Existing vision-language models often suffer from spatial hallucinations, i.e., generating incorrect descriptions about the relative positions of objects in an image. We argue that this problem mainly stems from the asymmetric properties between images and text. To enrich the spatial understanding ability of vision-language models, we propose a simple, annotation-free, plug-and-play method named Stitch and Tell (abbreviated as SiTe), which injects structured spatial supervision into multimodal data. It constructs stitched image-text pairs by stitching images along a spatial axis and generating spatially-aware captions or question answer pairs based on the layout of stitched image, without relying on costly advanced models or human involvement. We evaluate SiTe across three architectures including LLaVA-v1.5-7B,

AI-based weather forecasting now rivals traditional physics-based ensembles, but state-of-the-art (SOTA) models rely on specialized architectures and massive computational budgets, creating a high barrier to entry. We demonstrate that such complexity is unnecessary for frontier performance. We introduce U-Cast, a probabilistic forecaster built on a standard U-Net backbone trained with a simple recipe: deterministic pre-training on Mean Absolute Error followed by short probabilistic fine-tuning on the Continuous Ranked Probability Score (CRPS) using Monte Carlo Dropout for stochasticity. As a result, our model matches or exceeds the probabilistic skill of GenCast and IFS ENS at 1.5$^\circ\$ resolution while reducing training compute by over 10$\times$ compared to leading CRPS-based models and inference latency by over 10$\times$ compared to diffusion-based models. U-Cast trains in under 12 H200 GPU-days and generates a 60-step ensemble forecast in 11 seconds. These results suggest that scalable, general-purpose architectures paired with efficient training curricula can match complex domain-specific designs at a fraction of the cost, opening the training of frontier probabilistic weather models to the broader community. Our code is available at: https://github.com/Rose-STL-Lab/u-cast.

Fine-tuning services for Large Language Models (LLMs) have emerged as a new paradigm.

ABSTRACT Robust precoding is efficiently feasible in frequency divis ion duplex (FDD) systems by incorporating the learnt statistic s of the propagation environment through a generative model. W e build on previous work that successfully designed site-specific precoders based on a combination of Gaussian mixture models (GMMs) and graph neural networks (GNNs). In this paper, by utilizing a vector quantized-variational au toen-coder (VQ-V AE), we circumvent one of the key drawbacks of GMMs, i.e., the number of GMM components scales exponentially to the feedback bits. In addition, the deep lear n-ing architecture of the VQ-V AE allows us to jointly train the GNN together with VQ-V AE along with pilot optimization forming an end-to-end (E2E) model, resulting in considerable performance gains in sum rate for multi-user wireless systems. Simulations demonstrate the superiority of the pr o-posed frameworks over the conventional methods involving the sub-discrete Fourier transform (DFT) pilot matrix and i t-erative precoder algorithms enabling the deployment of sys - tems characterized by fewer pilots or feedback bits.

Fine-tuning services for Large Language Models (LLMs) have emerged as a new paradigm.

Inspired by our findings, we propose V accine, a perturbation-aware alignment technique to mitigate the security risk of users fine-tuning.

Multimodal pathological images are usually in clinical diagnosis, but computer vision-based multimodal image-assisted diagnosis faces challenges with modality fusion, especially in the absence of expert-annotated data. To achieve the modality fusion in multimodal images with label scarcity, we propose a novel ``pretraining + fine-tuning" framework for multimodal semi-supervised medical image classification. Specifically, we propose a synergistic learning pretraining framework of consistency, reconstructive, and aligned learning. By treating one modality as an augmented sample of another modality, we implement a self-supervised learning pre-train, enhancing the baseline model's feature representation capability. Then, we design a fine-tuning method for multimodal fusion. During the fine-tuning stage, we set different encoders to extract features from the original modalities and provide a multimodal fusion encoder for fusion modality. In addition, we propose a distribution shift method for multimodal fusion features, which alleviates the prediction uncertainty and overfitting risks caused by the lack of labeled samples. We conduct extensive experiments on the publicly available gastroscopy image datasets Kvasir and Kvasirv2. Quantitative and qualitative results demonstrate that the proposed method outperforms the current state-of-the-art classification methods. The code will be released at: https://github.com/LQH89757/MICS.