9 papers
KwaiMind Technical Report
Junlong Wu, Zijun Li, Yuting Hu +14
Commercial image editing requires product identity preservation, accurate text rendering, and user appeal alongside general editing quality. We present KwaiMind, an image editing s…
Joint Alignment and Distillation for Video Generation via Sample-Guided Distribution Matching
Jiuzhou Lin, Junlong Wu, Fei Zuo +11
Aligning video generative models to human preferences heavily relies on Reinforcement Learning (RL), which suffers from extensive computational overhead. Existing workflows typical…
Step Back to Move Forward: Reflection-Aware Preference Optimization for Visual Generation
Junlong Wu, Jiuzhou Lin, Jia Sun +7
Diffusion models have become the mainstream paradigm for modern visual generation and have substantially advanced multimedia content synthesis, especially in text-to-image and text…
TextRefine: Improving Textual Fidelity, Spatial Placement, and Glyph Rendering for Text Editing in Product Posters
Honglie Wang, Jia Sun, Zijun Li +11
Text editing in product posters entails inserting new text or replacing existing text while preserving product appearance, background content, and global composition. Despite recen…
DASH-OPD: Discrepancy-Aware Switching with Hysteresis for On-Policy Distillation
Yuchen Xia, Qianguo Sun, Chao Song +3
While on-policy distillation (OPD) reduces exposure bias by training student language models on their own rollouts, early student errors in long-horizon agentic scenarios can lead…
DetailAnywhere: Fashion Detail Generation via Cross-Modal Feature Alignment Distillation
Zijun Li, Yimin Zhou, Jia Sun +12
Diffusion-based generative AI has achieved remarkable success in e-commerce applications such as virtual try-on, poster generation, and product background synthesis. However, when…
Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe
Xixi Wu, Qianguo Sun, Ruiyang Zhang +4
Reinforcement Learning (RL) is essential for evolving Large Language Models (LLMs) into autonomous agents capable of long-horizon planning, yet a practical recipe for scaling RL in…
Linear Preference Optimization: Decoupled Gradient Control via Absolute Regularization
Rui Wang, Qianguo Sun, Chao Song +4
DPO (Direct Preference Optimization) has become a widely used offline preference optimization algorithm due to its simplicity and training stability. However, DPO is prone to overf…
UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic information
Rui Wang, Qianguo Sun, Tianrong Chen +3
The emergence of multi-codebook neutral audio codecs such as Residual Vector Quantization (RVQ) and Group Vector Quantization (GVQ) has significantly advanced Large-Language-Model…