SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.16558 · 2024

Elysium: Exploring Object-level Perception in Videos via MLLM

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 failures of our instrument; 1 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/2403.16558.json · badge: /api/ran/2403.16558.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
hon-wong/elysium canonical (classifier label)
classifier basis: census
7 ran · 1 no recorded run
FunctionStatusWhere it lives
b2str Ran
ran; our contract draft was wrong, not the code
hon-wong/elysium/eval/merge_result.py
pointer only (licence: NONE) · get_code("03ea4ef71d990d69")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hon-wong/elysium 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. A run is recorded.

build_adapter Ran
ran; our contract draft was wrong, not the code
hon-wong/elysium/models/rantselector.py
pointer only (licence: NONE) · get_code("14a5b06381b76869")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hon-wong/elysium 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. A run is recorded.

build_projector Ran
ran; our contract draft was wrong, not the code
hon-wong/elysium/models/build_vit.py
pointer only (licence: NONE) · get_code("dc5f7a793bd5c8b8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hon-wong/elysium 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. A run is recorded.

calc_err_center Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hon-wong/elysium/eval/otb.py
pointer only (licence: NONE) · get_code("66f1707e5716c275")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hon-wong/elysium 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. A run is recorded.

calc_iou_overlap Ran
ran; our contract draft was wrong, not the code
hon-wong/elysium/eval/otb.py
pointer only (licence: NONE) · get_code("3079b3e29bfecb3d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hon-wong/elysium 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. A run is recorded.

calc_seq_err_robust Ran
ran; our contract draft was wrong, not the code
hon-wong/elysium/eval/otb.py
pointer only (licence: NONE) · get_code("30aa0d18d04fc6fb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hon-wong/elysium 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. A run is recorded.

parse_box_from_raw_text Ran
ran, honoured the contract we drafted
hon-wong/elysium/eval/merge_result.py
pointer only (licence: NONE) · get_code("7f7a40ee6ae5eb93")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hon-wong/elysium 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. A run is recorded.

create_clip_vit Not yet run
unverified (harvested, no recorded run)
hon-wong/elysium/models/build_vit.py
pointer only (licence: NONE) · get_code("69245b70a5e8929e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hon-wong/elysium 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 7 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
build_projector 1 other paper
1 later
2412.09530 (2024-12)
Dynamic-VLM: Simple Dynamic Visual Token Compression for VideoLLM

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

Multi-modal Large Language Models (MLLMs) have demonstrated their ability to perceive objects in still images, but their application in video-related tasks, such as object tracking, remains understudied. This lack of exploration is primarily due to two key challenges. Firstly, extensive pretraining on large-scale video datasets is required to equip MLLMs with the capability to perceive objects across multiple frames and understand inter-frame relationships. Secondly, processing a large number of frames within the context window of Large Language Models (LLMs) can impose a significant computational burden. To address the first challenge, we introduce ElysiumTrack-1M, a large-scale video dataset supported for three tasks: Single Object Tracking (SOT), Referring Single Object Tracking (RSOT), and Video Referring Expression Generation (Video-REG). ElysiumTrack-1M contains 1.27 million annotated video frames with corresponding object boxes and descriptions. Leveraging this dataset, we conduct training of MLLMs and propose a token-compression model T-Selector to tackle the second challenge. Our proposed approach, Elysium: Exploring Object-level Perception in Videos via MLLM, is an end-to-end trainable MLLM that attempts to conduct object-level tasks in videos without requiring any additional plug-in or expert models. All codes and datasets are available at https://github.com/Hon-Wong/Elysium.

For agents

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

get_harvested_code_for_paper("2403.16558")
get_code_for_paper("2403.16558")
have("2403.16558")

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

curl https://syntology.ai/api/ran/2403.16558.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.16558.svg)](https://syntology.ai/paper/2403.16558)

Connect an agent — have() is free.