8 papers · 1 filter
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…
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
Local 3D asset editing requires modifying a target region while preserving the rest. Existing methods enforce locality through mechanisms external to the generator, such as manual…
Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO
Yiran Xu, Yiming Ren, 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…
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…
SIN-Bench: Tracing Native Evidence Chains in Long-Context Multimodal Scientific Interleaved Literature
Yiming Ren, Junjie Wang, Yuxin Meng +11
Evaluating whether multimodal large language models truly understand long-form scientific papers remains challenging: answer-only metrics and synthetic "Needle-In-A-Haystack" tests…
X-Coder: Advancing Competitive Programming with Synthetic Tasks, Solutions, and Tests
Jie Wu, Haoling Li, Xin Zhang +8
Competitive programming remains challenging for code LLMs. Despite recent progress, many training pipelines still depend on scarce real-world data, raising concerns about scalabili…