Haoran Wang

10

Papers

79

Total Citations

Papers (10)

MV-Adapter: Multi-View Consistent Image Generation Made Easy

Adaptive Multi-modal Fusion of Spatially Variant Kernel Refinement with Diffusion Model for Blind Image Super-Resolution

Understanding the Generalization of In-Context Learning in Transformers: An Empirical Study

SEGA: A Stepwise Evolution Paradigm for Content-Aware Layout Generation with Design Prior

OUS: Bridging Scene Context and Facial Features to Overcome the Rigid Cognitive Problem

Parallel Ranking of Ads and Creatives in Real-Time Advertising Systems

PersonaHOI: Effortlessly Improving Face Personalization in Human-Object Interaction Generation

Position: TrustLLM: Trustworthiness in Large Language Models

D2SP: Dynamic Dual-Stage Purification Framework for Dual Noise Mitigation in Vision-based Affective Recognition.

Correspondence as Video: Test-Time Adaption on SAM2 for Reference Segmentation in the Wild