Papers › Scaling RL to Long Videos
Scaling RL to Long Videos
Yukang Chen, Wei Huang, Baifeng Shi, Qinghao Hu, Hanrong Ye, Ligeng Zhu, Zhijian Liu, Pavlo Molchanov, Jan Kautz, Xiaojuan Qi, Sifei Liu, Hongxu Yin, Yao Lu, Song Han
We introduce a full-stack framework that scales up reasoning in vision-language models (VLMs) to long videos, leveraging reinforcement learning. We address the unique challenges of long video reasoning by integrating three critical components: (1) a large-scale dataset, LongVideo-Reason, comprising 52K long video QA pairs with high-quality reasoning annotations across diverse domains such as sports, games, and vlogs; (2) a two-stage training pipeline that extends VLMs with chain-of-thought supervised fine-tuning (CoT-SFT) and reinforcement learning (RL); and (3) a training infrastructure for long video RL, named Multi-modal Reinforcement Sequence Parallelism (MR-SP), which incorporates sequence parallelism and a vLLM-based engine tailored for long video, using cached video embeddings for efficient rollout and prefilling. In experiments, LongVILA-R1-7B achieves strong performance on long video QA benchmarks such as VideoMME. It also outperforms Video-R1-7B and even matches Gemini-1.5-Pro across temporal reasoning, goal and purpose reasoning, spatial reasoning, and plot reasoning on our LongVideo-Reason-eval benchmark. Notably, our MR-SP system achieves up to 2.1x speedup on long video RL training. LongVILA-R1 demonstrates consistent performance gains as the number of input video frames scales. LongVILA-R1 marks a firm step towards long video reasoning in VLMs. In addition, we release our training system for public availability that supports RL training on various modalities (video, text, and audio), various models (VILA and Qwen series), and even image and video generation models. On a single A100 node (8 GPUs), it supports RL training on hour-long videos (e.g., 3,600 frames / around 256k tokens).
In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2507.07966")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2507.07966", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2507.07966")
Code
Syntology 24 code samples harvested from 2 repositories linked to this paper: 18 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 11 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 10 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 6 samples from 1 repository, 4 ran (1 with no instrument failure; 3 where Syntology's instrument failed); found in paper text by Syntology: 18 samples from 1 repository, 14 ran (6 with no instrument failure; 8 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 18 samples that ran have no recorded date.
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
24 samples harvested: 18 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 11 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 1 of the 24 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.
Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.
A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.
9ab20c0df51491c6 · report
fixture: returned SeqAllToAll · level recorded 2026-09-22 bc1859396d0efde4 · report
fixture: signature x:Tensor/3/float, dim:int/0/int, padding_size:int/0/int · returned Tensor · level recorded 2026-09-22 c370c3e6e37ff52d · report
fixture: signature x:Tensor/4/float, seq_dim:int/0/int, head_dim:int/0/int, unpadded_dim_size:int/0/int, group:NoneType/0/? · returned Tensor · level recorded 2026-09-22 5bc06ef1058a26db · report
fixture: signature group:callable/0/? · returned Mock · level recorded 2026-09-22 50fceeb8e224ae4b · report
c3db68c3c1890a1b · report
8dd6b65f72c07727 · report
fixture: signature model_path:str/0/str · returned bool · level recorded, date not recorded defc3c221f010765 · report
fixture: signature folder:str/0/str · returned dict · level recorded 2026-09-25 b0bfe8a6b7ced02a · report
fixture: returned tuple · level recorded 2026-09-25 758c7f607efffb52 · report
fixture: signature token_level_rewards:Tensor/2/float, response_mask:Tensor/2/float, index:Tensor/1/int, eps:float/0/float · returned tuple · level recorded 2026-09-25 6e021f58ff92252d · report
fixture: signature caption_dict:list/1/dict · returned str · level recorded 2026-09-25 452188d5e8665c1e · report
fixture: signature token_indices:Tensor/1/int, tokens_per_chunk:int/0/int, remove_index:int/0/int · returned list · level recorded 2026-09-25 7633fd09bcf8972a · report
fixture: signature algorithm_config:AlgorithmConfig/0/? · returned AdaptiveKLController · level recorded 2026-09-26 2b24afde621bf5ff · report
fixture: signature start_idx:int/0/int, vision_idx:int/0/int, spatial_merge_size:int/0/int, t_index:list/1/int, grid_hs:list/1/int, grid_ws:list/1/int · returned Tensor · level recorded 2026-09-25 554c742ab091b991 · report
fixture: signature model_path:str/0/str · returned str · level recorded, date not recorded 34e4399c3e46211a · report
fixture: signature video_files:dict/0/?, input_folder:str/0/str · returned list · level recorded 2026-09-25 d9f1e79118788b85 · report
fixture: signature reasoning_text:str/0/str · returned dict · level recorded 2026-09-25 4049cf08f994464e · report
fixture: signature query:Tensor/3/float, key:Tensor/3/float, value:Tensor/3/float, position_ids:Tensor/1/int · returned tuple · level recorded 2026-09-24 ad658a1d6fe829ba · report
fixture: signature tensor_dict1:TensorDict/1/float, tensor_dict2:TensorDict/1/float · returned TensorDict · level recorded 2026-09-26 a91c18341292d50e · report
fixture: signature data:DataProto/0/?, pad_size:int/0/int · returned DataProto · level recorded 2026-09-24 2058875a75c3ff14 · report
c02118fc07296220 · report
867399f13a93e09a · report
c7a1430e0e702826 · report
Method as code Syntology
What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.
1 assembly on this paper: 1 harvested, 0 generated.
harvested Assembly for Multi-modal Reinforcement Sequence Parallelism (MR-SP) (graph method: Multi-modal Reinforcement Sequence Parallelism (MR-SP)). 6 bricks; individually on a fixture: 4 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.
- gather_seq_scatter_heads entry · level 1 · ran; the contract check could not run (RAISES) ·
c370c3e6e37ff52d - SeqAllToAll helper · level 1 · ran ·
9ab20c0df51491c6 - _unpad_tensor helper · level 1 · ran · our draft was wrong ·
bc1859396d0efde4 - get_ulysses_sequence_parallel_group helper · level 0 · unverified ·
c3db68c3c1890a1b - get_ulysses_sequence_parallel_world_size helper · level 1 · ran · our draft was wrong ·
5bc06ef1058a26db - all_to_all_tensor helper · level 0 · unverified ·
50fceeb8e224ae4b
Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2507.07966") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections