![trunk/4fdbeb7393919717a7ae4e49e982b46cd3dc2f31: [shard prop] use torch.Tag.pointwise for sharding prop rules (#176824)](https://avatars.githubusercontent.com/u/32071673?s=60&v=4)
trunk/4fdbeb7393919717a7ae4e49e982b46cd3dc2f31: [shard prop] use torch.Tag.pointwise for sharding prop rules (#176824)
<p>Pull Request resolved: <a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="4040669392" data-permission-text="Title is private" data-url="https://github.com/pytorch/pytorch/issues/176824" data-hovercard-type="pull_request" data-hovercard-url="/pytorch/pytorch/pull/176824/hovercard" href="https://github.com/pytorch/pytorch/pull/176824">#176824</a><br> Approved by: <a href="https://github.com/Skylion007">https://github.com/Skylion007</a></p>
Pull Request resolved: https://github.com/pytorch/pytorch/pull/176824 Approved by: https://github.com/Skylion007Pull Request resolved: https://github.com/pytorch/pytorch/pull/176824 Approved by: https://github.com/Skylion007Assets 2
PyTorch Releases
https://github.com/pytorch/pytorch/releases/tag/trunk%2F4fdbeb7393919717a7ae4e49e982b46cd3dc2f31Sign in to highlight and annotate this article
Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
github
Semantic Zone-Based Map Management for Stable AI-Integrated Mobile Robots
arXiv:2603.29627v1 Announce Type: new Abstract: Recent advances in large AI models (VLMs and LLMs) and joint use of the 3D dense maps, enable mobile robots to provide more powerful and interactive services grounded in rich spatial context. However, deploying both heavy AI models and dense maps on edge robots is challenging under strict memory budgets. When the memory budget is exceeded, required keyframes may not be loaded in time, which can degrade the stability of position estimation and interfering model performance. We proposes a semantic zone-based map management approach to stabilize dense-map utilization under memory constraints. We associate keyframes with semantic indoor regions (e.g., rooms and corridors) and keyframe management at the semantic zone level prioritizes spatially re
RAAP: Retrieval-Augmented Affordance Prediction with Cross-Image Action Alignment
arXiv:2603.29419v1 Announce Type: new Abstract: Understanding object affordances is essential for enabling robots to perform purposeful and fine-grained interactions in diverse and unstructured environments. However, existing approaches either rely on retrieval, which is fragile due to sparsity and coverage gaps, or on large-scale models, which frequently mislocalize contact points and mispredict post-contact actions when applied to unseen categories, thereby hindering robust generalization. We introduce Retrieval-Augmented Affordance Prediction (RAAP), a framework that unifies affordance retrieval with alignment-based learning. By decoupling static contact localization and dynamic action direction, RAAP transfers contact points via dense correspondence and predicts action directions throu
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
More in Products
Baidu’s robotaxis froze in traffic creating chaos
Numerous robotaxis operated by Chinese tech giant Baidu froze in a major city on Tuesday, reportedly trapping passengers inside, stranding them on highways, and causing at least one accident in snarled traffic. Police in Wuhan confirmed receiving multiple reports of Baidu's Apollo Go robotaxis stopping in the middle of streets and being unable to move. […]
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!