Papers › PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance

PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance

4 Nov 2024arXiv:2411.02327archive 2025-07-28

Ruyang Liu, Haoran Tang, Haibo Liu, Yixiao Ge, Ying Shan, Chen Li, Jiankun Yang

The past year has witnessed the significant advancement of video-based large language models. However, the challenge of developing a unified model for both short and long video understanding remains unresolved. Most existing video LLMs cannot handle hour-long videos, while methods custom for long videos tend to be ineffective for shorter videos and images. In this paper, we identify the key issue as the redundant content in videos. To address this, we propose a novel pooling strategy that simultaneously achieves token compression and instruction-aware visual feature aggregation. Our model is termed Prompt-guided Pooling LLaVA, or PPLLaVA for short. Specifically, PPLLaVA consists of three core components: the CLIP-based visual-prompt alignment that extracts visual information relevant to the user's instructions, the prompt-guided pooling that compresses the visual sequence to arbitrary scales using convolution-style pooling, and the clip context extension designed for lengthy prompt common in visual dialogue. Moreover, our codebase also integrates the most advanced video Direct Preference Optimization (DPO) and visual interleave training. Extensive experiments have validated the performance of our model. With superior throughput and only 1024 visual context, PPLLaVA achieves better results on image benchmarks as a video LLM, while achieving state-of-the-art performance across various video benchmarks, excelling in tasks ranging from caption generation to multiple-choice questions, and handling video lengths from seconds to hours. Codes have been available at https://github.com/farewellthree/PPLLaVA.

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 9 code samples: 6 from 1 repository linked to this paper, 3 identical to code harvested from another paper's repository. Across all 9: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 2 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 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 (4 with no instrument failure; 0 where Syntology's instrument failed); 3 identical to code first harvested elsewhere. 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 5 samples that ran have no recorded date.

farewellthree/ppllava officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 6 samples, 4 ran (0 instrument-failed) · 2 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

9 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 2 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 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 · violated contract
1ran; the contract check could not run
2ran
4unverified

Licence: 3 of the 9 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 farewellthree/ppllava. 3 samples are listed last, in a group without a repository. “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.

farewellthree/ppllava official repository 6 samples, 4 ran (0 instrument-failed) · 2 unverified
disabled_train in 172 papers ppllava/models/blip2.py ran · violated contract Apache-2.0 (permissive) · 4cb732f513d69dfd · report fixture: signature self:callable/0/?, mode:bool/0/bool · returned SimpleModel · level recorded, date not recorded
drop_path in 325 papers
census: 27 implementations from 61 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
ppllava/models/clip_btadapter.py ran Apache-2.0 (permissive) · 9a83c0663b6afcd4 · report fixture: signature x:Tensor/4/float, drop_prob:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-25
is_transformers_greater_than in 9 papers ppllava/import_utils.py ran · violated contract Apache-2.0 (permissive) · f4334934ee795269 · report fixture: signature version:str/0/str · returned bool · level recorded 2026-09-25
tile in 109 papers
census: 5 implementations from 7 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
ppllava/models/base_model.py ran fingerprinted Apache-2.0 (permissive) · ded9fb4cd3944865 · report fixture: signature x:Tensor/2/float, dim:int/0/int, n_tile:int/0/int · returned Tensor · level recorded 2026-09-25
all_gather_with_grad in 93 papers ppllava/models/base_model.py unverified Apache-2.0 (permissive) · 0ec9fc2025c16f65 · report
create_eva_vit_g in 13 papers ppllava/models/eva_vit.py unverified Apache-2.0 (permissive) · e3d9aac39bcef7a7 · report
Repository not located 3 samples, 1 ran (1 instrument-failed) · 2 unverified
3 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
split_to_even_chunks in 41 papers repository not located ran; the contract check could not run (RAISES) · metamorphic tier: well formed licence of this copy not recorded · 10893c4608c08075 · report fixture: signature indices:list/1/int, lengths:dict/0/?, num_chunks:int/0/int · returned list · level recorded, date not recorded
get_mm_adapter_state_maybe_zero_3 in 44 papers repository not located unverified licence of this copy not recorded · bb35e3ac741bb2c9 · report
maybe_zero_3 in 74 papers repository not located unverified licence of this copy not recorded · 735025744c1ab0cf · report

