Publications

Wenjie Shu (2025). Enhancing Diffusion-based Restoration Models via Difficulty-Adaptive Reinforcement Learning with IQA Reward. Under review.

Wenjie Shu (2025). Go with Your Gut: Scaling Confidence for Autoregressive Image Generation. Preprint.

Wenjie Shu (2025). ThinkVid: Benchmarking Visual Reasoning in Video Generative Models. Under review.

Wenjie Shu (2025). CoRe-GRPO: Consensus-driven and Region-focused RL for Human-Centric Generation in Lightweight Diffusion Models. Under review.

Wenjie Shu (2025). AlignVid: Training-Free Attention Scaling for Semantic Fidelity in Text-Guided Image-to-Video Generation. Under review.

Wenjie Shu (2025). Temporal Regularization Makes Your Video Generator Stronger. Preprint.

Wenjie Shu (2025). LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference Optimization. Preprint.

Wenjie Shu (2024). VideoGen-of-Thought: Step-by-step Generating Multi-shot Video with Minimal Manual Intervention. NIPSW 2026 (Workshop).

Wenjie Shu (2024). CMT: Cross Modulation Transformer with Hybrid Loss for Pansharpening. IEEE GRSL.

Wenjie Shu

Equal contribution

(2024). Exploring the Low-Pass Filtering Behavior in Image Super-Resolution. In ICML 2024.