14 papers
WorldReward: Reward Modeling for Camera-Conditioned World Models
Yibin Wang, Zehan Wang, Junshu Tang +13
Camera-conditioned world models generate interactive videos in which commanded actions should induce the expected scene changes while appearance, geometry, and temporal dynamics re…
HPSD: Hybrid-Policy Self-Distillation for Text-Image-to-Video Diffusion Models
Jiazi Bu, Pengyang Ling, Yujie Zhou +10
Text-Image-to-Video (TI2V) models are an emerging unified architecture, where a single model simultaneously supports text-to-video (T2V) and image-to-video (I2V) generation. Given…
CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioning
Penghui Yang, Long Xing, Xiaoyi Dong +10
Image and video captioning are fundamental tasks that bridge the visual and linguistic domains, playing a critical role in pre-training Large Vision-Language Models (LVLMs). Curren…
Light-WAM: Efficient World Action Models with State-Fusion Action Decoding
Ziang Li, Dongzhou Cheng, Yibin Wang +5
World Action Models (WAMs) extend robot policy learning by incorporating future prediction as an additional training objective, encouraging the policy to encode task-relevant tempo…
AdaGRPO: A Capability-Aware Adaptive Enhancement for Flow-based GRPO
Jiazi Bu, Pengyang Ling, Yujie Zhou +8
Group Relative Policy Optimization (GRPO) has demonstrated remarkable success in aligning text-to-image (T2I) flow models with human preferences. However, we have identified that t…
Pave-GRPO: Beyond Instantaneous Guidance through Principled Average Velocity Decomposition
Pengyang Ling, Jiazi Bu, Yujie Zhou +6
Group Relative Policy Optimization(GRPO) has emerged as an effective paradigm for aligning flow-based generative models with human preferences. However, the high cost of group roll…
LoMo: Local Modality Substitution for Deeper Vision-Language Fusion
Feng Han, Zhixiong Zhang, Zheming Liang +2
Vision-Language Models (VLMs) have achieved substantial progress across a wide range of understanding and reasoning tasks, driven by large-scale image-text training aimed at multim…
SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction
Zhixiong Zhang, Yizhuo Li, Shuangrui Ding +6
Referring segmentation grounds natural-language queries to pixel-level masks, but extending it to complex scenarios with multiple instances, cross-category groups, or open-ended ta…
From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space
Jiazi Bu, Pengyang Ling, Yujie Zhou +8
Group Relative Policy Optimization (GRPO) has emerged as a powerful framework for preference alignment in text-to-image (T2I) flow models. However, we observe that the standard par…
EtCon: Edit-then-Consolidate for Reliable Knowledge Editing
Ruilin Li, Yibin Wang, Wenhong Zhu +5
Knowledge editing aims to update specific facts in large language models (LLMs) without full retraining. Prior efforts sought to tune the knowledge layers of LLMs, achieving improv…
Fine-Grained GRPO for Precise Preference Alignment in Flow Models
Yujie Zhou, Pengyang Ling, Jiazi Bu +5
The incorporation of online reinforcement learning (RL) into diffusion and flow-based generative models has recently gained attention as a powerful paradigm for aligning model beha…
DiCache: Let Diffusion Model Determine Its Own Cache
Jiazi Bu, Pengyang Ling, Yujie Zhou +4
Recent years have witnessed the rapid development of acceleration techniques for diffusion models, especially caching-based acceleration methods. These studies seek to answer two f…
Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
Yibin Wang, Zhimin Li, Yuhang Zang +6
Recent advancements highlight the importance of GRPO-based reinforcement learning methods and benchmarking in enhancing text-to-image (T2I) generation. However, current methods usi…
GeometryZero: Advancing Geometry Solving via Group Contrastive Policy Optimization
Yikun Wang, Yibin Wang, Dianyi Wang +4
Recent progress in large language models (LLMs) has boosted mathematical reasoning, yet geometry remains challenging where auxiliary construction is often essential. Prior methods…