11 papers
Editing on the Generative Manifold: A Theoretical and Empirical Study of General Diffusion-Based Image Editing Trade-offs
Yi Hu, Leying Yi, Emily Davis +1
Diffusion-based editing has rapidly evolved from curated inpainting tools into general-purpose editors spanning text-guided instruction following, mask-localized edits, drag-based…
CutClaw: Agentic Hours-Long Video Editing via Music Synchronization
Shifang Zhao, Yihan Hu, Ying Shan +2
Editing the video content with audio alignment forms a digital human-made art in current social media. However, the time-consuming and repetitive nature of manual video editing has…
Ratio-Variance Regularized Policy Optimization for Efficient LLM Fine-tuning
Yu Luo, Shuo Han, Yihan Hu +2
On-policy reinforcement learning (RL), particularly Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO), has become the dominant paradigm for fine-tuni…
EasyOmnimatte: Taming Pretrained Inpainting Diffusion Models for End-to-End Video Layered Decomposition
Yihan Hu, Xuelin Chen, Xiaodong Cun
Existing video omnimatte methods typically rely on slow, multi-stage, or inference-time optimization pipelines that fail to fully exploit powerful generative priors, producing subo…
DeepFRC: An End-to-End Deep Learning Model for Functional Registration and Classification
Siyuan Jiang, Yihan Hu, Wenjie Li +1
Functional data, representing curves or trajectories, are ubiquitous in fields like biomedicine and motion analysis. A fundamental challenge is phase variability -- temporal misali…
Dual-Forward Path Teacher Knowledge Distillation: Bridging the Capacity Gap Between Teacher and Student
Tong Li, Long Liu, Yihang Hu +2
Knowledge distillation (KD) provides an effective way to improve the performance of a student network under the guidance of pre-trained teachers. However, this approach usually bri…