Han Zhao

Xiaoyu Tian, Sitong Zhao, Haotian Wang et al.

Although large language models (LLMs) have recently achieved remarkable performance on various complex reasoning benchmarks, the academic community still lacks an in-depth understanding of base model training processes and data quality. To address this, we construct a large-scale, difficulty-graded reasoning dataset containing approximately 3.34 million unique queries of varying difficulty levels and about 40 million distilled responses generated by multiple models over several passes. Leveraging pass rate and Coefficient of Variation (CV), we precisely select the most valuable training data to enhance reasoning capability. Notably, we observe a training pattern shift, indicating that reasoning-focused training based on base models requires higher learning rates for effective training. Using this carefully selected data, we significantly improve the reasoning capabilities of the base model, achieving a pass rate of 79.2\% on the AIME2024 mathematical reasoning benchmark. This result surpasses most current distilled models and closely approaches state-of-the-art performance. We provide detailed descriptions of our data processing, difficulty assessment, and training methodology, and have publicly released all datasets and methods to promote rapid progress in open-source long-reasoning LLMs. The dataset is available at: \href{https://huggingface.co/datasets/a-m-team/AM-DeepSeek-Distilled-40M}{https://huggingface.co/datasets/a-m-team/AM-DeepSeek-Distilled-40M}

Xingxuan Li, Yao Xiao, Dianwen Ng et al.

Large language models have recently evolved from fluent text generation to advanced reasoning across diverse domains, giving rise to reasoning language models. Among these domains, mathematical reasoning serves as a representative benchmark as it requires precise multi-step logic and abstract reasoning, which can be generalized to other tasks. While closed-source RLMs such as GPT-o3 demonstrate impressive reasoning capabilities, their proprietary nature limits transparency and reproducibility. Although many open-source projects aim to close this gap, most of them lack sufficient openness by omitting critical resources such as datasets and detailed training configurations, which hinders reproducibility. To contribute toward greater transparency in RLM development, we introduce the MiroMind-M1 series, a set of fully open-source RLMs built on the Qwen-2.5 backbone that match or exceed the performance of existing open-source RLMs. Specifically, our models are trained in two stages: SFT on a carefully curated corpus of 719K math-reasoning problems with verified CoT trajectories, followed by RLVR on 62K challenging and verifiable problems. To enhance the robustness and efficiency of the RLVR process, we introduce Context-Aware Multi-Stage Policy Optimization, an algorithm that integrates length-progressive training with an adaptive repetition penalty to encourage context-aware RL training. Our model achieves state-of-the-art or competitive performance and superior token efficiency among Qwen-2.5-based open-source 7B and 32B models on the AIME24, AIME25, and MATH benchmarks. To facilitate reproducibility, we release the complete stack: models (MiroMind-M1-SFT-7B, MiroMind-M1-RL-7B, MiroMind-M1-RL-32B); datasets (MiroMind-M1-SFT-719K, MiroMind-M1-RL-62K); and all training and evaluation configurations. We hope these resources will support further research and foster community advancement.

Zhao Han, Jenna Parrillo, Alexander Wilkinson et al.

For mobile robots, mobile manipulators, and autonomous vehicles to safely navigate around populous places such as streets and warehouses, human observers must be able to understand their navigation intent. One way to enable such understanding is by visualizing this intent through projections onto the surrounding environment. But despite the demonstrated effectiveness of such projections, no open codebase with an integrated hardware setup exists. In this work, we detail the empirical evidence for the effectiveness of such directional projections, and share a robot-agnostic implementation of such projections, coded in C++ using the widely-used Robot Operating System (ROS) and rviz. Additionally, we demonstrate a hardware configuration for deploying this software, using a Fetch robot, and briefly summarize a full-scale user study that motivates this configuration. The code, configuration files (roslaunch and rviz files), and documentation are freely available on GitHub at https://github.com/umhan35/arrow_projection.

Reuth Mirsky, Megan Zimmerman, Muneed Ahmad et al.

The Artificial Intelligence (AI) for Human-Robot Interaction (HRI) Symposium has been a successful venue of discussion and collaboration since 2014. During that time, these symposia provided a fertile ground for numerous collaborations and pioneered many discussions revolving trust in HRI, XAI for HRI, service robots, interactive learning, and more. This year, we aim to review the achievements of the AI-HRI community in the last decade, identify the challenges facing ahead, and welcome new researchers who wish to take part in this growing community. Taking this wide perspective, this year there will be no single theme to lead the symposium and we encourage AI-HRI submissions from across disciplines and research interests. Moreover, with the rising interest in AR and VR as part of an interaction and following the difficulties in running physical experiments during the pandemic, this year we specifically encourage researchers to submit works that do not include a physical robot in their evaluation, but promote HRI research in general. In addition, acknowledging that ethics is an inherent part of the human-robot interaction, we encourage submissions of works on ethics for HRI. Over the course of the two-day meeting, we will host a collaborative forum for discussion of current efforts in AI-HRI, with additional talks focused on the topics of ethics in HRI and ubiquitous HRI.