{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OO2D3RD6XHEATH5NY5DU322KDF","short_pith_number":"pith:OO2D3RD6","schema_version":"1.0","canonical_sha256":"73b43dc47eb9c8099fadc7474deb4a195144c4997a545220f336e76bc37dbcc5","source":{"kind":"arxiv","id":"2504.06958","version":5},"attestation_state":"computed","paper":{"title":"VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Reinforcement fine-tuning with rule-based temporal rewards creates a video model with state-of-the-art spatio-temporal perception.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Desen Meng, Limin Wang, Lu Dong, Xiangyu Zeng, Xinhao Li, Yali Wang, Yinan He, Yi Wang, Yu Qiao, Ziang Yan","submitted_at":"2025-04-09T15:09:27Z","abstract_excerpt":"Reinforcement Learning (RL) benefits Large Language Models (LLMs) for complex reasoning. Inspired by this, we explore integrating spatio-temporal specific rewards into Multimodal Large Language Models (MLLMs) to address the unique challenges of video understanding, such as long-range temporal associations. This paper investigates how rule-based rewards, particularly temporal ones, can improve video reasoning and their generalizability. Our study proposes Reinforcement Fine-Tuning (RFT) as a data-efficient method to enhance video reasoning on specific tasks without sacrificing original capabili"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2504.06958","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-09T15:09:27Z","cross_cats_sorted":[],"title_canon_sha256":"ec44830ff7b27ba891b808dca66f374e132a4205f905cac9be95422336277a31","abstract_canon_sha256":"67904bdf7f730bb66fe9d28a566e7454555ba6eba27c2c7f6e7a7cc7701082ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:50.192613Z","signature_b64":"A5+r6tInSXtq85NBbLVUbFHmxKouySz/qahIl5Iu/c/bXKr0SBXLIE28FzdSiyHul5LwBVzGIJguA2eyulxTAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73b43dc47eb9c8099fadc7474deb4a195144c4997a545220f336e76bc37dbcc5","last_reissued_at":"2026-05-17T23:38:50.192174Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:50.192174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Reinforcement fine-tuning with rule-based temporal rewards creates a video model with state-of-the-art spatio-temporal perception.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Desen Meng, Limin Wang, Lu Dong, Xiangyu Zeng, Xinhao Li, Yali Wang, Yinan He, Yi Wang, Yu Qiao, Ziang Yan","submitted_at":"2025-04-09T15:09:27Z","abstract_excerpt":"Reinforcement Learning (RL) benefits Large Language Models (LLMs) for complex reasoning. Inspired by this, we explore integrating spatio-temporal specific rewards into Multimodal Large Language Models (MLLMs) to address the unique challenges of video understanding, such as long-range temporal associations. This paper investigates how rule-based rewards, particularly temporal ones, can improve video reasoning and their generalizability. Our study proposes Reinforcement Fine-Tuning (RFT) as a data-efficient method to enhance video reasoning on specific tasks without sacrificing original capabili"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Through joint RFT on multiple spatio-temporal perception tasks, we developed VideoChat-R1, a powerful Video MLLM. VideoChat-R1 achieves state-of-the-art spatio-temporal perception, demonstrating significant improvements in tasks like temporal grounding (+31.8) and object tracking (+31.2), while also improving general QA benchmarks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That carefully designed rule-based rewards focused on temporal associations will produce generalizable improvements in video reasoning without post-hoc tuning or hidden data selection that inflates the reported deltas.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Reinforcement fine-tuning with temporal rewards produces VideoChat-R1, a video MLLM showing large gains on spatio-temporal perception benchmarks such as +31.8 temporal grounding and +31.2 object tracking.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Reinforcement fine-tuning with rule-based temporal rewards creates a video model with state-of-the-art spatio-temporal perception.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"1e6ba8c30e20bfae80cc583289f8d278c090c847f62641c85a531daaed64360d"},"source":{"id":"2504.06958","kind":"arxiv","version":5},"verdict":{"id":"46600adc-b342-4d2b-93fa-f09c53eabfa1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T20:52:13.629443Z","strongest_claim":"Through joint RFT on multiple spatio-temporal perception tasks, we developed VideoChat-R1, a powerful Video MLLM. VideoChat-R1 achieves state-of-the-art spatio-temporal perception, demonstrating significant improvements in tasks like temporal grounding (+31.8) and object tracking (+31.2), while also improving general QA benchmarks.","one_line_summary":"Reinforcement fine-tuning with temporal rewards produces VideoChat-R1, a video MLLM showing large gains on spatio-temporal perception benchmarks such as +31.8 temporal grounding and +31.2 object tracking.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That carefully designed rule-based rewards focused on temporal associations will produce generalizable improvements in video reasoning without post-hoc tuning or hidden data selection that inflates the reported deltas.","pith_extraction_headline":"Reinforcement fine-tuning with rule-based temporal rewards creates a video model with state-of-the-art spatio-temporal perception."