Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 24190v1 Announce Type: cross Abstract: Social robots that rely on large language models for conversation are unable to retain information across sessions.
arXiv:2504. 08909v2 Announce Type: replace Abstract: Digital elevation models derived from Interferometric Synthetic Aperture Radar (InSAR) data over glacial and snow-covered regions often exhibit systematic elevation errors, commonly termed "penetration bias.
arXiv:2504. 01219v2 Announce Type: replace Abstract: Neural networks are notorious for forgetting old skills when taught new ones - a problem known as catastrophic forgetting.
arXiv:2607. 23284v1 Announce Type: new Abstract: Automated sleep staging is increasingly used in large-scale studies to derive sleep-architecture endpoints: total sleep time, REM latency, sleep efficiency, and bout-duration statistics.
arXiv:2607. 24339v1 Announce Type: new Abstract: Large language model (LLM) agents inherit reactive failure modes: escalation under provocation, sycophantic drift under flattery, perseveration when stuck.
arXiv:2607. 23018v1 Announce Type: cross Abstract: Nonstationary Gaussian process (GP) models are powerful tools for capturing input-dependent variability by adapting to observed data.
arXiv:2607. 23054v1 Announce Type: cross Abstract: Multi-head Latent Attention (MLA), introduced in DeepSeek-V2, compresses key-value pairs through a shared low-rank bottleneck (cKV), achieving 81% KV-cache reduction during inference.
arXiv:2607. 23075v1 Announce Type: cross Abstract: Detecting fake-order fraud at scale remains a critical challenge for large online-to-offline (O2O) service platforms, as existing approaches often rely on expert-designed features, produce black-box decisions, and provide limited interpretability.
arXiv:2607. 23002v1 Announce Type: cross Abstract: Large language models increasingly write both code and the tests meant to check it; coverage records what ran, not what was verified.
arXiv:2607. 22794v1 Announce Type: cross Abstract: Automatic depression detection with deep learning has shown promise but often suffers from limited generalization due to domain shift arising from inter-speaker variability.
arXiv:2607. 22797v1 Announce Type: cross Abstract: Trustworthy deployment of AI-based diagnosis in safety-critical mechanical systems hinges on validation: whether a prediction can be checked against physical reality before it is acted upon.
arXiv:2607. 23929v1 Announce Type: new Abstract: LLM agents increasingly coordinate through persistent shared memory: one agent's write becomes another agent's premise, and eventually a tool call with real side effects.
arXiv:2607. 22758v1 Announce Type: cross Abstract: The integration of iterative LLMs within multi-agent diagnostic frameworks requires a rigorous quantitative reevaluation of underlying communication topologies.
arXiv:2607. 22766v1 Announce Type: cross Abstract: The alignment of Large Language Models (LLMs) is increasingly bottlenecked by data quality.
arXiv:2607. 22716v1 Announce Type: cross Abstract: In this paper, we show for the first time that visual token pruning enhances the robustness of Multimodal Large Language Models (MLLMs), mitigating vulnerabilities such as jailbreak attacks and hallucinations.
arXiv:2607. 22566v1 Announce Type: new Abstract: MedLoCoMo is a Medical Long-Context Memory benchmark for patient-specific clinical reasoning over multi-admission medical dialogue.
arXiv:2607. 23557v1 Announce Type: cross Abstract: FastLAS is a scalable system for Inductive Logic Programming (ILP): you give it some background knowledge, a language bias, and a set of examples, and it searches for a set of logic program rules (a hypothesis) that explains the examples.
arXiv:2607. 24522v1 Announce Type: new Abstract: While on-policy distillation (OPD) effectively addresses sparse rewards and exposure bias in large language model post-training, its extension to flow models remains underexplored.
arXiv:2607. 22925v1 Announce Type: cross Abstract: A key question for AI safety is whether a language model expresses all of its reasoning in its output tokens.
arXiv:2605. 14108v2 Announce Type: replace-cross Abstract: Diabetic Retinopathy (DR) is one of the leading causes of preventable blindness, and automated screening can help extend specialist capacity in resource-constrained clinical workflows.