We study how explicit world-modeling objectives affect the internal representations and downstream capability of Transformers, using Rubik's Cubes as our training domain. We ask: (1) how does explicitly pretraining a world model affect a model's latent representations, (2) how does world-model quality affect post-training performance, and (3) how should a finite data budget be split between pretraining and task-specific fine-tuning? We compare standard action-prediction fine-tuning with two strategies that add explicit state-prediction supervision: state pretraining followed by fine-tuning, and joint action and state training. We measure task accuracy after Group Relative Policy Optimization (GRPO). We further find that explicit world-modeling yields better representations in terms of higher probing accuracy and steerability of the model, and that better representations yield larger gains from GRPO, especially on harder cube states. Finally, when the fine-tuning budget is held fixed, probe accuracy strongly predicts the GRPO improvement. Under a fixed total data budget, accuracy is maximized by allocating only a small fraction to pretraining.
Beyond Static Interpretability: Anticipating Post-SFT Mechanisms from Pre-SFT Parameters for Better Tuning
College of Computing and Data Science（计算与数据科学学院）；Nanyang Technological University（南洋理工大学）；School of Computer Science and Engineering（计算机科学与工程学院）；The Chinese University of Hong Kong（香港中文大学）
GUI-GENESIS: Automated Synthesis of Efficient Environments with Verifiable Rewards for GUI Agent Post-Training
Key Lab of HCST (PKU), MOE；SCS, Peking University, Beijing, China；Tencent Inc., Shenzheng, China；Hong Kong University of Science；Department of Computer Science, University of Texas at Dallas, Richardson, USA；School of Computing Science, Simon Fraser University, Burnaby, BC, Canada
What Will Post-Training Fix? Per-Problem Gains Are Shared Across Independent RL Runs, and Existing Checkpoints Predict Them Better Than A Priori Signals
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Zhongguancun Academy（中关村学院）
Using Computer Vision to enhance Safety of Workforce in Manufacturing in a Post COVID World
Group Data & Analytics, ABMCPL, Aditya Birla Group（阿迪蒂亚·比拉集团ABMCPL集团数据分析部）
COVID-19疫情迫使世界各国政府实施封锁，以防止病毒传播。这导致所有经济活动停止，因此大多数部门的制造厂停止生产。虽然恢复生产迫在眉睫，但更需要确保工厂现场工人的安全。报告显示，在工作时保持社交距离和戴口罩明显降低了传播风险。我们决定在闭路电视上使用计算机视觉来监控工人的活动，并检测违规行为，从而在车间触发实时的语音警报。本文描述了一种有效且经济的方法，使用AI在制造环境中创建安全的环境。我们展示了我们的方法来建立一个强大的社会距离测量算法，使用现代的深度学习和经典的投影几何技术的混合。我们已经在Aditya Birla Group（ABG）的制造工厂部署了我们的解决方案。我们还描述了我们的面罩检测方法，该方法在一系列定制面罩中提供了高精度。
Why Does RL Generalize Better Than SFT? A Data-Centric Perspective on VLM Post-Training
College of Computer Science, Sichuan University（四川大学计算机科学学院）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）
