Tian Ye

OpenReview

papers

918

total citations

papers (22)

MovieChat: From Dense Token to Sparse Memory for Long Video Understanding

CVPR 2024arXiv

471

citations

Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process

ICLR 2025arXiv

100

citations

Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streaks

ICCV 2023arXiv

citations

Global Convergence of Gradient Descent for Asymmetric Low-Rank Matrix Factorization

NEURIPS 2021arXiv

citations

Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

ICLR 2025arXiv

citations

Teaching Tailored to Talent: Adverse Weather Restoration via Prompt Pool and Depth-Anything Constraint

ECCV 2024arXiv

citations

AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement

AAAI 2025arXiv

citations

Bringing RNNs Back to Efficient Open-Ended Video Understanding

ICCV 2025arXiv

citations

Dehaze-RetinexGAN: Real-World Image Dehazing via Retinex-based Generative Adversarial Network

AAAI 2025

citations

Detect Any Mirrors: Boosting Learning Reliability on Large-Scale Unlabeled Data with an Iterative Data Engine

CVPR 2025

citations

DPLUT: Unsupervised Low-light Image Enhancement with Lookup Tables and Diffusion Priors

AAAI 2025

citations

SnowMaster: Comprehensive Real-world Image Desnowing via MLLM with Multi-Model Feedback Optimization

CVPR 2025

citations

Residual Diffusion Deblurring Model for Single Image Defocus Deblurring

AAAI 2025

citations

GlassWizard: Harvesting Diffusion Priors for Glass Surface Detection

ICCV 2025

citations

GenHaze: Pioneering Controllable One-Step Realistic Haze Generation for Real-World Dehazing

ICCV 2025

citations

Perceiving and Modeling Density for Image Dehazing

ECCV 2022

citations

PromptHaze: Prompting Real-world Dehazing via Depth Anything Model

AAAI 2025

citations

Adverse Weather Removal with Codebook Priors

ICCV 2023

citations

Tian Ye

papers (22)

MovieChat: From Dense Token to Sparse Memory for Long Video Understanding

Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process

Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streaks

Global Convergence of Gradient Descent for Asymmetric Low-Rank Matrix Factorization

Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

Learning Diffusion Texture Priors for Image Restoration

VQCNIR: Clearer Night Image Restoration with Vector-Quantized Codebook

Aligning Videos in Space and Time

POSTA: A Go-to Framework for Customized Artistic Poster Generation

Teaching Tailored to Talent: Adverse Weather Restoration via Prompt Pool and Depth-Anything Constraint

AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement

Bringing RNNs Back to Efficient Open-Ended Video Understanding

Dehaze-RetinexGAN: Real-World Image Dehazing via Retinex-based Generative Adversarial Network

Detect Any Mirrors: Boosting Learning Reliability on Large-Scale Unlabeled Data with an Iterative Data Engine

DPLUT: Unsupervised Low-light Image Enhancement with Lookup Tables and Diffusion Priors

SnowMaster: Comprehensive Real-world Image Desnowing via MLLM with Multi-Model Feedback Optimization

Residual Diffusion Deblurring Model for Single Image Defocus Deblurring

GlassWizard: Harvesting Diffusion Priors for Glass Surface Detection

GenHaze: Pioneering Controllable One-Step Realistic Haze Generation for Real-World Dehazing

Perceiving and Modeling Density for Image Dehazing

PromptHaze: Prompting Real-world Dehazing via Depth Anything Model

Adverse Weather Removal with Codebook Priors

papers (22)

MovieChat: From Dense Token to Sparse Memory for Long Video Understanding

Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process

Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streaks

Global Convergence of Gradient Descent for Asymmetric Low-Rank Matrix Factorization

Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

Learning Diffusion Texture Priors for Image Restoration

VQCNIR: Clearer Night Image Restoration with Vector-Quantized Codebook

Aligning Videos in Space and Time

POSTA: A Go-to Framework for Customized Artistic Poster Generation

Teaching Tailored to Talent: Adverse Weather Restoration via Prompt Pool and Depth-Anything Constraint

AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement

Bringing RNNs Back to Efficient Open-Ended Video Understanding

Dehaze-RetinexGAN: Real-World Image Dehazing via Retinex-based Generative Adversarial Network

Detect Any Mirrors: Boosting Learning Reliability on Large-Scale Unlabeled Data with an Iterative Data Engine

DPLUT: Unsupervised Low-light Image Enhancement with Lookup Tables and Diffusion Priors

SnowMaster: Comprehensive Real-world Image Desnowing via MLLM with Multi-Model Feedback Optimization

Residual Diffusion Deblurring Model for Single Image Defocus Deblurring

GlassWizard: Harvesting Diffusion Priors for Glass Surface Detection

GenHaze: Pioneering Controllable One-Step Realistic Haze Generation for Real-World Dehazing

Perceiving and Modeling Density for Image Dehazing

PromptHaze: Prompting Real-world Dehazing via Depth Anything Model

Adverse Weather Removal with Codebook Priors