15 citations · 100 across the 85 of their papers we have counts for
34 papers · 1 filter
Proxy3D: Efficient 3D Representations for Vision-Language Models via Semantic Clustering and Alignment
Jerry Jiang, Haowen Sun, Denis Gudovskiy +4
Spatial intelligence in vision-language models (VLMs) attracts research interest with the practical demand to reason in the 3D world.Despite promising results, most existing method…
SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing
Xuanyi Zhou, Qiuyang Mang, Shuo Yang +7
Diffusion Transformers (DiTs) have become a leading backbone for video generation, yet their quadratic attention cost remains a major bottleneck. Sparse attention reduces this cost…
K-Sort Eval: Efficient Preference Evaluation for Visual Generation via Corrected VLM-as-a-Judge
Zhikai Li, Jiatong Li, Xuewen Liu +7
The rapid development of visual generative models raises the need for more scalable and human-aligned evaluation methods. While the crowdsourced Arena platforms offer human prefere…
StreamDiffusionV2: A Streaming System for Dynamic and Interactive Video Generation
Tianrui Feng, Zhi Li, Shuo Yang +11
Generative models are reshaping the live-streaming industry by redefining how content is created, styled, and delivered. Previous image-based streaming diffusion models have powere…
Radial Attention: Sparse Attention with Energy Decay for Long Video Generation
Xingyang Li, Muyang Li, Tianle Cai +11
Recent advances in diffusion models have enabled high-quality video generation, but the additional temporal dimension significantly increases computational costs, making training a…
R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation
William Ljungbergh, Bernardo Taveira, Wenzhao Zheng +8
Validating autonomous driving (AD) systems requires diverse and safety-critical testing, making photorealistic virtual environments essential. Traditional simulation platforms, whi…
GeoDrive: 3D Geometry-Informed Driving World Model with Precise Action Control
Anthony Chen, Wenzhao Zheng, Yida Wang +5
Recent advancements in world models have revolutionized dynamic environment simulation, allowing systems to foresee future states and assess potential actions. In autonomous drivin…
Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
Shuo Yang, Haocheng Xi, Yilong Zhao +10
Diffusion Transformers (DiTs) are essential for video generation but suffer from significant latency due to the quadratic complexity of attention. By computing only critical tokens…
Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility
Yiheng Li, Feng Liang, Dan Kondratyuk +3
The substantial training cost of diffusion models hinders their deployment. Immiscible Diffusion recently showed that reducing diffusion trajectory mixing in the noise space via li…
Segment Any Motion in Videos
Nan Huang, Wenzhao Zheng, Chenfeng Xu +4
Moving object segmentation is a crucial task for achieving a high-level understanding of visual scenes and has numerous downstream applications. Humans can effortlessly segment mov…
STORM: Token-Efficient Long Video Understanding for Multimodal LLMs
Jindong Jiang, Xiuyu Li, Zhijian Liu +13
Recent advances in video-based multimodal large language models (Video-LLMs) have significantly improved video understanding by processing videos as sequences of image frames. Howe…
Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
Haocheng Xi, Shuo Yang, Yilong Zhao +11
Diffusion Transformers (DiTs) dominate video generation but their high computational cost severely limits real-world applicability, usually requiring tens of minutes to generate a…
DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving
Hao Lu, Tianshuo Xu, Wenzhao Zheng +6
Photorealistic 4D reconstruction of street scenes is essential for developing real-world simulators in autonomous driving. However, most existing methods perform this task offline…
Driv3R: Learning Dense 4D Reconstruction for Autonomous Driving
Xin Fei, Wenzhao Zheng, Yueqi Duan +4
Realtime 4D reconstruction for dynamic scenes remains a crucial challenge for autonomous driving perception. Most existing methods rely on depth estimation through self-supervision…
A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervision
Chensheng Peng, Ido Sobol, Masayoshi Tomizuka +3
We present a novel framework for training 3D image-conditioned diffusion models using only 2D supervision. Recovering 3D structure from 2D images is inherently ill-posed due to the…
DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes
Chensheng Peng, Chengwei Zhang, Yixiao Wang +6
We present DeSiRe-GS, a self-supervised gaussian splatting representation, enabling effective static-dynamic decomposition and high-fidelity surface reconstruction in complex drivi…
PixelGaussian: Generalizable 3D Gaussian Reconstruction from Arbitrary Views
Xin Fei, Wenzhao Zheng, Yueqi Duan +4
We propose PixelGaussian, an efficient feed-forward framework for learning generalizable 3D Gaussian reconstruction from arbitrary views. Most existing methods rely on uniform pixe…
Interpolating Video-LLMs: Toward Longer-sequence LMMs in a Training-free Manner
Yuzhang Shang, Bingxin Xu, Weitai Kang +7
Advancements in Large Language Models (LLMs) inspire various strategies for integrating video modalities. A key approach is Video-LLMs, which incorporate an optimizable interface l…
UniDrive: Towards Universal Driving Perception Across Camera Configurations
Ye Li, Wenzhao Zheng, Xiaonan Huang +1
Vision-centric autonomous driving has demonstrated excellent performance with economical sensors. As the fundamental step, 3D perception aims to infer 3D information from 2D images…
SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
Yuan Zhang, Chun-Kai Fan, Junpeng Ma +8
In vision-language models (VLMs), visual tokens usually bear a significant amount of computational overhead despite sparsity of information in them when compared to text tokens. To…
Sparse Refinement for Efficient High-Resolution Semantic Segmentation
Zhijian Liu, Zhuoyang Zhang, Samir Khaki +5
Semantic segmentation empowers numerous real-world applications, such as autonomous driving and augmented/mixed reality. These applications often operate on high-resolution images…
Fisher-aware Quantization for DETR Detectors with Critical-category Objectives
Huanrui Yang, Yafeng Huang, Zhen Dong +6
The impact of quantization on the overall performance of deep learning models is a well-studied problem. However, understanding and mitigating its effects on a more fine-grained le…
Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment
Yiheng Li, Heyang Jiang, Akio Kodaira +3
In this paper, we point out that suboptimal noise-data mapping leads to slow training of diffusion models. During diffusion training, current methods diffuse each image across the…
Gaussian: Self-Supervised Street Gaussians for Autonomous Driving
Nan Huang, Xiaobao Wei, Wenzhao Zheng +6
Photorealistic 3D reconstruction of street scenes is a critical technique for developing real-world simulators for autonomous driving. Despite the efficacy of Neural Radiance Field…