Related papers: Analyzing the Mechanism of Attention Collapse in V…

3D reconstruction from multi-view images is a core challenge in computer vision. Recently, feed-forward methods have emerged as efficient and robust alternatives to traditional per-scene optimization techniques. Among them, state-of-the-art…

Foundation models for 3D vision have recently demonstrated remarkable capabilities in 3D perception. However, scaling these models to long-sequence image inputs remains a significant challenge due to inference-time inefficiency. In this…

High-resolution imagery is essential for accurate 3D reconstruction, as many geometric details only emerge at fine spatial scales. Recent feed-forward approaches, such as the Visual Geometry Grounded Transformer (VGGT), have demonstrated…

Models such as VGGT and $\pi^3$ have shown strong multi-view 3D performance, but their heavy reliance on global self-attention results in high computational cost. Existing sparse-attention variants offer partial speedups, yet lack a…

Feed-forward reconstruction has been progressed rapidly, with the Visual Geometry Grounded Transformer (VGGT) being a notable baseline. However, directly applying VGGT to autonomous driving (AD) fails to capture three domain-specific…

Recent feed-forward 3D reconstruction methods, such as visual geometry transformers, have substantially advanced the traditional per-scene optimization paradigm by enabling effective multi-view reconstruction in a single forward pass.…

Feed-forward 3D foundation models face a key challenge: the quadratic computational cost introduced by global attention, which severely limits scalability as input length increases. Concurrent acceleration methods, such as token merging,…

3D instance segmentation methods typically rely on high-quality point clouds or posed RGB-D scans, requiring complex multi-stage processing pipelines, and are highly sensitive to reconstruction noise. While recent feed-forward transformers…

Visual localization has traditionally been formulated as a pair-wise pose regression problem. Existing approaches mainly estimate relative poses between two images and employ a late-fusion strategy to obtain absolute pose estimates.…

Visual Geometry Grounded Transformer (VGGT) advances 3D reconstruction via scalable Transformer architecture, but the quadratic complexity of global attention prevents long context application. StreamVGGT enables streaming with causal…

Recently, Vision Transformers (ViTs) have attracted a lot of attention in the field of computer vision. Generally, the powerful representative capacity of ViTs mainly benefits from the self-attention mechanism, which has a high computation…

The Visual Geometry Grounded Transformer (VGGT) marks a significant leap forward in 3D scene reconstruction, as it is the first model that directly infers all key 3D attributes (camera poses, depths, and dense geometry) jointly in one pass.…

Vision transformers (ViTs) have been successfully applied in image classification tasks recently. In this paper, we show that, unlike convolution neural networks (CNNs)that can be improved by stacking more convolutional layers, the…

Large Language Models (LLMs) often assign disproportionate attention to the first token, a phenomenon known as the attention sink. Several recent approaches aim to address this issue, including Sink Attention in GPT-OSS and Gated Attention…

Graph transformers achieve strong results on molecular and long-range reasoning tasks, yet remain hampered by over-smoothing (the progressive collapse of node representations with depth) and attention entropy degeneration. We observe that…

Large vision-and-language models (LVLMs) have traditionally integrated visual and textual tokens by concatenating them into a single homogeneous input for large language models (LLMs), thereby maximally preserving the pre-trained language…

Large models based on the Transformer architecture are susceptible to extreme-token phenomena, such as attention sinks and value-state drains. These issues, which degrade model performance, quantization fidelity, and interpretability, arise…

3D vision foundation models like Visual Geometry Grounded Transformer (VGGT) have advanced greatly in geometric perception. However, it is time-consuming and memory-intensive for long sequences, limiting application to large-scale scenes…

Predicting the effect of amino acid mutations on enzyme thermodynamic stability (DDG) is fundamental to protein engineering and drug design. While recent deep learning approaches have shown promise, they often process sequence and structure…

3D semantic occupancy prediction requires accurate 2D-to-3D feature lifting, yet current methods restrict camera geometry to initial projections. Subsequent operations like offset learning, attention weighting, and cross-camera aggregation…