Zirui Wang

14

Papers

1,386

Total Citations

1

Affiliations

Affiliations

Carnegie Mellon University

Papers (14)

Scaling Autoregressive Models for Content-Rich Text-to-Image Generation

DifIISR: A Diffusion Model with Gradient Guidance for Infrared Image Super-Resolution

YOLO-Count: Differentiable Object Counting for Text-to-Image Generation

Seeing in the Dark: Benchmarking Egocentric 3D Vision with the Oxford Day-and-Night Dataset

NoPe-NeRF: Optimising Neural Radiance Field With No Pose Prior

REVEAL: Retrieval-Augmented Visual-Language Pre-Training With Multi-Source Multimodal Knowledge Memory

Temporal Cue Guided Video Highlight Detection With Low-Rank Audio-Visual Fusion

Guiding Image Captioning Models Toward More Specific Captions

DFNet: Enhance Absolute Pose Regression with Direct Feature Matching

Characterizing and Avoiding Negative Transfer

TokenCompose: Text-to-Image Diffusion with Token-level Supervision

Neural Refinement for Absolute Pose Regression with Feature Synthesis

Language Models as Science Tutors

Language Models Meet World Models: Embodied Experiences Enhance Language Models