on the quality of the rewar...
arXiv:2609.24220v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) systems over enterprise knowledge bases must ingest heterogeneous document formats -- PDFs, Word documents, presen...
arXiv:2609.24727v1 Announce Type: new Abstract: Spatial--temporal benchmarks are valid only when their questions, source annotations, and answer options identify the same physical quantity. We audit...
arXiv:2609.24872v1 Announce Type: new Abstract: Two-stage oriented detectors achieve high localization accuracy in synthetic aperture radar (SAR) ship detection, but their large backbones, feature py...
arXiv:2609.24304v1 Announce Type: cross Abstract: Astronomical maps made with different tracers are not expected to have identical morphology. Excitation, optical depth, chemistry, radiation, and ISM...
arXiv:2411.15921v3 Announce Type: replace Abstract: The removal of multiplicative Gamma noise is a critical research area in the application of synthetic aperture radar (SAR) imaging, where neural ne...
arXiv:2509.25998v4 Announce Type: replace Abstract: In light of recent progress in video editing, deep learning models focusing on both spatial and temporal dependencies have emerged as the primary m...
arXiv:2511.18921v2 Announce Type: replace Abstract: Backdoor attacks undermine the reliability and trustworthiness of machine learning systems by injecting hidden behaviors that can be maliciously ac...
arXiv:2607.06782v2 Announce Type: replace-cross Abstract: Under field-of-view (FOV) mismatch, pooling LiDAR features over unequal angular support can distort compact retrieval keys and exclude correc...
The paper introduces “CoLSafe-MDP”, a reinforcement learning algorithm that ensures safe exploration in constrained Markov decision processes. It replaces computationally heavy Gaussian process methods with a Nadaraya-Watson estimator, achieving constant-time scaling for estimate bounds. The authors evaluate the algorithm on a grid-based environment and on observational Martian terrain data.