{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KA2VX6DZAEGKYDLSJYYE4CTAEP","short_pith_number":"pith:KA2VX6DZ","schema_version":"1.0","canonical_sha256":"50355bf879010cac0d724e304e0a6023c4e5f4540537dc5d3350051a7c8bd64e","source":{"kind":"arxiv","id":"2509.06932","version":2},"attestation_state":"computed","paper":{"title":"LLaDA-VLA: Vision Language Diffusion Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Hebei Li, Kefan Gu, Tiancai Wang, Xiaoyan Sun, Yucheng Zhao, Yuqing Wen","submitted_at":"2025-09-08T17:45:40Z","abstract_excerpt":"The rapid progress of auto-regressive vision-language models (VLMs) has inspired growing interest in vision-language-action models (VLA) for robotic manipulation. Recently, masked diffusion models, a paradigm distinct from autoregressive models, have begun to demonstrate competitive performance in text generation and multimodal applications, leading to the development of a series of diffusion-based VLMs (d-VLMs). However, leveraging such models for robot policy learning remains largely unexplored. In this work, we present LLaDA-VLA, the first Vision-Language-Diffusion-Action model built upon p"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2509.06932","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-09-08T17:45:40Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e99a280ae5afc020f1c12a37dc3eaa89a84cad1c10a5d4f1f8cdc9b72468a30a","abstract_canon_sha256":"08056c0c8e2f8fbef47aa7f02bb74912f546096e20d08cdfa71065a928fd4fa2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:08:08.458390Z","signature_b64":"xQg2XJnyh4Ui7braXlTaYx2c4OoDbc5iWZummNof+raGxLucVw840HeZaxEaiVVgCXQCNkKh3WGoV7hlltl0BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50355bf879010cac0d724e304e0a6023c4e5f4540537dc5d3350051a7c8bd64e","last_reissued_at":"2026-07-05T12:08:08.457795Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:08:08.457795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLaDA-VLA: Vision Language Diffusion Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Hebei Li, Kefan Gu, Tiancai Wang, Xiaoyan Sun, Yucheng Zhao, Yuqing Wen","submitted_at":"2025-09-08T17:45:40Z","abstract_excerpt":"The rapid progress of auto-regressive vision-language models (VLMs) has inspired growing interest in vision-language-action models (VLA) for robotic manipulation. Recently, masked diffusion models, a paradigm distinct from autoregressive models, have begun to demonstrate competitive performance in text generation and multimodal applications, leading to the development of a series of diffusion-based VLMs (d-VLMs). However, leveraging such models for robot policy learning remains largely unexplored. In this work, we present LLaDA-VLA, the first Vision-Language-Diffusion-Action model built upon p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06932","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2509.06932/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2509.06932","created_at":"2026-07-05T12:08:08.457859+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.06932v2","created_at":"2026-07-05T12:08:08.457859+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06932","created_at":"2026-07-05T12:08:08.457859+00:00"},{"alias_kind":"pith_short_12","alias_value":"KA2VX6DZAEGK","created_at":"2026-07-05T12:08:08.457859+00:00"},{"alias_kind":"pith_short_16","alias_value":"KA2VX6DZAEGKYDLS","created_at":"2026-07-05T12:08:08.457859+00:00"},{"alias_kind":"pith_short_8","alias_value":"KA2VX6DZ","created_at":"2026-07-05T12:08:08.457859+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07895","citing_title":"TBD-VLA: Temporal Block Diffusion Vision Language Action Model","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25050","citing_title":"DiscreteRTC: Discrete Diffusion Policies are Natural Asynchronous Executors","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2602.12978","citing_title":"Learning Native Continuation for Action Chunking Flow Policies","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19282","citing_title":"Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08302","citing_title":"DMax: Aggressive Parallel Decoding for dLLMs","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2511.14148","citing_title":"AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Models","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13382","citing_title":"BlockVLA: Accelerating Autoregressive VLA via Block Diffusion Finetuning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04647","citing_title":"ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving","ref_index":124,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25050","citing_title":"DiscreteRTC: Discrete Diffusion Policies are Natural Asynchronous Executors","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22152","citing_title":"dWorldEval: Scalable Robotic Policy Evaluation via Discrete Diffusion World Model","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04647","citing_title":"ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving","ref_index":124,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08302","citing_title":"DMax: Aggressive Parallel Decoding for dLLMs","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07381","citing_title":"Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KA2VX6DZAEGKYDLSJYYE4CTAEP","json":"https://pith.science/pith/KA2VX6DZAEGKYDLSJYYE4CTAEP.json","graph_json":"https://pith.science/api/pith-number/KA2VX6DZAEGKYDLSJYYE4CTAEP/graph.json","events_json":"https://pith.science/api/pith-number/KA2VX6DZAEGKYDLSJYYE4CTAEP/events.json","paper":"https://pith.science/paper/KA2VX6DZ"},"agent_actions":{"view_html":"https://pith.science/pith/KA2VX6DZAEGKYDLSJYYE4CTAEP","download_json":"https://pith.science/pith/KA2VX6DZAEGKYDLSJYYE4CTAEP.json","view_paper":"https://pith.science/paper/KA2VX6DZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.06932&json=true","fetch_graph":"https://pith.science/api/pith-number/KA2VX6DZAEGKYDLSJYYE4CTAEP/graph.json","fetch_events":"https://pith.science/api/pith-number/KA2VX6DZAEGKYDLSJYYE4CTAEP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KA2VX6DZAEGKYDLSJYYE4CTAEP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KA2VX6DZAEGKYDLSJYYE4CTAEP/action/storage_attestation","attest_author":"https://pith.science/pith/KA2VX6DZAEGKYDLSJYYE4CTAEP/action/author_attestation","sign_citation":"https://pith.science/pith/KA2VX6DZAEGKYDLSJYYE4CTAEP/action/citation_signature","submit_replication":"https://pith.science/pith/KA2VX6DZAEGKYDLSJYYE4CTAEP/action/replication_record"}},"created_at":"2026-07-05T12:08:08.457859+00:00","updated_at":"2026-07-05T12:08:08.457859+00:00"}