SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.14485 · 2024

Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 0 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/2409.14485.json · badge: /api/ran/2409.14485.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
vectorspacelab/video-xl canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
2 ran · 0 no recorded run
FunctionStatusWhere it lives
compute_frame_timestamps Ran
ran, honoured the contract we drafted
vectorspacelab/video-xl/Video-XL-2/eval/lvu/pure/lmms_eval/tasks/longvideobench/utils.py
code served (permissive licence) · get_code("59a749b9c04b3f23")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Analyze the function:
# - duration: numeric value (int or float) representing duration
# - max_num_frames: numeric value with default 16, used in comparison and division

# Test case 1: duration > max_num_frames
duration_1 = 25
max_num_frames_1 = 16

# Test case 2: duration <= max_num_frames
duration_2 = 10
max_num_frames_2 = 16

# We'll use the first test case for ARGS
ARGS = {
    "duration": 25,
    "max_num_frames": 16
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
hash_args Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from mansicer/Q-Adapter
pointer only · get_code("20a7cc804eb22661")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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. A run is recorded.

timestamp_to_seconds Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from open-compass/VLMEvalKit
pointer only · get_code("b0e798a910385a74")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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. A run is recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 1 later) and 1 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.

FunctionAlso present inEarliest-datedOthers named
hash_args 44 other papers
19 dated earlier, 1 the same month, 22 later, 1 same year, order not determinable, 1 undated
2005.14165 (2020-05)
Language Models are Few-Shot Learners
2110.04374 (2021-10)
A Few More Examples May Be Worth Billions of Parameters
2303.17003 (2023-03)
Evaluating GPT-3.5 and GPT-4 Models on Brazilian University Admission Exams
and 41 more not named here
timestamp_to_seconds 2 other papers
2 dated earlier
2406.14515 (2024-06)
MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding
2407.15754 (2024-07)
LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding

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

Long video understanding poses a significant challenge for current Multi-modal Large Language Models (MLLMs). Notably, the MLLMs are constrained by their limited context lengths and the substantial costs while processing long videos. Although several existing methods attempt to reduce visual tokens, their strategies encounter severe bottleneck, restricting MLLMs' ability to perceive fine-grained visual details. In this work, we propose Video-XL, a novel approach that leverages MLLMs' inherent key-value (KV) sparsification capacity to condense the visual input. Specifically, we introduce a new special token, the Visual Summarization Token (VST), for each interval of the video, which summarizes the visual information within the interval as its associated KV. The VST module is trained by instruction fine-tuning, where two optimizing strategies are offered. 1.Curriculum learning, where VST learns to make small (easy) and large compression (hard) progressively. 2. Composite data curation, which integrates single-image, multi-image, and synthetic data to overcome the scarcity of long-video instruction data. The compression quality is further improved by dynamic compression, which customizes compression granularity based on the information density of different video intervals. Video-XL's effectiveness is verified from three aspects. First, it achieves a superior long-video understanding capability, outperforming state-of-the-art models of comparable sizes across multiple popular benchmarks. Second, it effectively preserves video information, with minimal compression loss even at 16x compression ratio. Third, it realizes outstanding cost-effectiveness, enabling high-quality processing of thousands of frames on a single A100 GPU.

For agents

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

get_harvested_code_for_paper("2409.14485")
get_code_for_paper("2409.14485")
have("2409.14485")

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

curl https://syntology.ai/api/ran/2409.14485.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.14485.svg)](https://syntology.ai/paper/2409.14485)

Connect an agent — have() is free.