Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2609.16245v1 Announce Type: new Abstract: Long-horizon scientific discovery requires agents to alternate between exploration, disciplined execution, and critical reassessment as evidence change...
arXiv:2609.16247v1 Announce Type: new Abstract: Large language models sometimes behave in ways resembling human emotional responses, and recent work has identified internal representations that may e...
arXiv:2501.09166v2 Announce Type: replace-cross Abstract: Pretrained Transformers keep what they learned in their weights and lose what they observe once a session ends. The first version of this pap...
arXiv:2609.16779v1 Announce Type: new Abstract: LLMs are increasingly employed in a wide range of decision-making tasks. However, the opacity of their internal reasoning makes it difficult to validat...
arXiv:2609.17474v1 Announce Type: cross Abstract: Large language model (LLM) distillation aims to transfer the capabilities of a powerful teacher to a smaller student. Direct imitation, however, can...
arXiv:2609.16213v1 Announce Type: new Abstract: Artificial intelligence is reshaping biological research across an increasingly connected digital-to-physical workflow. General-purpose large language...
arXiv:2609.16519v1 Announce Type: new Abstract: Scientific research increasingly relies on large, heterogeneous data sources, motivating interest in retrieval-augmented generation (RAG) systems that...
arXiv:2609.17010v1 Announce Type: new Abstract: Lifelong conversational agents rely on memory systems to maintain deep, context-aware interactions with users. However, existing explicit textual memor...
arXiv:2603.16365v3 Announce Type: replace Abstract: We study alpha factor mining, the automated discovery of predictive signals from noisy, non-stationary market data-under a practical requirement th...
arXiv:2606.13621v2 Announce Type: replace Abstract: Formal safety analysis determines whether a system admits a safe defense; adaptive evaluation characterizes the operating quality sustained under a...
arXiv:2601.14230v3 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) are emerging as promising socio-collaborative companions for emotional and cognitive support. However, existing sys...
arXiv:2604.18616v2 Announce Type: replace-cross Abstract: LLM coding agents can generate correct GPU kernels, but their performance still trails expert libraries. Reaching peak throughput requires co...
arXiv:2607.05364v4 Announce Type: replace-cross Abstract: Modern autoregressive ASR systems can emit timestamps as decoded tokens, enabling timestamped transcription without frame-level aligners or i...
arXiv:2609.13083v2 Announce Type: replace-cross Abstract: In urban search and rescue, articulated tracked robots (ATRs) must traverse structured but contact-rich environments such as stairwells and c...
arXiv:2609.16267v1 Announce Type: new Abstract: Many operational cases are documented more than once, at different workflow stages and for different purposes, yet model evaluations normally select on...
arXiv:2609.16365v1 Announce Type: cross Abstract: Real-world datasets often exhibit long-tailed class distributions, where a few head classes contain a large number of training samples while a large...
arXiv:2609.16448v1 Announce Type: cross Abstract: Breast histopathology analysis increasingly relies on distributed learning because direct data pooling across institutions is often restricted by pri...
arXiv:2609.16742v1 Announce Type: cross Abstract: Convolutional Neural Networks (CNNs) are increasingly deployed in safety-critical edge applications, where soft errors can silently corrupt inference...
arXiv:2609.17204v1 Announce Type: cross Abstract: Wi-Fi signal data can be used to compromise the privacy of individuals. While many existing approaches rely on Channel State Information (CSI), colle...
arXiv:2609.17296v1 Announce Type: cross Abstract: Policy learning aims to determine who should be treated based on individual characteristics. In high-stakes settings such as medicine and public poli...