16 citations · 22 across the 15 of their papers we have counts for
18 papers
Can Large Language Models Execute Parent Orders?
Zane Shen, Xinli Xu, Guangyi Zhang +7
Parent-order execution is a core problem in algorithmic trading, where the goal is to split a large order into smaller orders while reducing execution costs. Existing approaches ei…
WorldLines: Benchmarking and Modeling Long-Horizon Stateful Embodied Agents
Yehang Zhang, Jianchong Su, Haojian Huang +7
To assist humans over extended periods in real homes, embodied agents must remember user routines, world states, and past interactions. Existing long-term memory benchmarks mainly…
A Mechanistic View on Video Generation as World Models: State and Dynamics
Luozhou Wang, Zhifei Chen, Yihua Du +11
Large-scale video generation models have demonstrated emergent physical coherence, positioning them as potential world models. However, a gap remains between contemporary "stateles…
VideoMemory: Toward Consistent Video Generation via Memory Integration
Jinsong Zhou, Yihua Du, Xinli Xu +7
Maintaining consistent characters, props, and environments across multiple shots is a central challenge in narrative video generation. Existing models can produce high-quality shor…
PresentCoach: Dual-Agent Presentation Coaching through Exemplars and Interactive Feedback
Sirui Chen, Jinsong Zhou, Xinli Xu +3
Effective presentation skills are essential in education, professional communication, and public speaking, yet learners often lack access to high-quality exemplars or personalized…
ComfyMind: Toward General-Purpose Generation via Tree-Based Planning and Reactive Feedback
Litao Guo, Xinli Xu, Luozhou Wang +5
With the rapid advancement of generative models, general-purpose generation has gained increasing attention as a promising approach to unify diverse tasks across modalities within…
PreGenie: An Agentic Framework for High-quality Visual Presentation Generation
Xiaojie Xu, Xinli Xu, Sirui Chen +3
Visual presentations are vital for effective communication. Early attempts to automate their creation using deep learning often faced issues such as poorly organized layouts, inacc…
Kiss3DGen: Repurposing Image Diffusion Models for 3D Asset Generation
Jiantao Lin, Xin Yang, Meixi Chen +7
Diffusion models have achieved great success in generating 2D images. However, the quality and generalizability of 3D content generation remain limited. State-of-the-art methods of…
GaussianProperty: Integrating Physical Properties to 3D Gaussians with LMMs
Xinli Xu, Wenhang Ge, Dicong Qiu +8
Estimating physical properties for visual data is a crucial task in computer vision, graphics, and robotics, underpinning applications such as augmented reality, physical simulatio…
PRM: Photometric Stereo based Large Reconstruction Model
Wenhang Ge, Jiantao Lin, Guibao Shen +4
We propose PRM, a novel photometric stereo based large reconstruction model to reconstruct high-quality meshes with fine-grained local details. Unlike previous large reconstruction…
FlexGen: Flexible Multi-View Generation from Text and Image Inputs
Xinli Xu, Wenhang Ge, Jiantao Lin +5
In this work, we introduce FlexGen, a flexible framework designed to generate controllable and consistent multi-view images, conditioned on a single-view image, or a text prompt, o…
LucidFusion: Reconstructing 3D Gaussians with Arbitrary Unposed Images
Hao He, Yixun Liang, Luozhou Wang +5
Recent large reconstruction models have made notable progress in generating high-quality 3D objects from single images. However, current reconstruction methods often rely on explic…
DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving
Chen Min, Dawei Zhao, Liang Xiao +10
Vision-centric autonomous driving has recently raised wide attention due to its lower cost. Pre-training is essential for extracting a universal representation. However, current vi…
Scaling Multi-Camera 3D Object Detection through Weak-to-Strong Eliciting
Hao Lu, Jiaqi Tang, Xinli Xu +6
The emergence of Multi-Camera 3D Object Detection (MC3D-Det), facilitated by bird's-eye view (BEV) representation, signifies a notable progression in 3D object detection. Scaling M…
Sample-adaptive Augmentation for Point Cloud Recognition Against Real-world Corruptions
Jie Wang, Lihe Ding, Tingfa Xu +4
Robust 3D perception under corruption has become an essential task for the realm of 3D vision. While current data augmentation techniques usually perform random transformations on…
TiG-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning
Peixiang Huang, Li Liu, Renrui Zhang +4
To achieve accurate and low-cost 3D object detection, existing methods propose to benefit camera-based multi-view detectors with spatial cues provided by the LiDAR modality, e.g.,…
FusionRCNN: LiDAR-Camera Fusion for Two-stage 3D Object Detection
Xinli Xu, Shaocong Dong, Lihe Ding +3
3D object detection with multi-sensors is essential for an accurate and reliable perception system of autonomous driving and robotics. Existing 3D detectors significantly improve t…
Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoders
Chen Min, Xinli Xu, Dawei Zhao +3
Current perception models in autonomous driving heavily rely on large-scale labelled 3D data, which is both costly and time-consuming to annotate. This work proposes a solution to…