{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreiefasjxmv57wyy2wn5lskhwvwon4ens2kp4kp4cvfouqfj4ks7sjy",
"uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mmvr6oga4yp2"
},
"path": "/t/attention-is-all-we-had-but-not-what-we-needed-language-generation-without-attention-via-iterative-energy-based-state-refinement/176285#post_1",
"publishedAt": "2026-05-28T09:40:27.000Z",
"site": "https://discuss.huggingface.co",
"tags": [
"Attention Is All We Had — But Not What We Needed: Convergent State Machine for Iterative Energy-Based Language Generation"
],
"textContent": "We introduce CSM (Convergent State Machine) — a language model with zero attention layers that uses energy-based iterative state refinement over 16 state vectors. Key results: - 66M and 150M models, zero attention anywhere - 150M matches GPT-2 1.5B on MMLU within 0.3% (10x fewer params, 13x less data) - Perplexity decreases monotonically with more iterations - State dynamics scale with model size (66M → iter 15, 150M → iter 30+) - Total training cost: under $50\nPaper: Attention Is All We Had — But Not What We Needed: Convergent State Machine for Iterative Energy-Based Language Generation",
"title": "Attention Is All We Had — But Not What We Needed: Language generation without attention via iterative energy-based state refinement"
}