},"references":{"count":42,"sample":[{"doi":"","year":2025,"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","ref_index":1,"cited_arxiv_id":"2502.13923","is_internal_anchor":true},{"doi":"","year":2024,"title":"et al.: FlashVTG: Feature layering and adaptive score handling network for video temporal grounding","work_id":"c5f0f767-bf04-40e1-894c-327d95458eb7","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Boosting the generalization and reasoning of vision language models with curriculum reinforcement learning","work_id":"45c3a58c-d62f-4f0b-84d6-98d7c29563e4","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Open- vlthinker: Complex vision-language reasoning via iterative sft-rl cycles","work_id":"de4c64e1-82b1-4f70-8311-a3539e7bf400","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Video-R1: Reinforcing Video Reasoning in MLLMs","work_id":"0ce88332-564c-4361-8e2a-3850eb1ace9c","ref_index":5,"cited_arxiv_id":"2503.21776","is_internal_anchor":true}],"resolved_work":42,"snapshot_sha256":"5d9ce39e683f9d81d550955ea6fc3b6eb7b34451bcb19dbec72ab096f15e4a6e","internal_anchors":19},"formal_canon":{"evidence_count":2,"snapshot_sha256":"c514041f82825babf008d72b0e9474228497e59a03ee864cd9356814755bc085"},"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":"2504.06958","created_at":"2026-05-17T23:38:50.192240+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.06958v5","created_at":"2026-05-17T23:38:50.192240+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.06958","created_at":"2026-05-17T23:38:50.192240+00:00"},{"alias_kind":"pith_short_12","alias_value":"OO2D3RD6XHEA","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"OO2D3RD6XHEATH5N","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"OO2D3RD6","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":46,"internal_anchor_count":46,"sample":[{"citing_arxiv_id":"2605.06094","citing_title":"VISD: Enhancing Video Reasoning via Structured Self-Distillation","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22907","citing_title":"VideoOdyssey: A Benchmark for Ultra-Long-Context and Omni-Modal Video Understanding","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23216","citing_title":"CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2511.20785","citing_title":"LongVT: Incentivizing \"Thinking with Long Videos\" via Native Tool Calling","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20342","citing_title":"ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21988","citing_title":"Learning Spatiotemporal Sensitivity in Video LLMs via Counterfactual Reinforcement Learning","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21931","citing_title":"EvoVid: Temporal-Centric Self-Evolution for Video Large Language Models","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21954","citing_title":"MLLMs Know When Before Speaking: Revealing and Recovering Temporal Grounding via Attention Cues","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2505.23678","citing_title":"Grounded Reinforcement Learning for Visual Reasoning","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2506.08277","citing_title":"Task-conditioned probing of instruction-tuned multimodal LLMs: Region-specific brain alignment patterns under naturalistic stimuli","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2512.15693","citing_title":"Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20342","citing_title":"ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16079","citing_title":"VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20165","citing_title":"CaMo: Camera Motion Grounded Evaluation and Training for Vision-Language Models","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14692","citing_title":"Chain-of-Glimpse: Search-Guided Progressive Object-Grounded Reasoning for Video Understanding","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2505.20715","citing_title":"MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2509.15602","citing_title":"TennisTV: Do Multimodal Large Language Models Understand Tennis Rallies?","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2509.08827","citing_title":"A Survey of Reinforcement Learning for Large Reasoning Models","ref_index":288,"is_internal_anchor":true},{"citing_arxiv_id":"2511.11113","citing_title":"VIDEOP2R: Video Understanding from Perception to Reasoning","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2511.18373","citing_title":"MASS: Motion-Aware Spatial-Temporal Grounding for Physics Reasoning and Comprehension in Vision-Language Models","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2505.21374","citing_title":"Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2512.03963","citing_title":"TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2512.03043","citing_title":"OneThinker: All-in-one Reasoning Model for Image and Video","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2512.16918","citing_title":"AdaTooler-V: Adaptive Tool-Use for Images and Videos","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2602.00181","citing_title":"CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoning","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OO2D3RD6XHEATH5NY5DU322KDF","json":"https://pith.science/pith/OO2D3RD6XHEATH5NY5DU322KDF.json","graph_json":"https://pith.science/api/pith-number/OO2D3RD6XHEATH5NY5DU322KDF/graph.json","events_json":"https://pith.science/api/pith-number/OO2D3RD6XHEATH5NY5DU322KDF/events.json","paper":"https://pith.science/paper/OO2D3RD6"},"agent_actions":{"view_html":"https://pith.science/pith/OO2D3RD6XHEATH5NY5DU322KDF","download_json":"https://pith.science/pith/OO2D3RD6XHEATH5NY5DU322KDF.json","view_paper":"https://pith.science/paper/OO2D3RD6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.06958&json=true","fetch_graph":"https://pith.science/api/pith-number/OO2D3RD6XHEATH5NY5DU322KDF/graph.json","fetch_events":"https://pith.science/api/pith-number/OO2D3RD6XHEATH5NY5DU322KDF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OO2D3RD6XHEATH5NY5DU322KDF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OO2D3RD6XHEATH5NY5DU322KDF/action/storage_attestation","attest_author":"https://pith.science/pith/OO2D3RD6XHEATH5NY5DU322KDF/action/author_attestation","sign_citation":"https://pith.science/pith/OO2D3RD6XHEATH5NY5DU322KDF/action/citation_signature","submit_replication":"https://pith.science/pith/OO2D3RD6XHEATH5NY5DU322KDF/action/replication_record"}},"created_at":"2026-05-17T23:38:50.192240+00:00","updated_at":"2026-05-17T23:38:50.192240+00:00"}