Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2601. 17360v2 Announce Type: replace-cross Abstract: An adversary observing a model's released prediction can infer sensitive attributes of the queried input, or even reconstruct representatives of the model's training data.
arXiv:2606. 11533v1 Announce Type: cross Abstract: The advancement of AI capabilities compels researchers and the public to be more aware of its potential worldwide impact.
arXiv:2605. 28591v2 Announce Type: replace-cross Abstract: The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings.
arXiv:2606. 12074v1 Announce Type: cross Abstract: Face recognition systems have advanced significantly through deep learning techniques, delivering high performance and robustness in complex scenarios.
arXiv:2606. 12392v1 Announce Type: cross Abstract: Recently, large language models (LLMs) have achieved promising progress in the fields of classical Chinese translation and the generation of classical poetry.
arXiv:2606. 11195v1 Announce Type: cross Abstract: Large language models (LLMs) have transformed how humans access information, but not how we reason with it.
arXiv:2606. 11949v1 Announce Type: new Abstract: We present an online monitoring system for distributional shift in deployed safety classifiers, using calibrated sequential statistics to detect when a classifier has moved out of distribution.
arXiv:2606. 12342v1 Announce Type: cross Abstract: Domain fine-tuning degrades the safety of large language models: fine-tuned specialists readily comply with harmful prompts framed in domain language.
arXiv:2603. 21396v5 Announce Type: replace Abstract: Recent work has shown that LLMs can sometimes detect when steering vectors are injected into their residual stream and identify the injected concept -- a phenomenon termed "introspective awareness.
arXiv:2606. 11265v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems are vulnerable to corpus poisoning attacks that manipulate downstream model outputs through malicious knowledge injection.
arXiv:2604. 13733v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) enables high-frequency, closed-loop control for robotic manipulation, but scaling to long-horizon tasks with sparse or imperfect rewards remains difficult due to inefficient exploration and poor credit assignment.
arXiv:2606. 11835v1 Announce Type: cross Abstract: Collecting participants' lived experiences is central to design research.
arXiv:2606. 12397v1 Announce Type: cross Abstract: Router is the cornerstone component to the Mixture-of-Experts models.
Recently, large language models (LLMs) have achieved promising progress in the fields of classical Chinese translation and the generation of classical poetry. However, domain-specific research on precise translation and affective-semantic understanding of classical poetry remains limited.
Language-model post-training is the main stage at which model behavior is shaped, yet it still largely involves optimization of scalar rewards that summarize diverse desiderata. This abstraction gives practitioners little visibility into what their data actually teaches models, allowing spurious correlations to be learned by a model and inducing undesirable behaviors such as over-stylization and sycophancy.
Domain fine-tuning degrades the safety of large language models: fine-tuned specialists readily comply with harmful prompts framed in domain language. Existing inference-time defenses that mix logits from a safe anchor model require both models to share a vocabulary, which rules them out for the cross-family specialists where safety is most degraded.
World Action Models (WAMs) offer a promising route for robot manipulation by using video generation models to model future scene evolution before producing control actions. However, our empirical observations reveal a phenomenon: generating plausible visual futures does not always guarantee the extraction of accurate actions.
Sensitive personal information can appear in large-scale pre-training corpora for large language models (LLMs). Detecting and filtering such information is therefore essential to ensure compliance with privacy regulations and prevent unintended information leakage.
Automating compliance check for geometry-intensive regulations remains a significant technical bottleneck in Building Information Modeling (BIM), primarily due to the semantic disparity between high-level regulatory logic and structured IFC data. Existing methods, often reliant on static rule templates, struggle to traverse multi-hop reasoning chains or resolve latent spatial dependencies across multiple building entities.
Google DeepMind and partners announce a $10M funding call for multi-agent safety research.
