19 papers
AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization
Yu Li, Menghan Xia, Gongye Liu +8
Despite being a pivotal frontier, interactive world modeling remains underexplored in terms of the versatile controllability required by practical scenarios. To bridge this gap, we…
Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO
Yiming Ren, Yiran Xu, Zicheng Lin +8
We identify a new dimension for enhancing rollout diversity in Group Relative Policy Optimization (GRPO) for LLMs. While GRPO relies on diverse rollouts, prevailing strategies prim…
DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
Quanhao Li, Junqiu Yu, Kaixun Jiang +7
Reinforcement learning has emerged as a powerful tool for improving diffusion-based text-to-image models, but existing methods are largely limited to single-task optimization. Exte…
Video-Zero: Self-Evolution Video Understanding
Ruixu Zhang, Deyi Ji, Lanyun Zhu +4
Self-evolution offers a promising path for improving reasoning models without relying on intensive human annotation. However, extending this paradigm to video understanding remains…
Velocity-Space 3D Asset Editing
Hao Liu, Yuxuan Lin, Jingfeng Guo +4
Editing a 3D asset locally, modifying a target region while preserving the rest, is a fundamental requirement of native 3D editing. Existing methods enforce locality through mechan…
From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning
Ruilin Luo, Chufan Shi, Yizhen Zhang +10
The cold-start initialization stage plays a pivotal role in training Multimodal Large Reasoning Models (MLRMs), yet its mechanisms remain insufficiently understood. To analyze this…