← Search

Wenjie Xuan

2 accepted papers

2026

Learn to Think: Improving Multimodal Reasoning through Vision-Aware Self-Improvement Training

ICML 2026poster

Post-training with explicit reasoning traces is common to improve the reasoning capabilities of Multimodal Large Language Models (MLLMs). However, acquiring high-quality reasoning traces is often costly and time-consuming. Hence, the self-improvement paradigm has emerged, enabling MLLMs to self-gene…

Cited by 0SourceScholar
2025

Rethink Sparse Signals for Pose-guided Text-to-image Generation

ICCV 2025poster

Recent works favored dense signals (e.g., depth, DensePose), as an alternative to sparse signals (e.g., OpenPose), to provide detailed spatial guidance for pose-guided text-to-image generation. However, dense representations raised new challenges including editing difficulties and potential inconsis…