Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2604. 09967v2 Announce Type: replace-cross Abstract: Muon has emerged as a promising optimizer for large-scale foundation model pre-training by exploiting the matrix structure of neural network updates through iterative orthogonalization.
arXiv:2606. 08021v1 Announce Type: cross Abstract: As large language model (LLM) agents are integrated into autonomous cloud operations, distributed systems face a semantic reliability problem: proposer agents can generate production mutations, such as modifying IAM policies, opening firewall security groups, or executing data exports, that are syntactically valid and statically authorized but operationally unsafe.
arXiv:2606. 08016v1 Announce Type: cross Abstract: Current image editing software often hinges on fixed filters or expert tuning, leaving a gap between amateur users' intent and outcomes.
arXiv:2606. 07520v1 Announce Type: cross Abstract: Instruction Following (IF) is a core capability of LLMs, requiring strict adherence to diverse constraints, ranging from verifiable ones (e.
arXiv:2606. 09048v1 Announce Type: cross Abstract: Removing intermediate representations and separately trained decoding stages has become an important direction in generative modeling.
arXiv:2606. 08948v1 Announce Type: cross Abstract: Comprehensive estimation of dietary micronutrients from food images could improve clinical nutrition care, but training such models requires large multimodal datasets linking diverse foods to complete nutrient profiles.
arXiv:2606. 08044v1 Announce Type: cross Abstract: Large Language Model (LLM) safety has often been evaluated at the behavior level, which provides limited evidence of internal robustness, as these evaluations target outputs rather than representation-level vulnerability under intervention.
arXiv:2606. 09027v1 Announce Type: cross Abstract: Large Language Models enable flexible natural-language planning but remain unreliable in determinism-critical domains due to their probabilistic nature.
arXiv:2606. 08969v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for medical summarization, but their outputs can omit medically important information and introduce unsupported claims.
arXiv:2606. 07549v1 Announce Type: new Abstract: Recent advances in Multimodal Large Language Models (MLLMs) and agent workflows have shown strong promise for computational pathology, yet reliable patch-level reasoning remains challenging.
arXiv:2606. 08960v1 Announce Type: cross Abstract: Agent benchmarks score submissions with outcome verifiers that are typically hand-written and brittle, leaving them open to reward hacking.
arXiv:2512. 07355v2 Announce Type: replace Abstract: Two traditions of interpretability have evolved side by side but seldom spoken to each other: Concept Bottleneck Models (CBMs), which prescribe what a concept should be, and Sparse Autoencoders (SAEs), which discover what concepts emerge.
arXiv:2604. 18050v2 Announce Type: replace Abstract: AlphaGeometry represents a milestone in neuro-symbolic reasoning, yet its architecture faces a log-linear scaling bottleneck within its symbolic deduction engine that limits its efficiency as problem complexity increases.
arXiv:2605. 08876v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly deployed as autonomous agents that execute tool-augmented, multi-step tasks, where latency is a critical factor for real-world applications.
arXiv:2606. 09315v1 Announce Type: cross Abstract: BCI-to-agent pipelines turn decoded neural activity into an authorization channel for tool-use agents, exposing a new attack surface we call \emph{brain-prompt injection}: signal-side perturbations, context-only injections, and adaptive dual-decoder attacks can all change the routed action while EEG-side or text-side monitors remain blind.
arXiv:2606. 09701v1 Announce Type: cross Abstract: AI red teaming must continually adapt to evolving attackers and defenders.
arXiv:2606. 08296v1 Announce Type: new Abstract: A key premise in leading arguments for existential risk from artificial intelligence is that malfunctioning artificial agents could not be easily shut down.
arXiv:2606. 08067v1 Announce Type: new Abstract: Graph neural networks (GNNs) are widely deployed on relational data, yet they can leak sensitive or proprietary information about the training graph adjacency, e.
arXiv:2606. 08305v1 Announce Type: cross Abstract: Externally controlled survival trials are increasingly used when concurrent randomized controls are infeasible, particularly in oncology and rare-disease settings with time-to-event endpoints.
arXiv:2606. 08081v1 Announce Type: cross Abstract: Repeated reference games test whether interlocutors replace their initially long descriptions with shorter, partner-specific conventions grounded in shared interaction history.