Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

OGBench

AI overview

Sign in and the AI will write an overview from our coverage.

Headlines · 3

  1. AFFECT trains world models to respond to small action changes

    John Won, Yonghoon Dong, and Jinwoo Shin submitted a 27-page preprint introducing AFFECT, an auxiliary training objective that teaches world models how visual observations respond to action perturbations. The method injects temporally correlated noise into actions from a task-agnostic human teleoperation policy, avoiding repeated execution from the same initial state. The authors report improved world-model fidelity on OGBench, DROID, and ALOHA-2, with DROID policy-success correlation rising from 0.47 to 0.79 and planning task success improving by up to 8.3%.

    Hugging Face · Papers · 🔥 0
  2. JEPA4R brings JEPA planning to 4D point clouds and real robots

    A newly submitted paper introduces JEPA4R, an embodied JEPA world model that observes single-depth-camera point clouds, predicts and plans in latent space, and acts through a policy head using frozen representations. The authors report a mean point error within 1.1 cm over 200 predicted steps, strong results across OGBench, CortexBench, MetaWorld, and Adroit, and zero-shot operation of a real robotic arm after digital-twin training. These benchmark and hardware results are author-reported and have not been independently confirmed.

    Hugging Face · Papers · 🔥 0
  3. SQAM: Q-learning with scalar adjoint matching for flow policies

    An arXiv preprint proposes Q-Learning with Scalar Adjoint Matching (SQAM). The authors observe that the batch-averaged velocity Jacobian of pretrained flow policies concentrates on its diagonal, and use this to derive a closed-form scalar adjoint that scales the value gradient at the final action by flow time, removing per-step vector–Jacobian products. SQAM pairs this with a value penalty at policy-generated actions. It beats the strongest baseline in each of the four hardest OGBench domains by 18 to 35 percentage points, and when fine-tuning a vision-language-action policy on a real bimanual robot it improves over supervised fine-tuning on all three tasks.

    Hugging Face · Papers · 🔥 0

Experience and discussion from the community

Share my OGBench experienceAsk about OGBench

Nobody has shared their experience with OGBench yet.