Shuo Xu

Xu Yang, Yingzhe Peng, Haoxuan Ma et al.

As Archimedes famously said, ``Give me a lever long enough and a fulcrum on which to place it, and I shall move the world'', in this study, we propose to use a tiny Language Model (LM), \eg, a Transformer with 67M parameters, to lever much larger Vision-Language Models (LVLMs) with 9B parameters. Specifically, we use this tiny \textbf{Lever-LM} to configure effective in-context demonstration (ICD) sequences to improve the In-Context Learinng (ICL) performance of LVLMs. Previous studies show that diverse ICD configurations like the selection and ordering of the demonstrations heavily affect the ICL performance, highlighting the significance of configuring effective ICD sequences. Motivated by this and by re-considering the the process of configuring ICD sequence, we find this is a mirror process of human sentence composition and further assume that effective ICD configurations may contain internal statistical patterns that can be captured by Lever-LM. Then a dataset with effective ICD sequences is constructed to train Lever-LM. After training, given novel queries, new ICD sequences are configured by the trained Lever-LM to solve vision-language tasks through ICL. Experiments show that these ICD sequences can improve the ICL performance of two LVLMs compared with some strong baselines in Visual Question Answering and Image Captioning, validating that Lever-LM can really capture the statistical patterns for levering LVLMs. The code is available at \url{https://github.com/ForJadeForest/Lever-LM}.

Shuo Xu, Yucheng Zhang, Gang Chen et al.

Although sparse-view computed tomography (CT) has significantly reduced radiation dose, it also introduces severe artifacts which degrade the image quality. In recent years, deep learning-based methods for inverse problems have made remarkable progress and have become increasingly popular in CT reconstruction. However, most of these methods suffer several limitations: dependence on high-quality training data, weak interpretability, etc. In this study, we propose a fully unsupervised framework called Deep Radon Prior (DRP), inspired by Deep Image Prior (DIP), to address the aforementioned limitations. DRP introduces a neural network as an implicit prior into the iterative method, thereby realizing cross-domain gradient feedback. During the reconstruction process, the neural network is progressively optimized in multiple stages to narrow the solution space in radon domain for the under-constrained imaging protocol, and the convergence of the proposed method has been discussed in this work. Compared with the popular pre-trained method, the proposed framework requires no dataset and exhibits superior interpretability and generalization ability. The experimental results demonstrate that the proposed method can generate detailed images while effectively suppressing image artifacts.Meanwhile, DRP achieves comparable or better performance than the supervised methods.

Luyao Lei, Shuo Xu, Yifan Bai et al.

The performance of multi-modal 3D occupancy prediction is limited by ineffective fusion, mainly due to geometry-semantics mismatch from fixed fusion strategies and surface detail loss caused by sparse, noisy annotations. The mismatch stems from the heterogeneous scale and distribution of point cloud and image features, leading to biased matching under fixed neighborhood fusion. To address this, we propose a target-scale adaptive, bidirectional symmetric retrieval mechanism. It expands the neighborhood for large targets to enhance context awareness and shrinks it for small ones to improve efficiency and suppress noise, enabling accurate cross-modal feature alignment. This mechanism explicitly establishes spatial correspondences and improves fusion accuracy. For surface detail loss, sparse labels provide limited supervision, resulting in poor predictions for small objects. We introduce an improved volume rendering pipeline based on 3D Gaussian Splatting, which takes fused features as input to render images, applies photometric consistency supervision, and jointly optimizes 2D-3D consistency. This enhances surface detail reconstruction while suppressing noise propagation. In summary, we propose TACOcc, an adaptive multi-modal fusion framework for 3D semantic occupancy prediction, enhanced by volume rendering supervision. Experiments on the nuScenes and SemanticKITTI benchmarks validate its effectiveness.