Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 09476v1 Announce Type: cross Abstract: Cowork agents may complete benign tasks while disclosing protected data, manipulating unauthorized state, invocate unauthorized API.
arXiv:2508. 03875v2 Announce Type: replace Abstract: Many sequential decision problems offer qualitatively different ways of influencing the environment: some interventions act immediately, whereas others induce persistent effects that continue to shape future states long after the decision that initiated them.
arXiv:2608. 07945v1 Announce Type: cross Abstract: Cloud-native serverless data warehouses achieve fine-grained elasticity by decoupling storage from compute, yet determining the optimal resource allocation for highly heterogeneous ad-hoc queries remains a formidable industrial challenge.
arXiv:2608. 08883v1 Announce Type: new Abstract: Recent advances in retrieval-augmented generation (RAG) and large language models (LLMs) enable researchers to integrate AI into scientific workflows.
arXiv:2608. 08046v1 Announce Type: new Abstract: Text-conditioned chest X-ray generation aims to synthesize realistic radiographs that faithfully depict specified findings.
arXiv:2608. 09688v1 Announce Type: cross Abstract: Adversarial training under long tailed distributions suffers from a dual imbalance: the class imbalance skews the training objective toward head classes, and the adversarial inner maximization may further amplify this bias.
arXiv:2608. 08350v1 Announce Type: new Abstract: The initialisation of deep neural networks determines whether information and gradients can propagate across depth, yet a unified theory connecting these properties to learning dynamics remains elusive.
arXiv:2608. 07786v1 Announce Type: new Abstract: Open-weight large language models (LLMs) are increasingly developed through complex, multi-stage pipelines, leading to intricate lineage relationships that reflect model origin, ownership, and evolution.
arXiv:2605. 00754v4 Announce Type: replace-cross Abstract: Reward models (RMs) have become an indispensable fixture of the language model (LM) post-training playbook, enabling policy alignment and test-time scaling.
arXiv:2608. 09225v1 Announce Type: cross Abstract: The key-value (KV) cache is the primary throughput optimization in modern large language model (LLM) inference, enabling prefix reuse across requests.
arXiv:2608. 07953v1 Announce Type: new Abstract: Distribution shift poses a significant challenge to the robustness of machine learning models, but the current solutions only aim to detect out-of-distribution (OOD) samples and predict uncertainty levels.
arXiv:2608. 09510v1 Announce Type: cross Abstract: Detecting machine-generated disinformation on social media is increasingly difficult as large language models (LLMs) make it easier to generate and rewrite misleading content at scale.
arXiv:2608. 07533v1 Announce Type: new Abstract: An embodied agent is an intelligent entity that interacts with its environment through a physical body.
arXiv:2608. 08032v1 Announce Type: new Abstract: Safety alignment in multilingual models is uneven: a model that reliably refuses a harmful request in English will often comply with the same request in a lower-resource language.
arXiv:2608. 07931v1 Announce Type: new Abstract: Large reasoning models (LRMs) are prone to hallucination, which undermines their reliability and poses challenges for safe deployment.
arXiv:2608. 07642v1 Announce Type: new Abstract: Aligning large language models (LLMs) with human values remains a major challenge, especially for trustworthy AI.
arXiv:2608. 09899v1 Announce Type: new Abstract: In fair ranked link prediction, demographic parity ($\Delta_\mathrm{DP}$) is a common fairness metric.
arXiv:2608. 08180v1 Announce Type: cross Abstract: Abstractive text summarization systems frequently generate fluent yet unfaithful summaries by fabricating or distorting relationships between entities and events.
arXiv:2608. 07750v1 Announce Type: cross Abstract: Deep Neural Networks (DNNs) have found successful deployment in numerous vision perception systems.
arXiv:2608. 07978v1 Announce Type: cross Abstract: Multi-agent large language model(LLM)systems are applied to structural design,yet most use one-shot generation and cannot verify their output,leaving themill-suited to safety-critical tasks.