SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.03384 · ECCV · 2024

LongVLM: Efficient Long Video Understanding via Large Language Models

Bohan Zhuang, Xiaojun Chang, Haoyu He, Yuetian Weng, Mingfei Han

arXiv · PDF · Open in the Atlas

Code that ran

None of the 4 samples (functions and classes) lifted from this paper's linked repositories has a recorded run on a synthesized input (4 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2404.03384.json · badge: /api/ran/2404.03384.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
ziplab/longvlm marked official in Papers with Code
Papers with Code archive
0 ran · 4 no recorded run
FunctionStatusWhere it lives
LongVLMConfig Not yet run
unverified (harvested, no recorded run)
ziplab/longvlm/longvlm/model/longvlm.py
pointer only (licence: NONE) · get_code("083b34e4863de8dd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ziplab/longvlm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

LongVLMForCausalLM Not yet run
unverified (harvested, no recorded run)
ziplab/longvlm/longvlm/model/longvlm.py
pointer only (licence: NONE) · get_code("3f0ed3258ba58e79")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ziplab/longvlm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

LongVLMLlamaModel Not yet run
unverified (harvested, no recorded run)
ziplab/longvlm/longvlm/model/longvlm.py
pointer only (licence: NONE) · get_code("f9e6d48dd3e99ccd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ziplab/longvlm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

VisionConfig Not yet run
unverified (harvested, no recorded run)
ziplab/longvlm/longvlm/model/longvlm.py
pointer only (licence: NONE) · get_code("cffbd80e3b608272")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ziplab/longvlm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Empowered by Large Language Models (LLMs), recent advancements in Video-based LLMs (VideoLLMs) have driven progress in various video understanding tasks. These models encode video representations through pooling or query aggregation over a vast number of visual tokens, making computational and memory costs affordable. Despite successfully providing an overall comprehension of video content, existing VideoLLMs still face challenges in achieving detailed understanding due to overlooking local information in long-term videos. To tackle this challenge, we introduce LongVLM, a simple yet powerful VideoLLM for long video understanding, building upon the observation that long videos often consist of sequential key events, complex actions, and camera movements. Our approach proposes to decompose long videos into multiple short-term segments and encode local features for each segment via a hierarchical token merging module. These features are concatenated in temporal order to maintain the storyline across sequential short-term segments. Additionally, we propose to integrate global semantics into each local feature to enhance context understanding. In this way, we encode video representations that incorporate both local and global information, enabling the LLM to generate comprehensive responses for long-term videos. Experimental results on the VideoChatGPT benchmark and zero-shot video question-answering datasets demonstrate the superior capabilities of our model over the previous state-of-the-art methods. Qualitative examples show that our model produces more precise responses for long video understanding.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2404.03384")
get_code_for_paper("2404.03384")
have("2404.03384")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2404.03384.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2404.03384.svg)](https://syntology.ai/paper/2404.03384)

Connect an agent — have() is free.