Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2609.09895v1 Announce Type: new Abstract: Video-language models and video agents can produce hallucinations that conflict with spatiotemporal evidence. Existing benchmarks mainly evaluate model...
arXiv:2507.21816v1 Announce Type: cross Abstract: Few-shot object detection (FSOD) for optical remote sensing images aims to detect rare objects with only a few annotated bounding boxes. The limited...
arXiv:2506.10633v2 Announce Type: replace Abstract: Latent Diffusion Models have shown remarkable results in text-guided image synthesis in recent years. In the domain of natural (RGB) images, recent...
arXiv:2512.10237v2 Announce Type: replace Abstract: Reinforcement Learning from Human Feedback has emerged as a standard for aligning diffusion models. However, we identify a fundamental limitation i...
arXiv:2609.05889v1 Announce Type: new Abstract: Resource-exhaustion attacks against autoregressive vision-language models (VLMs) typically assume unimodal threat models, treating the image branch as...
arXiv:2609.07974v1 Announce Type: cross Abstract: Fairness in clustering has attracted sustained research interest, motivated by the need to ensure equitable representation of protected groups in mac...
arXiv:2609.05730v1 Announce Type: cross Abstract: Contrastive Language-Image Pretraining (CLIP) is a building block of many machine learning applications. Scaling laws have guided resource allocation...
arXiv:2609.05850v1 Announce Type: cross Abstract: Despite the significant efforts devoted to aligning large language models (LLMs) with human values and ensuring safe deployment, recent work has reve...
arXiv:2609.09801v1 Announce Type: cross Abstract: Malocclusion skeletal grading is a fundamental task in orthodontics, critical for diagnosis and treatment planning. Traditionally, cone-beam computed...
arXiv:2608.12134v2 Announce Type: replace-cross Abstract: We study nonnegative submodular maximization on $n$ elements subject to a general matroid of rank $k$, when the offline algorithm is given an...
arXiv:2609.05910v1 Announce Type: cross Abstract: Reinforcement learning (RL) excels on tasks with verifiable rewards, but in open-ended tasks, the reliability of reward models remains a key challeng...
arXiv:2609.07213v1 Announce Type: new Abstract: We observe a phenomenon that current algorithmic research in the field of explainable artificial intelligence primarily pursues better performance on s...
arXiv:2609.08016v1 Announce Type: new Abstract: Multi-agent debate, in which several LLMs exchange arguments before answering, is widely assumed to improve answer quality by surfacing genuine disagre...
arXiv:2609.05966v1 Announce Type: new Abstract: Existing unlearning approaches typically rely on post hoc weight adaptation or distillation, leading to duplicated memory costs, degraded generalizatio...
arXiv:2609.06106v1 Announce Type: new Abstract: Heterogeneous Federated Learning (HFL) aims to train models across devices with diverse resource budgets while preserving data privacy. Existing HFL me...
arXiv:2609.06195v1 Announce Type: new Abstract: This paper proposes a transferable Map of Dynamics (MoD) framework that generalizes to unknown environments using only egocentric 3D LiDAR point clouds...
arXiv:2609.08186v1 Announce Type: new Abstract: The emergence of Chain-of-Thought (CoT) has established a robust foundation for Large Reasoning Models (LRMs). While deep reasoning is widely believed...
arXiv:2609.00335v2 Announce Type: replace Abstract: Following arXiv:2607.25507, this report examines whether phase-derived features improve endpoint prediction over a combined baseline in two setting...
arXiv:2609.08200v1 Announce Type: new Abstract: Token-level text anomaly detection, as an emerging trend of text anomaly detection, moves beyond coarse-grained document-level detection by localizing...
arXiv:2609.06540v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in safety-critical applications, yet jailbreak attacks can conceal harmful intent through role...