arXiv:2510.17088v2 Announce Type: replace-cross Abstract: Financial anomalies arise from heterogeneous mechanisms — price shocks, liquidity freezes, contagion cascades, and momentum reversals — yet existing detectors produce uniform scores without revealing which mechanism is failing. This hinders targeted responses: liquidity freezes call for market-making support, whereas price shocks call for circuit breakers. Three key challenges remain: […]
HatePrototypes: Interpretable and Transferable Representations for Implicit and Explicit Hate Speech Detection
arXiv:2511.06391v2 Announce Type: replace-cross Abstract: Optimization of offensive content moderation models for different types of hateful messages is typically achieved through continued pre-training or fine-tuning on new hate speech benchmarks. However, existing benchmarks mainly address explicit hate toward protected groups and often overlook implicit or indirect hate, such as demeaning comparisons, calls for exclusion or […]
ITO: Images and Texts as One via Synergizing Multiple Alignment and Training-Time Fusion
arXiv:2603.02767v3 Announce Type: replace-cross Abstract: Image-text contrastive pretraining has become a dominant paradigm for visual representation learning, yet existing methods often yield representations that remain partially organized by modality. We propose ITO, a framework addressing this limitation through two synergistic mechanisms. Multimodal multiple alignment enriches supervision by mining diverse image-text correspondences, while a lightweight training-time […]
Retrieval-Augmented Anatomical Guidance for Text-to-CT Generation
arXiv:2603.08305v1 Announce Type: cross Abstract: Text-conditioned generative models for volumetric medical imaging provide semantic control but lack explicit anatomical guidance, often resulting in outputs that are spatially ambiguous or anatomically inconsistent. In contrast, structure-driven methods ensure strong anatomical consistency but typically assume access to ground-truth annotations, which are unavailable when the target image is to […]
Don’t Look Back in Anger: MAGIC Net for Streaming Continual Learning with Temporal Dependence
arXiv:2603.08600v1 Announce Type: cross Abstract: Concept drift, temporal dependence, and catastrophic forgetting represent major challenges when learning from data streams. While Streaming Machine Learning and Continual Learning (CL) address these issues separately, recent efforts in Streaming Continual Learning (SCL) aim to unify them. In this work, we introduce MAGIC Net, a novel SCL approach that […]
ELHPlan: Efficient Long-Horizon Task Planning for Multi-Agent Collaboration
arXiv:2509.24230v2 Announce Type: replace Abstract: Large Language Models (LLMs) enable intelligent multi-robot collaboration but face fundamental trade-offs: open-loop methods that compile tasks into formal representations for external executors produce sound plans but lack adaptability in partially observable environments, while iterative methods incur prohibitive computational costs that scale poorly with team size and task complexity. In […]
A Geometric Taxonomy of Hallucinations in LLMs
arXiv:2602.13224v2 Announce Type: replace Abstract: The term “hallucination” converge different failure modes with specific geometric signatures in embedding space. We propose a taxonomy identifying three types: unfaithfulness (Type I: ignoring provided context), confabulation (Type II: inventing semantically foreign content), and factual error (Type III: wrong details within correct conceptual frames). We introduce two detection methods […]
Exploring Diffusion Models’ Corruption Stage in Few-Shot Fine-tuning and Mitigating with Bayesian Neural Networks
arXiv:2405.19931v2 Announce Type: replace-cross Abstract: Few-shot fine-tuning of Diffusion Models (DMs) is a key advancement, significantly reducing training costs and enabling personalized AI applications. However, we explore the training dynamics of DMs and observe an unanticipated phenomenon: during the training process, image fidelity initially improves, then unexpectedly deteriorates with the emergence of noisy patterns, only […]
MediTools — Medical Education Powered by LLMs
arXiv:2503.22769v2 Announce Type: replace-cross Abstract: Artificial Intelligence (AI) has been advancing rapidly and with the advent of large language models (LLMs) in late 2022, numerous opportunities have emerged for adopting this technology across various domains, including medicine. These innovations hold immense potential to revolutionize and modernize medical education. Our research project leverages large language models […]
M4Diffuser: Multi-View Diffusion Policy with Manipulability-Aware Control for Robust Mobile Manipulation
arXiv:2509.14980v2 Announce Type: replace-cross Abstract: Mobile manipulation requires the coordinated control of a mobile base and a robotic arm while simultaneously perceiving both global scene context and fine-grained object details. Existing single-view approaches often fail in unstructured environments due to limited fields of view, exploration, and generalization abilities. Moreover, classical controllers, although stable, struggle with […]
UnfoldLDM: Deep Unfolding-based Blind Image Restoration with Latent Diffusion Priors
arXiv:2511.18152v2 Announce Type: replace-cross Abstract: Deep unfolding networks (DUNs) combine the interpretability of model-based methods with the learning ability of deep networks, yet remain limited for blind image restoration (BIR). Existing DUNs suffer from: (1) textbfDegradation-specific dependency, as their optimization frameworks are tied to a known degradation model, making them unsuitable for BIR tasks; and […]
Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs
arXiv:2510.13795v4 Announce Type: replace-cross Abstract: Fully open multimodal large language models (MLLMs) currently lag behind proprietary counterparts, primarily due to a significant gap in data quality for supervised fine-tuning (SFT). Existing open-source datasets are often plagued by widespread noise and a critical deficit in complex reasoning data, such as Chain-of-Thought (CoT), which hinders the development […]