Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2609.08379v1 Announce Type: new Abstract: Accurate diagnostic and risk-prediction models are important for supporting clinical decision-making during infectious disease outbreaks. However, priv...
arXiv:2609.05484v1 Announce Type: cross Abstract: Deep learning registration methods routinely stack two kinds of enhancement on a base network: architectural additions such as affine pre-alignment s...
arXiv:2609.06036v1 Announce Type: new Abstract: Proposal-based controllers---learned policies, language-model planners, and other black-box \emph{generators}---are increasingly deployed behind runtim...
arXiv:2609.05744v1 Announce Type: cross Abstract: Reconstructing continuous terrain manifolds from massive, unstructured airborne LiDAR point clouds remains challenging in complex Wildland-Urban Inte...
arXiv:2605.30273v2 Announce Type: replace-cross Abstract: Large language models (LLMs) show promise in generating supportive responses for mental health queries, but improving their usefulness, empat...
arXiv:2609.10292v1 Announce Type: new Abstract: Data augmentation is fundamental to training modern deep vision and multimodal models. While individual methods, such as RandAug, CutMix, Mixup, RandEr...
arXiv:2609.07915v1 Announce Type: cross Abstract: Large vision models provide useful representations for remote-sensing segmentation but are often too expensive for deployment at the satellite or fie...
arXiv:2609.08602v1 Announce Type: new Abstract: Embodied planning increasingly relies on vision-language models (VLMs) to translate instructions and visual observations into executable action sequenc...
arXiv:2609.09004v1 Announce Type: cross Abstract: Large Language Models (LLMs) demonstrate impressive performance across diverse NLP tasks, yet their ability to exhibit genuine contextual understandi...
arXiv:2606.23609v2 Announce Type: replace-cross Abstract: Machine learning models exploit spurious correlations, achieving high average accuracy but failing disproportionately on underrepresented sub...
arXiv:2609.09556v1 Announce Type: new Abstract: Neural networks can leverage feature superposition to encode more concepts than dimensions, but cross-feature interference constrains the linear access...
arXiv:2609.06294v1 Announce Type: new Abstract: Estimating conditional average treatment effects (CATE) enables efficient targeting of interventions, but many applications have limited experimental s...
arXiv:2609.08216v1 Announce Type: new Abstract: Agentic AI systems built on large language models fail in two persistent ways that scaling does not fix: they break under distribution shift, and they...
arXiv:2609.05721v1 Announce Type: new Abstract: Understanding whether language-model embeddings encode structured real-world information is important for both representation analysis and information...
arXiv:2603.08275v2 Announce Type: replace-cross Abstract: With the global proliferation of Large Language Models (LLMs), cultural safety, defined as the ability to generate respectful and appropriate...
arXiv:2609.08322v1 Announce Type: cross Abstract: Multilingual LLMs show stereotype-related behavior that varies across languages, but behavioral scores do not show where the relevant information is...
arXiv:2609.05800v1 Announce Type: new Abstract: Activation steering controls LLM behavior at inference time by adding learned directions to hidden states, but existing methods handle one concept at a...
arXiv:2609.05782v1 Announce Type: new Abstract: Vision-language models (VLMs) offer a promising alternative to conventional fire detection systems by reasoning about the semantic context of a scene a...
arXiv:2609.08115v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) pretraining relies on an auxiliary load-balancing loss (LBL) to drive per-expert utilization toward uniformity. Post-training...
arXiv:2609.08247v1 Announce Type: new Abstract: Wallet reputation scores decide who receives an airdrop, who can borrow, and who enters an allowlist across decentralised finance. They almost always b...