Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 14962v1 Announce Type: cross Abstract: Text-to-image (T2I) models can synthesize realistic, prompt-aligned images, yet samples generated for the same prompt often cover only a small subset of visually distinct modes.
arXiv:2607. 14275v1 Announce Type: new Abstract: Context engineering has become central to building reliable AI agents, yet it remains largely unmeasured.
arXiv:2607. 14249v1 Announce Type: new Abstract: Mobile usage traces are critical for tasks such as user behavior prediction and app recommendation, yet their use is constrained by privacy restrictions and costly large-scale data collection.
arXiv:2406. 01514v4 Announce Type: replace-cross Abstract: We introduce a training-free safety enhancement method for aligning large language models (LLMs) without the need for supervised fine-tuning or reinforcement learning from human feedback.
arXiv:2607. 14466v1 Announce Type: new Abstract: Noise injection is a well-known technique in stochastic optimization.
arXiv:2602. 13061v2 Announce Type: replace-cross Abstract: The ability of Flow Matching (FM) to model complex conditional distributions has established it as the state-of-the-art for prediction tasks (e.
arXiv:2607. 14651v1 Announce Type: cross Abstract: Persistent external memory enhances agent continuity but introduces persistent security vulnerabilities: adversarial content can be injected via standard interaction channels, retained across turns, and later distort downstream behavior.
arXiv:2603. 16351v2 Announce Type: replace-cross Abstract: Accurate taxonomic identification of parasitoid wasps within the superfamily Ichneumonoidea is essential for biodiversity assessment, ecological monitoring, and biological control programs.
arXiv:2607. 14194v1 Announce Type: cross Abstract: Text-to-video (T2V) generators can synthesize realistic and temporally coherent videos, but controllably removing a target concept from a generator remains difficult.
arXiv:2607. 14607v1 Announce Type: cross Abstract: Machine learning (ML) models deployed in sensitive domains such as healthcare, law enforcement, and finance must satisfy not only utility requirements but also fairness and privacy guarantees.
arXiv:2607. 14932v1 Announce Type: cross Abstract: Synthetic face datasets have become effective enough to train face recognition models with accuracy rivaling that of models trained on real photographs.
arXiv:2607. 14095v1 Announce Type: new Abstract: Retrieval Augmented Generation (RAG) has proven to be a widely successful process at improving the quality of outputs from a Large Language Model (LLM) for wider context.
arXiv:2607. 15095v1 Announce Type: cross Abstract: The formation of political coalitions is a complex negotiation driven by both concrete policy objectives and deep-seated ideological convictions.
arXiv:2607. 14256v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) are increasingly deployed for nuanced content safety and moderation tasks, yet they remain vulnerable to adversarial attacks and out-of-distribution edge cases.
arXiv:2607. 14240v1 Announce Type: new Abstract: Current alignment approaches typically focus on emulating human behavior using static representations of human preferences, failing to capture the dynamic, context-dependent nature of real-world human-AI interactions.
arXiv:2607. 14791v1 Announce Type: new Abstract: Transcoders have recently emerged as a promising approach for mechanistic interpretability (MI), enabling circuit-level analysis of model behaviour.
arXiv:2607. 14126v1 Announce Type: new Abstract: Type 1 Diabetes (T1D) is a chronic, life-threatening autoimmune condition characterized by the complete destruction of insulin-producing pancreatic beta cells.
arXiv:2607. 15202v1 Announce Type: new Abstract: Annotation quality is a major bottleneck in building reliable and explainable artificial intelligence (XAI) systems for mental health research.
arXiv:2607. 15080v1 Announce Type: new Abstract: This article explores the application of covariate balance diagnostics for detecting the presence of hidden confounding/model miss-specification in studies applying offline reinforcement learning (RL) to deriving optimal treatment recommendations.
arXiv:2607. 14345v1 Announce Type: cross Abstract: People use language models for practical questions whose answers are difficult to verify.