ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Junfeng He

Junfeng He

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 1:13 AM AMS

8

papers

198

total citations

papers (8)

Rich Human Feedback for Text-to-Image Generation

Calibrated Multi-Preference Optimization for Aligning Diffusion Models

Deep Saliency Prior for Reducing Visual Distraction

Erasing More Than Intended? How Concept Erasure Degrades the Generation of Non-Target Concepts

Cropper: Vision-Language Model for Image Cropping through In-Context Learning

Focus-N-Fix: Region-Aware Fine-Tuning for Text-to-Image Generation

Learning From Unique Perspectives: User-Aware Saliency Modeling

Teacher-Generated Spatial-Attention Labels Boost Robustness and Accuracy of Contrastive Models