Benlin Liu

papers

1,784

total citations

papers (10)

DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

NEURIPS 2021arXiv

946

citations

TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering

ICCV 2023arXiv

355

citations

Unleashing Text-to-Image Diffusion Models for Visual Perception

ICCV 2023arXiv

302

citations

RandomRooms: Unsupervised Pre-Training From Synthetic Shapes and Randomized Layouts for 3D Object Detection

ICCV 2021arXiv

citations

Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model

CVPR 2025arXiv

citations

Seeking and Updating with Live Visual Knowledge

NEURIPS 2025arXiv

citations

GMValuator: Similarity-based Data Valuation for Generative Models

ICLR 2025arXiv

citations

Benlin Liu

papers (10)

DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering

Unleashing Text-to-Image Diffusion Models for Visual Perception

RandomRooms: Unsupervised Pre-Training From Synthetic Shapes and Randomized Layouts for 3D Object Detection

MetaDistiller: Network Self-Boosting via Meta-Learned Top-Down Distillation

Robust Object Detection via Instance-Level Temporal Cycle Confusion

Efficient Inference of Vision Instruction-Following Models with Elastic Cache

Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model

Seeking and Updating with Live Visual Knowledge

GMValuator: Similarity-based Data Valuation for Generative Models

papers (10)

DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering

Unleashing Text-to-Image Diffusion Models for Visual Perception

RandomRooms: Unsupervised Pre-Training From Synthetic Shapes and Randomized Layouts for 3D Object Detection

MetaDistiller: Network Self-Boosting via Meta-Learned Top-Down Distillation

Robust Object Detection via Instance-Level Temporal Cycle Confusion

Efficient Inference of Vision Instruction-Following Models with Elastic Cache

Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model

Seeking and Updating with Live Visual Knowledge

GMValuator: Similarity-based Data Valuation for Generative Models