Xiangyu Yue

CoRR, 2024

Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?

[BibT_eX]

[DOI]

CoRR, 2024

DiffFluid: Plain Diffusion Models are Effective Predictors of Flow Dynamics.

[BibT_eX]

[DOI]

CoRR, 2024

Training Matting Models without Alpha Labels.

[BibT_eX]

[DOI]

CoRR, 2024

Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT.

[BibT_eX]

[DOI]

CoRR, 2024

Explore the Limits of Omni-modal Pretraining at Scale.

[BibT_eX]

[DOI]

CoRR, 2024

EMR-Merging: Tuning-Free High-Performance Model Merging.

[BibT_eX]

[DOI]

CoRR, 2024

Safety Alignment for Vision Language Models.

[BibT_eX]

[DOI]

CoRR, 2024

Continual Offline Reinforcement Learning via Diffusion-based Dual Generative Replay.

[BibT_eX]

[DOI]

CoRR, 2024

ChemLLM: A Chemical Large Language Model.

[BibT_eX]

[DOI]

CoRR, 2024

InteractiveVideo: User-Centric Controllable Video Generation with Synergistic Multimodal Instructions.

[BibT_eX]

[DOI]

CoRR, 2024

Seeing through Wave - Real-time Beam Tracking via a ResNet-based Model in Water-air OWC Systems.

[BibT_eX]

[DOI]

Proceedings of the Optical Fiber Communications Conference and Exhibition, 2024

Online Vectorized HD Map Construction Using Geometry.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2024, 2024

Reg-TTA3D: Better Regression Makes Better Test-Time Adaptive 3D Object Detection.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2024, 2024

SSNVC: Single Stream Neural Video Compression with Implicit Temporal Information.

[BibT_eX]

[DOI]

Proceedings of the Data Compression Conference, 2024

Multimodal Pathway: Improve Transformers with Irrelevant Data from Other Modalities.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

OneLLM: One Framework to Align All Modalities with Language.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics, 2024

2023

Scenic: a language for scenario specification and data generation.

[BibT_eX]

[DOI]

Mach. Learn., October, 2023

Towards Unified and Effective Domain Generalization.

[BibT_eX]

[DOI]

CoRR, 2023

Beyond One-Preference-for-All: Multi-Objective Direct Preference Optimization for Language Models.

[BibT_eX]

[DOI]

CoRR, 2023

ImageBind-LLM: Multi-modality Instruction Tuning.

[BibT_eX]

[DOI]

CoRR, 2023

Revisiting DETR Pre-training for Object Detection.

[BibT_eX]

[DOI]

CoRR, 2023

Backdoor Defense with Non-Adversarial Backdoor.

[BibT_eX]

[DOI]

Min Liu

CoRR, 2023

Meta-Transformer: A Unified Framework for Multimodal Learning.

[BibT_eX]

[DOI]

CoRR, 2023

LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model.

[BibT_eX]

[DOI]

CoRR, 2023

Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Space Engage: Collaborative Space Supervision for Contrastive-based Semi-Supervised Semantic Segmentation.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Beating Backdoor Attack at Its Own Game.

[BibT_eX]

[DOI]

Min Liu

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

3D Environment Modeling for Falsification and Beyond with Scenic 3.0.

[BibT_eX]

[DOI]

Proceedings of the Computer Aided Verification - 35th International Conference, 2023

2022

Dissecting lightning strike hazard impact patterns to National Airspace System facilities in the contiguous United States.

[BibT_eX]

[DOI]

Comput. Environ. Urban Syst., 2022

A Review of Single-Source Deep Unsupervised Visual Domain Adaptation.

[BibT_eX]

[DOI]

IEEE Trans. Neural Networks Learn. Syst., 2022

Emotional Semantics-Preserved and Feature-Aligned CycleGAN for Visual Emotion Adaptation.

[BibT_eX]

[DOI]

IEEE Trans. Cybern., 2022

Prompt Vision Transformer for Domain Generalization.

