Papers › VLog: Video-Language Models by Generative Retrieval of Narration Vocabulary

VLog: Video-Language Models by Generative Retrieval of Narration Vocabulary

12 Mar 2025CVPR 2025 1arXiv:2503.09402archive 2025-07-28

Kevin Qinghong Lin, Mike Zheng Shou

Human daily activities can be concisely narrated as sequences of routine events (e.g., turning off an alarm) in video streams, forming an event vocabulary. Motivated by this, we introduce VLog, a novel video understanding framework that define video narrations as vocabulary, going beyond the typical subword vocabularies in existing generative video-language models. Built on the lightweight language model GPT-2, VLog feature three key innovations: (i) A generative retrieval model, marrying language model's complex reasoning capabilities with contrastive retrieval's efficient similarity search. (ii) A hierarchical vocabulary derived from large-scale video narrations using our narration pair encoding algorithm, enabling efficient indexing of specific events (e.g., cutting a tomato) by identifying broader scenarios (e.g., kitchen) with expressive postfixes (e.g., by the left hand). (iii) A vocabulary update strategy leveraging generative models to extend the vocabulary for novel events encountered during inference. To validate our approach, we introduce VidCap-Eval, a development set requiring concise narrations with reasoning relationships (e.g., before and after). Experiments on EgoSchema, COIN, and HiREST further demonstrate the effectiveness of VLog, highlighting its ability to generate concise, contextually accurate, and efficient narrations, offering a novel perspective on video understanding. Codes are released at https://github.com/showlab/VLog.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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):

Code

Syntology 10 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 1 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: 10 samples from 1 repository, 7 ran (5 with no instrument failure; 2 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

showlab/vlog officialmentioned in papermentioned on GitHubpytorchSyntology: 10 samples, 7 ran (2 instrument-failed) · 3 unverified report

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

10 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
1ran; the contract check could not run
5ran
3unverified

Licence: 10 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from showlab/vlog. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

showlab/vlog official repository 10 samples, 7 ran (2 instrument-failed) · 3 unverified
DropPath in 75 papers
census: 17 implementations from 17 papers, 8 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 3, kind float, dtype float32
VLog/model/models.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · eb3438f3ff649ddf · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
PositionEmbeddingSine in 21 papers
census: 6 implementations from 6 papers, 3 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 3 of 3, arg 1: rank 3, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
VLog/model/models.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 77fa2643a3a1c67a · report fixture: signature x:Tensor/3/float, mask:Tensor/2/float · returned Tensor · level recorded 2026-09-22
Transformer in 173 papers VLog/model/models.py ran fingerprinted no licence file found · pointer only · 3b38513f46a92d3f · report fixture: signature src:Tensor/3/float, mask:Tensor/2/bool, pos_embed:Tensor/3/float · returned Tensor · level recorded 2026-09-24
TransformerEncoder in 96 papers VLog/model/models.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · b2e7f0187d163a01 · report fixture: signature src:Tensor/3/float, mask:NoneType/0/?, src_key_padding_mask:NoneType/0/?, pos:Tensor/3/float · returned Tensor · level recorded 2026-09-22
TransformerEncoderLayer in 90 papers VLog/model/models.py ran · metamorphic tier: invariant no licence file found · pointer only · f33ffe92f2473798 · report fixture: signature src:Tensor/3/float, src_mask:NoneType/0/?, src_key_padding_mask:NoneType/0/?, pos:Tensor/3/float · returned Tensor · level recorded 2026-09-22
build_position_encoding in 42 papers VLog/model/models.py ran · our draft was wrong no licence file found · pointer only · 020b7f70a236fb97 · report fixture: signature hidden_dim:int/0/int · returned PositionEmbeddingSine · level recorded 2026-09-22
drop_path in 325 papers
census: 27 implementations from 61 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 2, kind float, dtype float32
VLog/model/models.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 10e67144852e5fce · report fixture: signature x:Tensor/2/float, drop_prob:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22
ModelArgs in 13 papers VLog/model/models.py unverified no licence file found · pointer only · 35622089c9d95b72 · report
VLog VLog/model/models.py unverified no licence file found · pointer only · ce55dd9224e4a28a · report
build_transformer in 62 papers VLog/model/models.py unverified no licence file found · pointer only · c8d145f15e26a93d · 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 VLog (graph method: VLog). 12 bricks; individually on a fixture: 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. VLog entry · level 0 · unverified · ce55dd9224e4a28a
  2. ModelArgs model · level 0 · unverified · 35622089c9d95b72
  3. build_position_encoding helper · level 1 · ran · our draft was wrong · 020b7f70a236fb97
  4. build_transformer helper · level 0 · unverified · c8d145f15e26a93d
  5. PositionEmbeddingSine helper · level 1 · ran · 77fa2643a3a1c67a
  6. Transformer model · level 1 · ran · 3b38513f46a92d3f
  7. TransformerEncoder helper · level 1 · ran · b2e7f0187d163a01
  8. TransformerEncoderLayer helper · level 1 · ran · f33ffe92f2473798
  9. _get_clones helper · level 1 · ran · our draft was wrong · a8f1bbeb369e1829
  10. DropPath helper · level 1 · ran · eb3438f3ff649ddf
  11. _get_activation_fn helper · level 1 · ran · our draft was wrong · 0bb264f52e707e08
  12. drop_path helper · level 1 · ran; the contract check could not run (RAISES) · 10e67144852e5fce

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="2503.09402") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

RetrievalVideo Understanding

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBPECosine AnnealingDense ConnectionsDiscriminative Fine-TuningDropoutGPT-2Layer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionResidual ConnectionSETSoftmaxWeight Decay

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