Papers › A Simple LLM Framework for Long-Range Video Question-Answering

A Simple LLM Framework for Long-Range Video Question-Answering

28 Dec 2023arXiv:2312.17235archive 2025-07-28

Ce Zhang, Taixi Lu, Md Mohaiminul Islam, Ziyang Wang, Shoubin Yu, Mohit Bansal, Gedas Bertasius

We present LLoVi, a language-based framework for long-range video question-answering (LVQA). Unlike prior long-range video understanding methods, which are often costly and require specialized long-range video modeling design (e.g., memory queues, state-space layers, etc.), our approach uses a frame/clip-level visual captioner (e.g., BLIP2, LaViLa, LLaVA) coupled with a Large Language Model (GPT-3.5, GPT-4) leading to a simple yet surprisingly effective LVQA framework. Specifically, we decompose short and long-range modeling aspects of LVQA into two stages. First, we use a short-term visual captioner to generate textual descriptions of short video clips (0.5-8s in length) densely sampled from a long input video. Afterward, an LLM aggregates the densely extracted short-term captions to perform long-range temporal reasoning needed to understand the whole video and answer a question. To analyze what makes our simple framework so effective, we thoroughly evaluate various components of our system. Our empirical analysis reveals that the choice of the visual captioner and LLM is critical for good LVQA performance. Furthermore, we show that a specialized prompt that asks the LLM first to summarize the noisy short-term visual captions and then answer a given input question leads to a significant LVQA performance boost. On EgoSchema, which is best known as a very long-form video question-answering benchmark, our method achieves 50.3% accuracy, outperforming the previous best-performing approach by 18.1% (absolute gain). In addition, our approach outperforms the previous state-of-the-art by 4.1% and 3.1% on NeXT-QA and IntentQA. We also extend LLoVi to grounded LVQA and show that it outperforms all prior methods on the NeXT-GQA dataset. We will release our code at https://github.com/CeeZh/LLoVi.

PaperPDFCodeCode Syntology ran

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 6 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 6 samples from 1 repository, 6 ran (3 with no instrument failure; 3 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ceezh/llovi officialmentioned in papermentioned on GitHubpytorchMITSyntology: 6 samples, 6 ran (3 instrument-failed) · 0 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

6 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 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.

2ran · honoured contract
3ran · our draft was wrong
1ran

Licence: 0 of the 6 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 ceezh/llovi. “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.

ceezh/llovi official repository 6 samples, 6 ran (3 instrument-failed) · 0 unverified
build_fewshot_examples util.py ran fingerprinted MIT (permissive) · a16cc02636239688 · report fixture: signature qa_path:str/0/str, data_path:str/0/str · returned str · level recorded 2026-09-24
first_char_as_answer in 5 papers prompts.py ran · honoured contract fingerprinted MIT (permissive) · 4c7e348b2c9eac20 · report fixture: signature res:str/0/str · returned int · level recorded 2026-09-24
first_char_as_answer_raw prompts.py ran · our draft was wrong fingerprinted MIT (permissive) · 544bdde34ff89202 · report fixture: signature res:str/0/str · returned str · level recorded 2026-09-24
identity in 174 papers
census: 11 implementations from 39 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
prompts.py ran · honoured contract fingerprinted MIT (permissive) · 036725c05a3d96f8 · report fixture: signature res:Tensor/2/float · returned Tensor · level recorded 2026-09-24
load_json in 344 papers util.py ran · our draft was wrong MIT (permissive) · 658682feda4928a2 · report fixture: signature fn:str/0/str · returned dict · level recorded 2026-09-24
load_pkl in 46 papers util.py ran · our draft was wrong MIT (permissive) · 8080055de6293a6b · report fixture: signature fn:str/0/str · returned dict · level recorded 2026-09-24

Tasks

Language ModellingLarge Language ModelLong-range modelingQuestion AnsweringVideo Question AnsweringVideo UnderstandingZero-Shot Video Question Answer

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Zero-Shot Video Question Answer EgoSchema (fullset) LLoVi (GPT-3.5) Accuracy 50.3 #17 of 29 Archive leaderboard report
Zero-Shot Video Question Answer EgoSchema (fullset) LLoVi (7B) Accuracy 33.5 #23 of 29 Archive leaderboard report
Zero-Shot Video Question Answer EgoSchema (subset) LLoVi (GPT-3.5) Accuracy 57.6 #10 of 14 Archive leaderboard report
Zero-Shot Video Question Answer EgoSchema (subset) LLoVi (7B) Accuracy 50.8 #11 of 14 Archive leaderboard report
Zero-Shot Video Question Answer IntentQA LLoVi (GPT-4) Accuracy 64.0 #7 of 13 Archive leaderboard report
Zero-Shot Video Question Answer IntentQA LLoVi (7B) Accuracy 53.6 #11 of 13 Archive leaderboard report
Zero-Shot Video Question Answer NExT-GQA LLoVi (GPT-4) Acc@GQA 26.8 #4 of 9 Archive leaderboard report
Zero-Shot Video Question Answer NExT-GQA LLoVi (7B) Acc@GQA 11.2 #8 of 9 Archive leaderboard report
Zero-Shot Video Question Answer NExT-QA LLoVi (GPT-4) Accuracy 67.7 #14 of 27 Archive leaderboard report
Zero-Shot Video Question Answer NExT-QA LLoVi (7B) Accuracy 54.3 #25 of 27 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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