American Open Source is so back. 9 / 30 of the models on page 1 of Huggingface are published by Nvidia.

Excited to introduce SOLE-R1, a video-language reasoning model for zero-shot reward prediction for robot manipulation tasks! SOLE-R1 reasoning can serve as the SOLE signal for learning new tasks (completely from scratch) through online RL - i.e., robots start with random actions and learn previously unseen tasks guided only by SOLE-R1 rewards, without any demonstrations, ground-truth rewards, success indicators, or task-specific tuning. SOLE-R1 significantly outperforms strong baselines (e.g., Robometer, RoboReward, TOPReward, GPT-5, Gemini-3-Pro) in zero-shot online RL when evaluated across 40 tasks - including a real-world tabletop manipulation setting and 4 sim environments (LIBERO, ManiSkill, Meta-World, RoboSuite). We open source all models, training data, and code. Website, demos, and paper at: philip-mit.github.io/sole-r1… 🧵 (1/6)

releasing AME2: Agile and Generalized Legged Locomotion via Attention-Based Neural Map Encoding arxiv.org/abs/2601.08485 In this work, we discuss how to achieve a combination of generalization and agility in legged locomotion, and propose a general solution.

🎉 We released MIKASA-Robo-VLA v1.0.0 — a benchmark suite for studying memory in Vision-Language-Action (VLA) policies for tabletop robotic manipulation. mikasarobo.github.io/ 🧠 The goal is simple: make memory evaluation in robotic manipulation more systematic. 👇

Humanity, created by God in all its grandeur, is today facing a pivotal choice: either to construct a new Tower of Babel or to build the city in which God and humanity dwell together. In Jesus Christ, this humanity in its grandeur becomes the Way, the Truth and the Life, opening the path for each of us to grow toward fullness. #MagnificaHumanitas vatican.va/content/leo-xiv/e…

Most capable generalist robotics models today are closed or at best, open weights. But robotics won’t reach its ChatGPT moment without real openness. That GPT moment was built on years of open tools and datasets such as Python, PyTorch, ImageNet and more, that let researchers inspect, reproduce, and build. Today, we’re introducing MolmoAct 2: a fully open-source action reasoning model for real-world robotics. We rethought and reshaped everything! 🧵👇

本日5月14日（木）から、ポケモンセンターオンラインで「ミニテーブル ヌオー」が注文受け付け中！ ヌオーといっしょなら、おやつタイムがもっと楽しくなるかも……!? くわしくはこちらをチェックしてね！ pokemoncenter-online.com/452… #ポケモンセンターオンライン

I feel it’s really unhelpful that searching for “deep RL” sends you to Q learning, MDPs, Bellman’s equation etc, when it’s literally just Run LLM agent on data -> was it good? -> policy gradient /- reward Like that’s actually it! And LLMs are just stacks of attn MLP

Most open VLA models are not really open. They release weights and call it reproducibility. The training data is withheld. The training code is withheld. The deployment pipeline is withheld. You get a checkpoint file and a paper. You cannot verify the data quality. You cannot reproduce the training run. You cannot adapt it to your robot without starting from scratch. Researchers from Allen AI released MolmoAct2, the first VLA that is open. Weights, training code, complete datasets.  • MolmoAct2-BimanualYAM Dataset: 720 hours of teleoperated trajectories across 28 real-world tasks, the largest open bimanual dataset available.  • MolmoAct2-SO100/101 Dataset: 38,059 episodes curated from 1,222 public datasets.  • MolmoAct2-DROID Dataset: Quality-filtered Franka trajectories with re-annotated instructions. The system deploys out-of-the-box on three platforms spanning the low-to-medium cost range. Bimanual YAM, SO-100/101, DROID Franka. No additional fine-tuning required. The backbone is Molmo2-ER, trained on a 3.3M sample corpus for embodied reasoning: metric distance estimation, free space detection, cross-view object tracking, scene geometry reconstruction. The skills general-purpose VLMs do not test. Results Look Promissing 63.8% average across 13 embodied reasoning benchmarks. Outperforms GPT-5 and Gemini Robot ER-1.5 on 9 of 13 tasks. Outperforms π0.5 across 7 simulation and real-world benchmarks. The architecture uses per-layer KV conditioning between the VLM and a flow-matching action expert trained with DiT-style transformers. This bridges discrete reasoning tokens to continuous control trajectories while exposing the attention state the VLM itself uses. This is the deployment model NeuraCore advocates for: standardized ecosystems with reproducible training data. Custom infrastructure for every embodiment is technical debt that prevents fleet scaling. Nice work from @hq_fang, @DJiafei, and the team at @allen_ai