12 citations · 28 across the 10 of their papers we have counts for
10 papers
Hy-MT2: A Family of Fast, Efficient and Powerful Multilingual Translation Models in the Wild
Mao Zheng, Zheng Li, Tao Chen +10
Hy-MT2 is a family of fast-thinking multilingual translation models designed for complex real-world scenarios. It includes three model sizes: 1.8B, 7B, and 30B-A3B (MoE), all of wh…
SparseForge: Efficient Semi-Structured LLM Sparsification via Annealing of Hessian-Guided Soft-Mask
Liu Hanzuo, Chaofan Lin, Weixuan Sun +4
Semi-structured sparsity provides a practical path to accelerate large language models (LLMs) with native hardware support, but post-training semi-structured pruning often suffers…
CDI3D: Cross-guided Dense-view Interpolation for 3D Reconstruction
Zhiyuan Wu, Xibin Song, Senbo Wang +8
3D object reconstruction from single-view image is a fundamental task in computer vision with wide-ranging applications. Recent advancements in Large Reconstruction Models (LRMs) h…
Pandora3D: A Comprehensive Framework for High-Quality 3D Shape and Texture Generation
Jiayu Yang, Taizhang Shang, Weixuan Sun +7
This report presents a comprehensive framework for generating high-quality 3D shapes and textures from diverse input prompts, including single images, multi-view images, and text d…
MARS: Mesh AutoRegressive Model for 3D Shape Detailization
Jingnan Gao, Weizhe Liu, Weixuan Sun +8
State-of-the-art methods for mesh detailization predominantly utilize Generative Adversarial Networks (GANs) to generate detailed meshes from coarse ones. These methods typically l…
LAM3D: Large Image-Point-Cloud Alignment Model for 3D Reconstruction from Single Image
Ruikai Cui, Xibin Song, Weixuan Sun +8
Large Reconstruction Models have made significant strides in the realm of automated 3D content generation from single or multiple input images. Despite their success, these models…
NeuSDFusion: A Spatial-Aware Generative Model for 3D Shape Completion, Reconstruction, and Generation
Ruikai Cui, Weizhe Liu, Weixuan Sun +9
3D shape generation aims to produce innovative 3D content adhering to specific conditions and constraints. Existing methods often decompose 3D shapes into a sequence of localized c…
Frankenstein: Generating Semantic-Compositional 3D Scenes in One Tri-Plane
Han Yan, Yang Li, Zhennan Wu +9
We present Frankenstein, a diffusion-based framework that can generate semantic-compositional 3D scenes in a single pass. Unlike existing methods that output a single, unified 3D s…
BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation
Zhennan Wu, Yang Li, Han Yan +8
We present BlockFusion, a diffusion-based model that generates 3D scenes as unit blocks and seamlessly incorporates new blocks to extend the scene. BlockFusion is trained using dat…
GETAM: Gradient-weighted Element-wise Transformer Attention Map for Weakly-supervised Semantic segmentation
Weixuan Sun, Jing Zhang, Zheyuan Liu +2
Weakly Supervised Semantic Segmentation (WSSS) is challenging, particularly when image-level labels are used to supervise pixel level prediction. To bridge their gap, a Class Activ…