Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 07538v1 Announce Type: new Abstract: As LLM agents move from decision support to autonomous procurement, firms need to know whether delegated negotiators create value, divide it predictably, and avoid money-losing contracts.
arXiv:2608. 09158v1 Announce Type: cross Abstract: Large audio-language models (LALMs) have demonstrated strong capabilities in understanding diverse audio inputs.
arXiv:2608. 09928v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) exhibit strong visual understanding, yet the internal features that cause these behaviors remain difficult to identify, audit, or control.
arXiv:2608. 08606v1 Announce Type: cross Abstract: Machine translation (MT) systems often fail to correctly translate gender, especially when converting from a gender-neutral language like English to a gendered target language such as Romanian.
arXiv:2608. 08567v1 Announce Type: new Abstract: A central obstacle in building graph foundation models is the input heterogeneity in terms of feature space dimensionality, semantics, and structure.
arXiv:2608. 07594v1 Announce Type: cross Abstract: Interpretability is often treated as a tax on capability: language models are trained as opaque systems, then explained after the fact, with methods whose reliability is difficult to establish.
arXiv:2608. 08029v1 Announce Type: cross Abstract: Khatri et al.
arXiv:2608. 07577v1 Announce Type: cross Abstract: A closed-set detector for autonomous driving must assign every object one of a fixed set of labels.
arXiv:2511. 10453v4 Announce Type: replace-cross Abstract: Large language models often respond to ambiguous requests by implicitly committing to one interpretation, frustrating users and creating safety risks when that interpretation is wrong.
arXiv:2608. 08430v1 Announce Type: cross Abstract: Virtual cells employ machine learning models to simulate and predict cellular behaviors, serving as a critical computational framework for investigating health and disease.
arXiv:2608. 09622v1 Announce Type: new Abstract: Reliability qualification of advanced semiconductor devices requires sequential stress decisions that balance characterization objectives against multiple competing failure mechanisms.
arXiv:2608. 08309v1 Announce Type: cross Abstract: We argue that learning visual representations without labels requires a training signal jointly complete across three non-overlapping objectives: semantic invariance across augmented views, patch-level spatial prediction, and representational non-degeneracy.
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.
arXiv:2608. 07750v1 Announce Type: cross Abstract: Deep Neural Networks (DNNs) have found successful deployment in numerous vision perception systems.
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. 09523v1 Announce Type: new Abstract: Deep neural network (DNN) training with stochastic gradient descent (SGD) and its variants achieves strong empirical performance, yet classical optimization theory does not fully explain this success.
arXiv:2608. 07535v1 Announce Type: cross Abstract: Multi-modal large language models (MLLMs) integrate heterogeneous modalities through modality alignment and fusion, enabling stronger understanding and reasoning.
arXiv:2608. 08160v1 Announce Type: cross Abstract: The rapid advancement of Large Language Models (LLMs) is revolutionizing AI for Games by enabling open-ended and fluid interactive storytelling.
arXiv:2608. 07639v1 Announce Type: cross Abstract: Agent Skills provide reusable capabilities to LLM agents.
arXiv:2608. 08968v1 Announce Type: cross Abstract: Microservice root cause analysis (RCA) requires correlating failures across heterogeneous telemetry within complex service dependency graphs.