Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 14629v1 Announce Type: cross Abstract: As Large Language Models (LLMs) become the mainstay for information retrieval and summarization tasks, ensuring that they are always non-partisan and invulnerable to political bias is a critical step towards safer and more trustworthy Artificial Intelligence (AI).
arXiv:2508. 07195v2 Announce Type: replace-cross Abstract: Recent advances have demonstrated that Large Language Models (LLMs) can be effectively adapted for time series forecasting, revealing strong potential beyond natural language tasks.
arXiv:2504. 06659v2 Announce Type: replace-cross Abstract: Despite advances in Preference Alignment (PA) for Large Language Models (LLMs), mainstream methods like reinforcement learning with human feedback face notable challenges.
arXiv:2608. 15972v1 Announce Type: cross Abstract: Synchronized camera and wireless measurements observe the same scene through different physical channels.
arXiv:2608. 15113v1 Announce Type: cross Abstract: Learned image compression (LIC) has demonstrated remarkable rate-distortion (RD) performance in benign settings.
arXiv:2608. 16340v1 Announce Type: cross Abstract: The combination of traditional statistical models and neural network (NN) components into semi-structured hybrid models is an intriguing approach to construct models that, ideally, combine traditional interpretability with the unprecedented flexibility of NNs.
arXiv:2508. 09105v3 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) and its Multimodal Retrieval-Augmented Generation (MRAG) significantly improve the knowledge coverage and contextual understanding of Large Language Models (LLMs) by introducing external knowledge sources.
arXiv:2608. 16394v1 Announce Type: new Abstract: Generating regulation-compliant test scenarios is essential for validating safety-critical automotive systems, yet Large Language Models (LLMs) struggle to ground outputs in long, hierarchical standards.
arXiv:2608. 14646v1 Announce Type: cross Abstract: Interpretable representation learning remains a key challenge in modern neural computation, particularly when models are expected not only to perform but also to explain their reasoning.
arXiv:2405. 17678v2 Announce Type: replace-cross Abstract: Achieving zero-shot adversarial robustness without sacrificing generalization remains challenging for foundation models such as CLIP, especially under large adversarial perturbations.
arXiv:2608. 16084v1 Announce Type: new Abstract: Neural autoregressive models have rapidly emerged as powerful emulators of high-dimensional chaotic systems, yet their long-term instability and error growth remain poorly understood, leading to ad-hoc solutions.
arXiv:2608. 15260v1 Announce Type: cross Abstract: Maintaining global geometric consistency is a central challenge in long-sequence 3D reconstruction, with scale drift being the most critical failure mode.
arXiv:2608. 16094v1 Announce Type: new Abstract: Accurate protein structure prediction is fundamental to structural biology because protein structure underlies molecular function and provides a basis for mechanistic interpretation.
arXiv:2608. 16564v1 Announce Type: new Abstract: Machine learning (ML) is a key technology driving innovation today, but ensuring ML safety remains a major challenge for safety-related applications.
arXiv:2506. 01584v2 Announce Type: replace-cross Abstract: Developing machine learning (ML) systems for real-world deployment requires navigating context-dependent trade-offs among accuracy, fairness, stability, and other objectives.
arXiv:2601. 17944v2 Announce Type: replace-cross Abstract: We study repeated allocation of shared resources among agents with time-varying demands and capped linear utilities.
arXiv:2606. 12654v2 Announce Type: replace-cross Abstract: We develop a new, differentially private mean estimator called the balloon mean.
arXiv:2608. 16390v1 Announce Type: cross Abstract: PDF corpora advertise their size in tokens but compute every rate they publish (coverage, OCR routing, re-fetch recovery, language mix) per document, and none decomposes its token total.
arXiv:2608. 16627v1 Announce Type: cross Abstract: Natural language explanations (NLEs) are increasingly used as inputs, for example, as few-shot rationales that influence model behavior in in-context learning (ICL).
arXiv:2608. 16353v1 Announce Type: cross Abstract: Even well-aligned large language models confidently generate factually incorrect text, making hallucination a persistent reliability risk in high-stakes deployments.