SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.00515 · ICML · 2026

MLLM-4D: Towards Visual-based Spatial-Temporal Intelligence

Chi-Man Pun, Chengzhengxu Li, Cun, Xingyilang Yin, Jiahao Chang

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 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; 5 failures of our instrument; 1 no recorded run), measured 2026-11-22; 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/2603.00515.json · badge: /api/ran/2603.00515.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
GVCLab/MLLM-4D canonical (classifier label)
classifier basis: census
6 ran · 1 no recorded run
FunctionStatusWhere it lives
build_transform Ran
ran; our contract draft was wrong, not the code
GVCLab/MLLM-4D/evaluation/model_inference/internvideo2_5.py
pointer only (licence: NONE) · get_code("8e7f5895ff4790f2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GVCLab/MLLM-4D 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.

dynamic_preprocess Ran
ran; our contract draft was wrong, not the code
GVCLab/MLLM-4D/evaluation/model_inference/internvideo2_5.py
pointer only (licence: NONE); the stored copy get_code serves, from OpenGVLab/MM-NIAH, is pointer only (licence: NONE) · get_code("d610b5eabe0c9db1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GVCLab/MLLM-4D 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.

extract_option_key Ran
ran; our contract draft was wrong, not the code
GVCLab/MLLM-4D/evaluation/model_inference/mllm4d.py
pointer only (licence: NONE) · get_code("77998a2873f080cf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GVCLab/MLLM-4D 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.

find_closest_aspect_ratio Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
GVCLab/MLLM-4D/evaluation/model_inference/internvideo2_5.py
pointer only (licence: NONE); the stored copy get_code serves, from OpenGVLab/MM-NIAH, is pointer only (licence: NONE) · get_code("bd77f5f8067f18e9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GVCLab/MLLM-4D 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.

get_index Ran
ran, honoured the contract we drafted
GVCLab/MLLM-4D/evaluation/model_inference/internvideo.py
pointer only (licence: NONE) · get_code("65d587525000912a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GVCLab/MLLM-4D 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.

prepare_evaluation_message Ran
ran; our contract draft was wrong, not the code
GVCLab/MLLM-4D/evaluation/evaluation.py
pointer only (licence: NONE) · get_code("328c78ffa1568e68")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GVCLab/MLLM-4D 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.

evaluate_with_qwen Not yet run
unverified (harvested, no recorded run)
GVCLab/MLLM-4D/evaluation/evaluation.py
pointer only (licence: NONE) · get_code("fdeaee32bf8e5862")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GVCLab/MLLM-4D 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 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 2 later) and 3 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
find_closest_aspect_ratio 43 other papers
39 dated earlier, 4 later
1910.01108 (2019-10)
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
2312.13271 (2023-12)
Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting
2403.15952 (2024-03)
IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models
and 40 more not named here
dynamic_preprocess 13 other papers
12 dated earlier, 1 later
2312.13271 (2023-12)
Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting
2405.14156 (2024-05)
Unveiling the Tapestry of Consistency in Large Vision-Language Models
2406.07230 (2024-06)
Needle In A Multimodal Haystack
and 10 more not named here
get_index 3 other papers
3 dated earlier
2311.10111 (2023-11)
VideoCon: Robust Video-Language Alignment via Contrast Captions
2403.07350 (2024-03)
VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark
2503.06800 (2025-03)
VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation
build_transform 2 other papers
2 dated earlier
2406.06462 (2024-06)
VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text
2412.12693 (2024-12)
SPHERE: Unveiling Spatial Blind Spots in Vision-Language Models Through Hierarchical Evaluation

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

for Supervised Fine-Tuning (SFT) and Reinforcement Fine-Tuning (RFT), alongside MLLM4D-Bench for comprehensive evaluation. Regarding model training, our post-training strategy establishes a foundational 4D understanding via SFT and further catalyzes 4D reasoning capabilities by employing Group Relative Policy Optimization (GRPO) with specialized Spatiotemporal Chain of Thought (ST-CoT) prompting and Spatiotemporal reward functions (ST-reward) without involving the modification of architecture. Extensive experiments demonstrate that MLLM-4D achieves state-of-the-art spatial-temporal understanding and reasoning capabilities from purely 2D RGB inputs. Project page: https:// github.com/GVCLab/MLLM-4D.

For agents

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

get_harvested_code_for_paper("2603.00515")
get_code_for_paper("2603.00515")
have("2603.00515")

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

curl https://syntology.ai/api/ran/2603.00515.json

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

[![Syntology run record](https://syntology.ai/api/ran/2603.00515.svg)](https://syntology.ai/paper/2603.00515)

Connect an agent — have() is free.