Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 31639v1 Announce Type: cross Abstract: Large language models are no longer only text generators.
arXiv:2605. 16399v2 Announce Type: replace-cross Abstract: The inversion of diffusion models plays a central role in image editing.
arXiv:2502. 00684v2 Announce Type: replace-cross Abstract: Deep reinforcement learning (DRL) has successfully addressed many complex control problems.
arXiv:2606. 23032v3 Announce Type: replace Abstract: Finance Agent v2 (by Vals AI) has emerged as the reference benchmark for evaluating both Anthropic Claude and OpenAI ChatGPT frontier language models on financial tasks.
arXiv:2606. 31110v1 Announce Type: new Abstract: Artificial neural networks (NNs) and machine learning (ML) algorithms are poorly understood from a theoretical perspective, which makes it difficult to fully realize their potential and overcome their weaknesses.
arXiv:2606. 31320v1 Announce Type: new Abstract: Safe online reinforcement learning requires policies to respect safety constraints while maintaining smooth optimization dynamics.
arXiv:2602. 02124v2 Announce Type: replace-cross Abstract: Drug-induced toxicity is a leading cause of preclinical and early-clinical failure, making early detection critical.
arXiv:2603. 12893v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become a standard technique for post-training diffusion-based image synthesis models, as it enables learning from reward signals to explicitly improve desirable aspects such as image quality and prompt alignment.
arXiv:2402. 06734v2 Announce Type: replace-cross Abstract: We study data corruption robustness for reinforcement learning with human feedback (RLHF) in an offline setting.
arXiv:2603. 29759v2 Announce Type: replace-cross Abstract: Recent advances in vision-language models (VLMs) have accelerated their application to indoor safety hazards assessment.
arXiv:2606. 31480v1 Announce Type: new Abstract: We study constrained online convex optimization with adversarial losses and stochastic or adversarial constraints.
arXiv:2512. 04008v2 Announce Type: replace Abstract: Training with differential privacy (DP) guarantees dataset members that they cannot be identified by users of the released model.
arXiv:2606. 31023v1 Announce Type: cross Abstract: Hard-constrained sequential decision systems have no certified way to spend the test-time compute of modern AI: executing the multi-step drafts of a learned policy or a frozen LLM forfeits the feasibility guarantee a trusted solver provides, while invoking the solver at every step forfeits the speed the AI offers.
arXiv:2606. 30877v1 Announce Type: cross Abstract: Recent literature shows that large language models (LLMs) are useful for general-purpose tasks yet perform poorly on specific domain ones.
arXiv:2603. 19127v2 Announce Type: replace Abstract: As Spoken Language Models (SLMs) integrate speech and text modalities, they inherit the safety vulnerabilities of their LLM backbone while introducing an expanded attack surface.
arXiv:2606. 31609v1 Announce Type: cross Abstract: Radar sensors provide reliable perception under adverse weather and lighting conditions, but their sparse, noisy, and weakly semantic measurements make dense semantic segmentation challenging.
arXiv:2606. 31054v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) are critically hampered by hallucination, generating content inconsistent with the provided image.
arXiv:2606. 31700v1 Announce Type: new Abstract: Biological neural circuits obey Dale's principle: each neuron's synapses are uniformly excitatory or inhibitory.
arXiv:2605. 09235v2 Announce Type: replace-cross Abstract: One-step generative modeling has emerged as a leading approach for amortizing the inference cost of diffusion and flow-matching models.
Theory of Mind (ToM) benchmarks for Large Language Models (LLMs) typically rely on passive question-answering formats, but the deployment of LLMs in increasingly agentic and autonomous forms demands new evaluations. In this paper we evaluate an agent's ability to induce specific belief states in other agents by taking actions rather than using conversational persuasion, a capability we call Non-Conversational Planning ToM (NCP-ToM).