Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 13596v1 Announce Type: cross Abstract: When cast as the protector of a vulnerable user yet given no explicit capability boundary, a large language model (LLM) may respond not by acknowledging its limits but by claiming to have taken -- or to be taking -- a real-world protective action it cannot perform, such as contacting emergency services or administering care.
arXiv:2601. 12349v3 Announce Type: replace-cross Abstract: Large multimodal model powered GUI agents are emerging as high-privilege operators on mobile platforms, entrusted to perceive screen content and inject inputs across application boundaries.
arXiv:2607. 13103v1 Announce Type: cross Abstract: Knowledge tracing (KT) aims to predict students' future performance by modeling their evolving knowledge states from historical interactions.
arXiv:2607. 13801v1 Announce Type: cross Abstract: Large language model (LLM)-based intrusion detection systems (IDS) are increasingly studied for security monitoring, yet their robustness against feasible traffic manipulation remains largely empirical.
arXiv:2607. 13394v1 Announce Type: cross Abstract: Generative Flow Networks (GFlowNets) offer a promising alternative to reward-maximizing reinforcement learning (RL) for large reasoning models, encouraging diverse reasoning paths by matching reward distributions rather than collapsing to dominant modes.
arXiv:2607. 13420v1 Announce Type: new Abstract: Clicks on homepage marketing blocks are driven by a dual-mechanism of content interest and access habits.
arXiv:2511. 13592v2 Announce Type: replace-cross Abstract: The existing method of GS-PowerOpt solves the non-convex optimization problem of the form $\max_{\boldsymbol{x} \in \mathbb{R}^d} f(\boldsymbol{x})$ through maximizing a Gaussian-smoothed surrogate $F_{N,\sigma}(\boldsymbol{\mu}) = \mathbb{E}_{\boldsymbol{x}\sim\mathcal{N}(\boldsymbol{\mu},\sigma^2 I_d)}[e^{N f(\boldsymbol{x})}]$.
arXiv:2508. 12466v2 Announce Type: replace-cross Abstract: Traditional multimodal learning approaches rely on alignment pre-training to bridge vision and language modalities, typically by projecting visual features into discrete text token spaces using large-scale image--text data.
arXiv:2607. 13328v1 Announce Type: cross Abstract: Personalized recommendation systems are central to modern e-commerce and retail platforms, but they typically rely on centralized storage of detailed user interaction data, creating significant privacy and regulatory challenges.
arXiv:2607. 13899v1 Announce Type: new Abstract: We propose the AIMO Interpretability Challenge, a competition on distinguishing robust from spurious reasoning in frontier mathematical language models based on the models' internal mechanisms.
arXiv:2607. 13039v1 Announce Type: cross Abstract: Safety evaluations for dual-use biology assistants often measure base-model capability, refusal behavior, or jailbreak success.
arXiv:2607. 13565v1 Announce Type: cross Abstract: We investigate which language model evasion attacks survive state-of-the-art adversarial fine-tuning, developing strategies that sweep the top 5 positions on the ELOQUENT 2026 Voight-Kampff leaderboard.
arXiv:2607. 13411v1 Announce Type: cross Abstract: Clinical AI models can expose patients to harm when adversarial vulnerabilities go undetected, yet formal security auditing requires statistical expertise, specialized tools, and significant time.
arXiv:2607. 13056v1 Announce Type: cross Abstract: Current vision-language-action (VLA) benchmarks primarily evaluate isolated manipulation skills while leaving human-robot interaction structure largely unmodeled.
arXiv:2510. 10002v3 Announce Type: replace Abstract: As large language models (LLMs) are increasingly deployed in sensitive everyday contexts -- offering personal advice, mental health support, and moral guidance -- understanding their behavior in navigating complex moral reasoning is essential.
arXiv:2603. 00546v2 Announce Type: replace Abstract: Using Multimodal Large Language Models (MLLMs) as judges to achieve precise and consistent evaluations has gradually become an emerging paradigm across various domains.
arXiv:2607. 13073v1 Announce Type: new Abstract: Neuro-symbolic AI based on $IFOL_B$ is a way to combine neural learning and symbolic reasoning to overcome limitations of purely neural systems (like lack of interpretability and logical structure) with formal logical machinery for self-reference.
arXiv:2607. 13336v1 Announce Type: cross Abstract: Recent diffusion-based video generation models have enabled high-quality personalized video customization through both tuning-based pipelines, which fine-tune a video diffusion model, and reference-based pipelines such as image-to-video generation.
arXiv:2607. 13093v1 Announce Type: cross Abstract: On-device LLM inference faces a trilemma of response latency, limited hardware resources and user privacy.
arXiv:2607. 13172v1 Announce Type: new Abstract: We address the problem of safely training an agent policy and deploying a good and safe policy, in settings where the environment dynamics are unknown and no suitable reward function is available.