Rufus-Air is an open and reproducible post-training method for the GLM-4.5-Air-Base model, structured as an eight-stage pipeline that progresses from basic to advanced capabilities. It emphasizes diverse data, reward design, and infrastructure choices to enhance model performance.
The chart will appear after repeat observations. The current metric comes from the source.
1 source votesReal observations only. History before source connection is not reconstructed.
This approach provides a structured, open-source method for improving large language models through a staged training process, emphasizing reproducibility and practical engineering choices.
OmniEdu is an open family of foundation models designed for K-12 education, focusing on problem solving, curriculum understanding, diagnostic reasoning, and instructional support. The models are trained on a diverse dataset of educational resources and evaluated on multiple benchmarks, showing strong performance in educational tasks.
6 days agoDaily PapersThe paper introduces Taste-Bench, a benchmark for evaluating an agent's 'taste' in making long-horizon decisions. It measures the ability to choose the better path in decision forks without knowing future outcomes, revealing that current models perform poorly and that taste can be improved through distillation.
3 days agoDaily PapersThe paper introduces Document Retrieval-Aware Chunking (D-RAC), a method for efficiently processing enterprise documents by normalizing them into PDF and converting them into retrieval-optimized Markdown using a multimodal LLM. This approach preserves document structure, reduces token costs, and improves chunking efficiency compared to traditional methods.
4 days agoDaily PapersHappyWorld-Bench is a comprehensive benchmark for evaluating the reliability of generated worlds under interaction, exploring their consistency and responsiveness. It includes three tracks—video, spatial, and embodied world models—with 1,138 video prompts, 300 spatial scenes, and 254 embodied test cases. The benchmark uses human A/B comparisons and automated metrics to assess behavioral correctness and model performance across 14 video, 9 spatial, and 8 embodied systems.
4 days agoDaily PapersThis paper introduces an all-in-one multilingual scene text recognition system that uses a script-aware Mixture-of-Experts (MoE) architecture. The system, called ScriptMoE, outperforms existing methods on multilingual text recognition tasks by leveraging a large synthetic dataset and a lightweight architecture that shares a visual encoder while using script-specific experts for decoding.
4 days agoDaily PapersThe paper introduces Spatial-Interactor, a framework for training vision-language models (VLMs) to model physical-world state transitions through interaction. It uses a three-level curriculum and a dataset of simulated and real interaction trajectories to improve spatial reasoning in dynamic environments.
6 days ago