arXiv:2502.13061v4 Announce Type: replace-cross Abstract: Hateful memes have become a significant concern on the Internet, necessitating robust automated detection systems. While Large Multimodal Models (LMMs) have shown promise in hateful meme detection, they face notable challenges like sub-optimal performance and…
arXiv:2509.12249v1 Announce Type: new Abstract: Joint-Embedding Predictive Architecture (JEPA) is increasingly used for visual representation learning and as a component in model-based RL, but its behavior remains poorly understood. We provide a theoretical characterization of a simple, practical JEPA variant…
arXiv:2509.04245v2 Announce Type: replace Abstract: Background: Heart failure (HF) research is constrained by limited access to large, shareable datasets due to privacy regulations and institutional barriers. Synthetic data generation offers a promising solution to overcome these challenges while preserving patient…
arXiv:2509.12239v1 Announce Type: new Abstract: This work introduces InJecteD, a framework for interpreting Denoising Diffusion Probabilistic Models (DDPMs) by analyzing sample trajectories during the denoising process of 2D point cloud generation. We apply this framework to three datasets from the…
arXiv:2411.01109v2 Announce Type: replace Abstract: Recent trends in lower precision, e.g. half-precision floating point, training have shown improved system performance and reduced memory usage for Deep Learning while maintaining accuracy. However, current GNN systems cannot achieve such goals for GNN,…
arXiv:2509.12238v1 Announce Type: new Abstract: Purpose: Thyroid cancer has been a common cancer. Papillary thyroid cancer and follicular thyroid cancer are the two most common types of thyroid cancer. Follicular thyroid cancer lacks distinctive ultrasound signs and is more difficult…
arXiv:2509.13229v1 Announce Type: cross Abstract: Hyperspectral imaging (HSI) captures detailed spectral signatures across hundreds of contiguous bands per pixel, being indispensable for remote sensing applications such as land-cover classification, change detection, and environmental monitoring. Due to the high dimensionality of…
arXiv:2509.12237v1 Announce Type: new Abstract: Accurate prediction of machining deformation in structural components is essential for ensuring dimensional precision and reliability. Such deformation often originates from residual stress fields, whose distribution and influence vary significantly with geometric complexity. Conventional numerical…
arXiv:2509.12768v1 Announce Type: cross Abstract: Vision Transformers (ViTs) have shown significant promise in computer vision applications. However, their performance in few-shot learning is limited by challenges in refining token-level interactions, struggling with limited training data, and developing a strong inductive…
arXiv:2509.12235v1 Announce Type: new Abstract: The two-stage fine-tuning paradigm of Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has empirically shown better reasoning performance than one-stage SFT for the post-training of Large Language Models (LLMs). However, the evolution and mechanism…
