{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreiek3lyzzr6nqe5cfi3bfcepvv37bcn6e2wmyplkuotc5amnnww6eq",
"uri": "at://did:plc:mxzzpugn7bprjjrszwkbez3u/app.bsky.feed.post/3mja7dhxnj5u2"
},
"coverImage": {
"$type": "blob",
"ref": {
"$link": "bafkreihklqxyrzbfjpmfqyl5ykuh4brbytsolko4hobgr3gs4bg2exezza"
},
"mimeType": "image/jpeg",
"size": 314836
},
"path": "/news/2026-04-hardware-software-efficiently-ai-edge.html",
"publishedAt": "2026-04-11T11:00:04.000Z",
"site": "https://techxplore.com",
"tags": [
"Software"
],
"textContent": "A new hardware-software co-design increases AI energy efficiency and reduces latency, enabling real-time processing of continuous data streams like video or sensor feeds. The neuromorphic approach unlocks the ability to run powerful, real-time AI directly on local edge devices like phones, hearing aids or autonomous vehicle cameras, according to a University of Michigan Engineering study published in Nature Communications.",
"title": "A hardware-software co-design can efficiently run AI on edge devices"
}