Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 03197v1 Announce Type: new Abstract: Sharpness-Aware Minimization (SAM) improves generalization by seeking parameters whose loss is robust to local adversarial perturbations, but the quantitative mechanism underlying its implicit bias toward flat minima remains unclear.
arXiv:2608. 03662v1 Announce Type: new Abstract: Safety shields are runtime enforcement mechanisms that restrict the actions of a controller to guarantee safety.
arXiv:2608. 03838v1 Announce Type: new Abstract: Reasoning-based guard models improve LLM safeguards, but decoding explicit rationales for every interaction makes them costly to deploy.
arXiv:2608. 02674v1 Announce Type: cross Abstract: With the widespread deployment of large foundation models (LFMs) in open environments, safety threats are shifting from black-box jailbreaks toward white-box attacks that directly identify and disrupt internal safety neurons or routes.
arXiv:2608. 03148v1 Announce Type: cross Abstract: RAG improves the factual grounding of LLM by incorporating external knowledge, but deploying RAG on mobile and edge devices remains challenging because retrieved context increases computation and memory.
arXiv:2608. 03174v1 Announce Type: cross Abstract: Generative AI systems increasingly produce content whose provenance is difficult to verify, motivating watermarking techniques for identifying model-generated outputs.
arXiv:2608. 03581v1 Announce Type: cross Abstract: AI-assisted peer review is increasingly discussed and adopted as a tool to support the scientific publishing process, yet there is little systematic understanding of how publication venues regulate its use or of how capable current AI review systems are.
arXiv:2510. 10961v4 Announce Type: replace-cross Abstract: As language models become increasingly deployed in online environments, toxicity detection and detoxification have received growing attention.
arXiv:2608. 03499v1 Announce Type: new Abstract: Recent advances in persistent personal-agent frameworks are making human-centered agent networks realistic deployment targets: each user can be served by an AI agent that acts on the user's behalf, maintains state, and communicates with other agents through social and task relations.
arXiv:2603. 19066v2 Announce Type: replace-cross Abstract: Four-term word analogies (A:B::C:D) are classically modeled geometrically as parallelograms: adding the vector B-A+C produces D.
arXiv:2603. 20381v2 Announce Type: replace-cross Abstract: Understanding the fundamental mechanisms governing the production of meaning in the processing of natural language is critical for designing safe, thoughtful, engaging, and empowering human-agent interactions.
arXiv:2608. 02632v1 Announce Type: new Abstract: Circuit tracing is an exciting technique for revealing the internal computation of language models, but it requires a time-intensive manual step of grouping individual features or MLP neurons into supernodes.
arXiv:2608. 01666v2 Announce Type: replace-cross Abstract: However, whether these judges truly evaluate the scientific substance of ideas or are influenced by superficial stylistic presentation remains an open question.
arXiv:2608. 03324v1 Announce Type: new Abstract: Federated learning enables collaborative model training across distributed edge devices while strictly preserving data privacy.
arXiv:2608. 03887v1 Announce Type: new Abstract: Fine-tuning a large language model on new data degrades what it previously learned.
arXiv:2608. 02689v1 Announce Type: cross Abstract: We convert 21 of 28 full-attention layers of Qwen3-0.
arXiv:2608. 03395v1 Announce Type: cross Abstract: Deepfake technologies pose increasing threats to facial privacy and identity security, motivating proactive defenses that protect facial images before misuse.
arXiv:2412. 08394v2 Announce Type: replace Abstract: Deep neural networks (DNNs) are vulnerable to adversarial samples crafted by adding imperceptible perturbations to clean data, potentially leading to incorrect and dangerous predictions.
arXiv:2606. 20880v2 Announce Type: replace-cross Abstract: Decision-making under partial or adversarial observability requires accurate inference of the environment's latent state and its associated uncertainty.
arXiv:2608. 01755v2 Announce Type: replace Abstract: Recent Vision-Language-Action (VLA) models for autonomous driving (AD) increasingly utilize chain-of-thought (CoT) supervision to enhance the reasoning capabilities of their Vision-Language Model (VLM) components, yet existing annotation pipelines commonly expose the teacher model to the logged ground-truth (GT) future trajectory.