{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RW52MPL5ED325SK2FHLZJD6OE5","short_pith_number":"pith:RW52MPL5","schema_version":"1.0","canonical_sha256":"8dbba63d7d20f7aec95a29d7948fce2766d8b2f7d677acdc873e3e84a6593b53","source":{"kind":"arxiv","id":"2511.16672","version":4},"attestation_state":"computed","paper":{"title":"EvoLMM: Self-Evolving Large Multimodal Models with Continuous Rewards","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdelrahman Shaker, Fahad Khan, Hisham Cholakkal, Omkar Thawakar, Rao Muhammad Anwer, Ritesh Thawkar, Salman Khan, Shravan Venkatraman","submitted_at":"2025-11-20T18:59:54Z","abstract_excerpt":"Recent advances in large multimodal models (LMMs) have enabled impressive reasoning and perception abilities, yet most existing training pipelines still depend on human-curated data or externally verified reward models, limiting their autonomy and scalability. In this work, we strive to improve LMM reasoning capabilities in a purely unsupervised fashion (without any annotated data or reward distillation). To this end, we propose a self-evolving framework, named EvoLMM, that instantiates two cooperative agents from a single backbone model: a Proposer, which generates diverse, image-grounded que"},"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":"2511.16672","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-20T18:59:54Z","cross_cats_sorted":[],"title_canon_sha256":"34a3166dfc4c413fdbbe12dee39bbca1c9e6b8f39333b28521225a25a631476d","abstract_canon_sha256":"d442c833a0705db3f13df83c63e4082c0906423831841a94912c45d5e3130fdc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:22.201704Z","signature_b64":"jygJ45hV0N1R9kIm/R241kkjucY64kd/WlwRaKFM40FbpwrTXSsWEMFNeEaL0d4Oed9PgY+oxxbrDmLnpZJ7Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dbba63d7d20f7aec95a29d7948fce2766d8b2f7d677acdc873e3e84a6593b53","last_reissued_at":"2026-06-11T01:09:22.200556Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:22.200556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EvoLMM: Self-Evolving Large Multimodal Models with Continuous Rewards","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdelrahman Shaker, Fahad Khan, Hisham Cholakkal, Omkar Thawakar, Rao Muhammad Anwer, Ritesh Thawkar, Salman Khan, Shravan Venkatraman","submitted_at":"2025-11-20T18:59:54Z","abstract_excerpt":"Recent advances in large multimodal models (LMMs) have enabled impressive reasoning and perception abilities, yet most existing training pipelines still depend on human-curated data or externally verified reward models, limiting their autonomy and scalability. In this work, we strive to improve LMM reasoning capabilities in a purely unsupervised fashion (without any annotated data or reward distillation). To this end, we propose a self-evolving framework, named EvoLMM, that instantiates two cooperative agents from a single backbone model: a Proposer, which generates diverse, image-grounded que"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.16672","kind":"arxiv","version":4},"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/2511.16672/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":"2511.16672","created_at":"2026-06-11T01:09:22.200724+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.16672v4","created_at":"2026-06-11T01:09:22.200724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.16672","created_at":"2026-06-11T01:09:22.200724+00:00"},{"alias_kind":"pith_short_12","alias_value":"RW52MPL5ED32","created_at":"2026-06-11T01:09:22.200724+00:00"},{"alias_kind":"pith_short_16","alias_value":"RW52MPL5ED325SK2","created_at":"2026-06-11T01:09:22.200724+00:00"},{"alias_kind":"pith_short_8","alias_value":"RW52MPL5","created_at":"2026-06-11T01:09:22.200724+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"2605.21931","citing_title":"EvoVid: Temporal-Centric Self-Evolution for Video Large Language Models","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20914","citing_title":"RISE: Reliable Improvement in Self-Evolving Vision-Language Models","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24919","citing_title":"Agentic AI for Remote Sensing: Technical Challenges and Research Directions","ref_index":114,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13803","citing_title":"EvoGround: Self-Evolving Video Agents for Video Temporal Grounding","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24919","citing_title":"Agentic AI for Remote Sensing: Technical Challenges and Research Directions","ref_index":114,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18320","citing_title":"EVE: Verifiable Self-Evolution of MLLMs via Executable Visual Transformations","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RW52MPL5ED325SK2FHLZJD6OE5","json":"https://pith.science/pith/RW52MPL5ED325SK2FHLZJD6OE5.json","graph_json":"https://pith.science/api/pith-number/RW52MPL5ED325SK2FHLZJD6OE5/graph.json","events_json":"https://pith.science/api/pith-number/RW52MPL5ED325SK2FHLZJD6OE5/events.json","paper":"https://pith.science/paper/RW52MPL5"},"agent_actions":{"view_html":"https://pith.science/pith/RW52MPL5ED325SK2FHLZJD6OE5","download_json":"https://pith.science/pith/RW52MPL5ED325SK2FHLZJD6OE5.json","view_paper":"https://pith.science/paper/RW52MPL5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.16672&json=true","fetch_graph":"https://pith.science/api/pith-number/RW52MPL5ED325SK2FHLZJD6OE5/graph.json","fetch_events":"https://pith.science/api/pith-number/RW52MPL5ED325SK2FHLZJD6OE5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RW52MPL5ED325SK2FHLZJD6OE5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RW52MPL5ED325SK2FHLZJD6OE5/action/storage_attestation","attest_author":"https://pith.science/pith/RW52MPL5ED325SK2FHLZJD6OE5/action/author_attestation","sign_citation":"https://pith.science/pith/RW52MPL5ED325SK2FHLZJD6OE5/action/citation_signature","submit_replication":"https://pith.science/pith/RW52MPL5ED325SK2FHLZJD6OE5/action/replication_record"}},"created_at":"2026-06-11T01:09:22.200724+00:00","updated_at":"2026-06-11T01:09:22.200724+00:00"}