[BibT_eX]

[DOI]

CoRR, 2022

MLSeg: Image and Video Segmentation as Multi-Label Classification and Selected-Label Pixel Classification.

[BibT_eX]

[DOI]

CoRR, 2022

Self-Supervised Pretraining Improves Self-Supervised Pretraining.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2022

Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2022, 2022

RankSeg: Adaptive Pixel Classification with Image Category Ranking for Segmentation.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2022, 2022

Conditional Synthetic Data Generation for Robust Machine Learning Applications with Limited Pandemic Data.

[BibT_eX]

[DOI]

Costas J. Spanos

Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021

MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation.

[BibT_eX]

[DOI]

Int. J. Comput. Vis., 2021

2nd Place Solution for VisDA 2021 Challenge - Universally Domain Adaptive Image Recognition.

[BibT_eX]

[DOI]

CoRR, 2021

Multi-source Few-shot Domain Adaptation.

[BibT_eX]

[DOI]

CoRR, 2021

Image2Point: 3D Point-Cloud Understanding with Pretrained 2D ConvNets.

[BibT_eX]

[DOI]

CoRR, 2021

Curriculum CycleGAN for Textual Sentiment Domain Adaptation with Multiple Sources.

[BibT_eX]

[DOI]

Proceedings of the WWW '21: The Web Conference 2021, 2021

Scene-aware Learning Network for Radar Object Detection.

[BibT_eX]

[DOI]

Zangwei Zheng

Proceedings of the ICMR '21: International Conference on Multimedia Retrieval, 2021

Unsupervised Point Cloud Pre-training via Occlusion Completion.

[BibT_eX]

[DOI]

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Prototypical Cross-Domain Self-Supervised Learning for Few-Shot Unsupervised Domain Adaptation.

[BibT_eX]

[DOI]

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

2020

A Customizable Dynamic Scenario Modeling and Data Generation Platform for Autonomous Driving.

[BibT_eX]

[DOI]

Sanjit Seshia

CoRR, 2020

Pre-Training by Completing Point Clouds.

[BibT_eX]

[DOI]

CoRR, 2020

Generalizing Fault Detection Against Domain Shifts Using Stratification-Aware Cross-Validation.

[BibT_eX]

[DOI]

CoRR, 2020

Using Ensemble Classifiers to Detect Incipient Anomalies.

[BibT_eX]

[DOI]

CoRR, 2020

Exploiting Uncertainties from Ensemble Learners to Improve Decision-Making in Healthcare AI.

[BibT_eX]

[DOI]

CoRR, 2020

PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation.

[BibT_eX]

[DOI]

CoRR, 2020

MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation.

[BibT_eX]

[DOI]

CoRR, 2020

PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation.

[BibT_eX]

[DOI]

Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

2019

Scenic: a language for scenario specification and scene generation.

[BibT_eX]

[DOI]

Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation, 2019

Multi-source Domain Adaptation for Semantic Segmentation.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Robotics and Automation, 2019

Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization Without Accessing Target Domain Data.

[BibT_eX]

[DOI]

Yang Zhang

Sicheng Zhao

Boqing Gong

Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

2018

Scenic: Language-Based Scene Generation.

[BibT_eX]

[DOI]

CoRR, 2018

A LiDAR Point Cloud Generator: from a Virtual World to Autonomous Driving.

[BibT_eX]

[DOI]

Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval, 2018

A Novel Domain Adaptation Framework for Medical Image Segmentation.

[BibT_eX]

[DOI]

Proceedings of the Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, 2018

Counterexample-Guided Data Augmentation.

[BibT_eX]

[DOI]

Marcell Vazquez-Chanlatte

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, 2018

SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE International Conference on Robotics and Automation, 2018

Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

SqueezeNext: Hardware-Aware Neural Network Design.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2018

Formal Specification for Deep Neural Networks.

[BibT_eX]

[DOI]