As executable environments for language agents scale, generating and verifying their rollouts becomes increasingly expensive. Under finite rollout budgets, this raises an important question: can data management at the environment level make agentic reinforcement learning (RL) more efficient by organizing, evaluating, a...
Sihan Yang, Wei Bai, Rui-Chuan An et al.· 0 citations
Large language model agents have enabled software development through natural-language interaction, but extending this paradigm to end-to-end game development remains challenging. Building a playable game requires coordinating code, scenes, assets, animations, physics, and configurations, while allowing developers to v...
Wen-Bo Hu, Ken Li, Jia-Zhe Wei et al.· 2 citations
SteerVTE is introduced, a unified framework that steers a frozen video diffusion model to perform precise Video Text Editing through style and glyph control and substantially outperforms existing video editing baselines across text accuracy, style consistency, and temporal coherence.
Kai Zeng, Mo-Ran Li, Zheng-Wei Wang et al.· arXiv.org· 5 citations
CapGeo-Bench is proposed, a benchmark of 4,641 high-quality figure-caption pairs equipped with a fine-grained keypoint-based evaluation metric that provides high-quality captions consistently and substantially boosts performance of MLLMs, empirically validating the visual perception bottleneck in geometric reasoning.
Yu-Ying Li, Si-Yi Qian, Hao Liang et al.· 5 citations
VideoCoCo, an agentic dual-engine framework in which executable Blender code serves as a process-level chain of thought, demonstrates that executable code provides an effective, controllable, and inspectable intermediate representation for physically consistent video generation.
Haodong Li, Tianfei Ren, Xiaoxiao Ma et al.· arXiv.org· 8 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.