11 papers
CatPortrait: Taming Video Generative Models for Portrait Animation via In-context Conditioning
Ziqi Ni, Zhou Fang, Shijian Wang +2
Recent video generative models have shown strong capability in synthesizing high-quality and temporally coherent videos. Yet, adapting them for controllable portrait animation rema…
Dreaming in Flow: Bidirectional Self-Refinement for Unified Multimodal Models
Ke Hao, Yuanzhi Liang, Tingxi Chen +5
Unified multimodal models can generate images and interpret them, but their two capabilities are usually optimized with separate supervision. We introduce Bidirectional Self-Refine…
Sample-Adaptive Latent Rewards for Uncertainty-Guided Diffusion Post-Training
Rui Li, Yuanzhi Liang, Ke Hao +4
Latent reward models can supervise visual diffusion models without decoding intermediate states into pixel space. This makes alignment with human preferences more efficient. Howeve…
Stochasticity in Tokenisation Improves Robustness
Sophie Steger, Rui Li, Sofiane Ennadir +4
The widespread adoption of large language models (LLMs) has increased concerns about their robustness. Vulnerabilities in perturbations of tokenisation of the input indicate that m…
Learning to Credit the Right Steps: Objective-aware Process Optimization for Visual Generation
Rui Li, Ke Hao, Yuanzhi Liang +4
Reinforcement learning, particularly Group Relative Policy Optimization (GRPO), has emerged as an effective framework for post-training visual generative models with human preferen…
Reward-Aware Trajectory Shaping for Few-step Visual Generation
Rui Li, Bingyu Li, Yuanzhi Liang +3
Achieving high-fidelity generation in extremely few sampling steps has long been a central goal of generative modeling. Existing approaches largely rely on distillation-based frame…
TeleBoost: A Systematic Alignment Framework for High-Fidelity, Controllable, and Robust Video Generation
Yuanzhi Liang, Xuan'er Wu, Yirui Liu +12
Post-training is the decisive step for converting a pretrained video generator into a production-oriented model that is instruction-following, controllable, and robust over long te…
Rethinking Reward Signals in Video GRPO: When Scores Become Targets
Rui Li, Yuanzhi Liang, Ziqi Ni +3
Group Relative Policy Optimization (GRPO) enables stable and preference-oriented updates via group-wise comparisons for post-training video generation. However, GRPO directly optim…
Seeing What Matters: Visual Preference Policy Optimization for Visual Generation
Ziqi Ni, Yuanzhi Liang, Rui Li +4
Reinforcement learning (RL) has become a powerful tool for post-training visual generative models, with Group Relative Policy Optimization (GRPO) increasingly used to align generat…
Integrating Reinforcement Learning with Visual Generative Models: Foundations and Advances
Yuanzhi Liang, Yijie Fang, Ke Hao +4
Generative models have made significant progress in synthesizing visual content, including images, videos, and 3D/4D structures. However, they are typically trained with surrogate…
From Captions to Rewards (CAREVL): Leveraging Large Language Model Experts for Enhanced Reward Modeling in Large Vision-Language Models
Muzhi Dai, Jiashuo Sun, Zhiyuan Zhao +4
Aligning large vision-language models (LVLMs) with human preferences is challenging due to the scarcity of fine-grained, high-quality, and multimodal preference data without human…