Jingren Zhou

papers

1,127

total citations

papers (21)

EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism

ICML 2024arXiv

citations

Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent

ICLR 2025arXiv

citations

Devil Is in the Queries: Advancing Mask Transformers for Real-World Medical Image Segmentation and Out-of-Distribution Localization

CVPR 2023arXiv

citations

Res-Tuning: A Flexible and Efficient Tuning Paradigm via Unbinding Tuner from Backbone

NEURIPS 2023arXiv

citations

Lipschitz Singularities in Diffusion Models

ICLR 2024arXiv

citations

CancerUniT: Towards a Single Unified Model for Effective Detection, Segmentation, and Diagnosis of Eight Major Cancers Using a Large Collection of CT Scans

ICCV 2023arXiv

citations

Dimensionality-Varying Diffusion Process

CVPR 2023arXiv

citations

Data-Juicer Sandbox: A Feedback-Driven Suite for Multimodal Data-Model Co-development

ICML 2025arXiv

citations

Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inference

ICLR 2025arXiv

citations

ViM: Vision Middleware for Unified Downstream Transferring

ICCV 2023arXiv

citations

Neural Dependencies Emerging From Learning Massive Categories

CVPR 2023arXiv

citations

UFC-BERT: Unifying Multi-Modal Controls for Conditional Image Synthesis

NEURIPS 2021

citations

FaceComposer: A Unified Model for Versatile Facial Content Creation

NEURIPS 2023

citations

Learning to Mutate with Hypergradient Guided Population

NEURIPS 2020

citations

LipFormer: High-Fidelity and Generalizable Talking Face Generation With a Pre-Learned Facial Codebook

CVPR 2023

citations

RA-CLIP: Retrieval Augmented Contrastive Language-Image Pre-Training

CVPR 2023

citations

Jingren Zhou

papers (21)

VideoComposer: Compositional Video Synthesis with Motion Controllability

DreamVideo: Composing Your Dream Videos with Customized Subject and Motion

Customizable Image Synthesis with Multiple Subjects

Ranni: Taming Text-to-Image Diffusion for Accurate Instruction Following

Low-Rank Subspaces in GANs

EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism

Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent

Devil Is in the Queries: Advancing Mask Transformers for Real-World Medical Image Segmentation and Out-of-Distribution Localization

Res-Tuning: A Flexible and Efficient Tuning Paradigm via Unbinding Tuner from Backbone

Lipschitz Singularities in Diffusion Models

CancerUniT: Towards a Single Unified Model for Effective Detection, Segmentation, and Diagnosis of Eight Major Cancers Using a Large Collection of CT Scans

Dimensionality-Varying Diffusion Process

Data-Juicer Sandbox: A Feedback-Driven Suite for Multimodal Data-Model Co-development

Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inference

ViM: Vision Middleware for Unified Downstream Transferring

Neural Dependencies Emerging From Learning Massive Categories

UFC-BERT: Unifying Multi-Modal Controls for Conditional Image Synthesis

FaceComposer: A Unified Model for Versatile Facial Content Creation

Learning to Mutate with Hypergradient Guided Population

LipFormer: High-Fidelity and Generalizable Talking Face Generation With a Pre-Learned Facial Codebook

RA-CLIP: Retrieval Augmented Contrastive Language-Image Pre-Training

papers (21)

VideoComposer: Compositional Video Synthesis with Motion Controllability

DreamVideo: Composing Your Dream Videos with Customized Subject and Motion

Customizable Image Synthesis with Multiple Subjects

Ranni: Taming Text-to-Image Diffusion for Accurate Instruction Following

Low-Rank Subspaces in GANs

EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism

Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent

Devil Is in the Queries: Advancing Mask Transformers for Real-World Medical Image Segmentation and Out-of-Distribution Localization

Res-Tuning: A Flexible and Efficient Tuning Paradigm via Unbinding Tuner from Backbone

Lipschitz Singularities in Diffusion Models

CancerUniT: Towards a Single Unified Model for Effective Detection, Segmentation, and Diagnosis of Eight Major Cancers Using a Large Collection of CT Scans

Dimensionality-Varying Diffusion Process

Data-Juicer Sandbox: A Feedback-Driven Suite for Multimodal Data-Model Co-development

Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inference

ViM: Vision Middleware for Unified Downstream Transferring

Neural Dependencies Emerging From Learning Massive Categories

UFC-BERT: Unifying Multi-Modal Controls for Conditional Image Synthesis

FaceComposer: A Unified Model for Versatile Facial Content Creation

Learning to Mutate with Hypergradient Guided Population

LipFormer: High-Fidelity and Generalizable Talking Face Generation With a Pre-Learned Facial Codebook

RA-CLIP: Retrieval Augmented Contrastive Language-Image Pre-Training