Tasks

Caption GenerationMultiple-choiceVideo Question AnsweringVideo UnderstandingVideo-based Generative Performance BenchmarkingVideo-based Generative Performance Benchmarking (Consistency)Video-based Generative Performance Benchmarking (Contextual Understanding)Video-based Generative Performance Benchmarking (Correctness of Information)Video-based Generative Performance Benchmarking (Detail Orientation))Video-based Generative Performance Benchmarking (Temporal Understanding)Zero-Shot Video Question Answer

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Question Answering MVBench PPLLaVA (7b) Avg. 59.2 #9 of 22 Archive leaderboard report
Video-based Generative Performance Benchmarking VideoInstruct PPLLaVA-7B-dpo Consistency 3.81 #1 of 23 Archive leaderboard report
Video-based Generative Performance Benchmarking VideoInstruct PPLLaVA-7B-dpo Contextual Understanding 4.21 #1 of 23 Archive leaderboard report
Video-based Generative Performance Benchmarking VideoInstruct PPLLaVA-7B-dpo Correctness of Information 3.85 #1 of 23 Archive leaderboard report
Video-based Generative Performance Benchmarking VideoInstruct PPLLaVA-7B-dpo Detail Orientation 3.56 #1 of 23 Archive leaderboard report
Video-based Generative Performance Benchmarking VideoInstruct PPLLaVA-7B-dpo Temporal Understanding 3.21 #1 of 23 Archive leaderboard report
Video-based Generative Performance Benchmarking VideoInstruct PPLLaVA-7B-dpo mean 3.73 #1 of 23 Archive leaderboard report
Video-based Generative Performance Benchmarking VideoInstruct PPLLaVA-7B Consistency 3.20 #5 of 23 Archive leaderboard report
Video-based Generative Performance Benchmarking VideoInstruct PPLLaVA-7B Contextual Understanding 3.88 #5 of 23 Archive leaderboard report
Video-based Generative Performance Benchmarking VideoInstruct PPLLaVA-7B Correctness of Information 3.32 #5 of 23 Archive leaderboard report
Video-based Generative Performance Benchmarking VideoInstruct PPLLaVA-7B Detail Orientation 3.20 #5 of 23 Archive leaderboard report
Video-based Generative Performance Benchmarking VideoInstruct PPLLaVA-7B Temporal Understanding 3.0 #5 of 23 Archive leaderboard report
Video-based Generative Performance Benchmarking VideoInstruct PPLLaVA-7B mean 3.32 #5 of 23 Archive leaderboard report
Video-based Generative Performance Benchmarking (Consistency) VideoInstruct PPLLaVA-7B gpt-score 3.81 #1 of 18 Archive leaderboard report
Video-based Generative Performance Benchmarking (Contextual Understanding) VideoInstruct PPLLaVA-7B gpt-score 4.21 #1 of 18 Archive leaderboard report
Video-based Generative Performance Benchmarking (Correctness of Information) VideoInstruct PPLLaVA-7B gpt-score 3.85 #1 of 18 Archive leaderboard report
Video-based Generative Performance Benchmarking (Detail Orientation)) VideoInstruct PPLLaVA-7B gpt-score 3.56 #1 of 18 Archive leaderboard report
Video-based Generative Performance Benchmarking (Temporal Understanding) VideoInstruct PPLLaVA-7B gpt-score 3.21 #1 of 18 Archive leaderboard report
Zero-Shot Video Question Answer ActivityNet-QA PPLLaVA-7B Accuracy 60.7 #3 of 28 Archive leaderboard report
Zero-Shot Video Question Answer ActivityNet-QA PPLLaVA-7B Confidence Score 3.6 #3 of 28 Archive leaderboard report
Zero-Shot Video Question Answer MSRVTT-QA PPLLaVA-7B Accuracy 64.3 #8 of 30 Archive leaderboard report
Zero-Shot Video Question Answer MSRVTT-QA PPLLaVA-7B Confidence Score 3.5 #8 of 30 Archive leaderboard report
Zero-Shot Video Question Answer MSVD-QA PPLLaVA-7B Accuracy 77.1 #9 of 28 Archive leaderboard report
Zero-Shot Video Question Answer MSVD-QA PPLLaVA-7B Confidence Score 4.0 #9 of 28 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.

Methods

CLIP

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