{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_343b7fd07e24fb897f5a204d651ff391887ccc94eda88f7e58ed866f8fd16a60","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_343b7fd07e24fb897f5a204d651ff391887ccc94eda88f7e58ed866f8fd16a60","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"ef3df4f57115ff3ebb7b0b8f8e221d05e2c5fa421db727b8288781d0ddf9577d","published":"Wed, 27 May 2026 00:00:00 -0400","receipt_hash":"ef3df4f57115ff3ebb7b0b8f8e221d05e2c5fa421db727b8288781d0ddf9577d","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"ef3df4f57115ff3ebb7b0b8f8e221d05e2c5fa421db727b8288781d0ddf9577d","observed_at":"2026-05-27T04:43:18.926230Z","parent_run_hash":"6f581915edab4326e2b95fed7c82c2ee149e978d6d7c2443439442a927c31dfa","published":"Wed, 27 May 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2605.24001v2 Announce Type: replace-cross \nAbstract: Recent advances in one-step text-to-image generation have enabled real-time synthesis with remarkable efficiency and quality. Previous reinforcement learning methods for one-step generators combine image-space reward optimization with diffusion noisy-space distribution matching. This paradigm brings challenges due to a mismatch between terminal reward optimization and the underlying generative dynamics. As a result, optimization tends to exploit stochastic degrees of freedom, often improving reward at the expense of image fidelity. To address this issue, we propose Diff-Instruct with Diffused Reward (DIDR), a data-free trajectory-level alignment framework derived from Integral KL minimization. DIDR propagates the RLHF-optimal reward-tilted clean-image distribution across all noise levels along the diffusion trajectory. We show that this objective admits the same minimizer as clean-image RLHF, while naturally inducing the Diffus","title":"Diff-Instruct with Diffused Reward: Towards Principled One-step Generator RL","url":"https://arxiv.org/abs/2605.24001","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.24001v2 Announce Type: replace-cross \nAbstract: Recent advances in one-step text-to-image generation have enabled real-time synthesis with remarkable efficiency and quality. Previous reinforcement learning methods for one-step generators combine image-space reward optimization with diffusion noisy-space distribution matching. This paradigm brings challenges due to a mismatch between terminal reward optimization and the underlying generative dynamics. As a result, optimization tends to exploit stochastic degrees of freedom, often improving reward at the expense of image fidelity. To address this issue, we propose Diff-Instruct with Diffused Reward (DIDR), a data-free trajectory-level alignment framework derived from Integral KL minimization. DIDR propagates the RLHF-optimal reward-tilted clean-image distribution across all noise levels along the diffusion trajectory. We show that this objective admits the same minimizer as clean-image RLHF, while naturally inducing the Diffus","title":"Diff-Instruct with Diffused Reward: Towards Principled One-step Generator RL","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-27T04:43:18Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.24001"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:f7d41c6f2b9653e0652ca76524a2ba0ba0d86d4e62a71cb6f0af4a7079c245b468acfbfb44257311e89f791dd11ecbf1bbd276c2b8df79245816f6edb7a54704","signer":"crovia.substrate","subject":{"observed_at":"2026-05-27T04:43:18Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.24001"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"1e91a0cf0f245d4156ba35e43e87a839966c3e2bcdc8919e48d0527e51439c50","leaf_index":154007,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"68d3f3c648fb2666da708962cfe584c37b733a8130558d8496686dbc20ba5ae4","side":"left"},{"sibling":"21e916d26ef680bdfd71879fe0d46c1832697a680b645aaff536aa240f4393b5","side":"left"},{"sibling":"346d1e570d01c2afdc0a9a4309cfb3f8603dc8f687a78eebcfc55c6567b896f7","side":"left"},{"sibling":"48ad545c993e39bc007d9dbb5f9b92c4a7ddcd99da4f7d4174cf4af269174b1f","side":"right"},{"sibling":"bdab384782c8f46c42b2d20c722e44775a1dc82aa539824853fd1584b03c24dd","side":"left"},{"sibling":"3f8a4c1da74f8ace63125682e65daad3f027c83e12545bed4e5e502497a69769","side":"right"},{"sibling":"cc672c1300e7193c9ebe208defb6285b8c64e30c3301a5c7d7a31eb02ac23e5d","side":"right"},{"sibling":"78f1bf1ac0323860fbf9acf5cd7ad4ff9898b7360db2cfe79e3301d2eb634202","side":"left"},{"sibling":"c14a4eb4b07d22a6a83f548cf6c304559dc63f0e53071e550ecc566dbba50b14","side":"left"},{"sibling":"3165125427a29042fc9d02858a59a68858dbdcb2e19d1afa5f6dd6a95cfbce6a","side":"right"},{"sibling":"04b9a68b8ec6fa37251564383c685c23ce69e5e031df4eae69f79a3a334b68bf","side":"right"},{"sibling":"816f233274bb10f5a122aac086a0c8c697b78fec67a4af55190bb596b7506fab","side":"left"},{"sibling":"d415e6939aee710631f5062799379b547d2c3e3d9a68f263bbb5a693285ab2ca","side":"left"},{"sibling":"374c02d15fb12bd356c179c94766043a982052c6132af8bfc15361b431ffa9f7","side":"right"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"990705096edf483cc877217308f731dc42d6f6d99f82880167bbdbbfef32560a","side":"right"},{"sibling":"dd265753d95fa2e2fb4f5768e37fab6f691ccff09ad60d0910ff7dc23bac9226","side":"right"},{"sibling":"d841ad93efda0869e5eb97678f348f03f5caab4353e05ff4bf18f47fb945b822","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":154065,"merkle_root":"4993cfdc172e7880b60667f16789dc2e831ff000f81bb1ecba248e73f1510eca","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260527T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-27T05:37:36Z","sig_algorithm":"ed25519","signature":"76ecf118011540405e96506e6219752df04a2850632f2903dc6f10e08b98bc5a42c8d9e1cb5b7c5bf714479806a403df5f34399afa40c23fbb71493a1f77bd0c","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_343b7fd07e24fb897f5a204d651ff391887ccc94eda88f7e58ed866f8fd16a60"}}