11 papers
Temporal Concentration from Rollout Errors: Implicit Preference Optimization for Text-to-Video Diffusion
Henglin Liu, Fangyuan Kong, Jing Wang +7
Recent advances in preference alignment for diffusion-based video generation, particularly via Direct Preference Optimization (DPO), have significantly improved visual quality. How…
MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control
Kaiqi Liu, Yunyao Mao, Ziqi Cai +8
While recent generative models produce high-fidelity videos, they struggle with the complex narrative control required for coherent multi-shot audio-visual generation. Existing met…
Balancing Image Compression and Generation with Bootstrapped Tokenization
Haozhe Chi, Jinghan Li, Hao Jiang +4
Despite progress in image tokenization, standard methods encode redundant information by mixing all granularities within each token, thus redundancy persists between tokens. The mi…
LithoGRPO: Fast Inverse Lithography via GRPO Reinforced Flow Matching
Yao Lai, Xuyuan Xiong, Zeyue Xue +7
In semiconductor manufacturing, lithography projects circuit layouts onto silicon wafers through an optical mask. As circuit features shrink below the wavelength of light, optical…
Efficient Generative Retrieval for E-commerce Search with Semantic Cluster IDs and Expert-Guided RL
Jianbo Zhu, Xing Fang, Jing Wang +5
Generative retrieval offers a promising alternative by unifying the fragmented multi-stage retrieval process into a single end-to-end model. However, its practical adoption in indu…
HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer
Qi Cai, Jingwen Chen, Chengmin Gao +22
The evolution of visual generative models has long been constrained by fragmented architectures relying on disjoint text encoders and external VAEs. In this report, we present HiDr…
Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping
Haoyuan Sun, Jing Wang, Yuxin Song +9
Recently, post-training methods based on reinforcement learning, with a particular focus on Group Relative Policy Optimization (GRPO), have emerged as the robust paradigm for furth…
CADC: Content Adaptive Diffusion-Based Generative Image Compression
Xihua Sheng, Lingyu Zhu, Tianyu Zhang +3
Diffusion-based generative image compression has demonstrated remarkable potential for achieving realistic reconstruction at ultra-low bitrates. The key to unlocking this potential…
DiverseGRPO: Mitigating Mode Collapse in Image Generation via Diversity-Aware GRPO
Henglin Liu, Huijuan Huang, Jing Wang +3
Reinforcement learning (RL), particularly GRPO, improves image generation quality significantly by comparing the relative performance of images generated within the same group. How…
GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping
Jing Wang, Jiajun Liang, Jie Liu +10
Recently, GRPO-based reinforcement learning has shown remarkable progress in optimizing flow-matching models, effectively improving their alignment with task-specific rewards. With…
PatchVSR: Breaking Video Diffusion Resolution Limits with Patch-wise Video Super-Resolution
Shian Du, Menghan Xia, Chang Liu +5
Pre-trained video generation models hold great potential for generative video super-resolution (VSR). However, adapting them for full-size VSR, as most existing methods do, suffers…