SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.11289 · 2024

ManipVQA: Injecting Robotic Affordance and Physically Grounded Information into Multi-Modal Large Language Models

arXiv · PDF · Open in the Atlas

Code that ran

8 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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures 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/2403.11289.json · badge: /api/ran/2403.11289.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
siyuanhuang95/manipvqa canonical (classifier label)
classifier basis: census
8 ran · 0 no recorded run
FunctionStatusWhere it lives
T_padded_resize Ran
ran; our contract draft was wrong, not the code
siyuanhuang95/manipvqa/accessory/eval_manip.py
pointer only (licence: NONE) · get_code("1cbb43c0dc4ea2ca")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, siyuanhuang95/manipvqa 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.

bb_intersection_over_union Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
siyuanhuang95/manipvqa/accessory/get_ap_tool.py
pointer only (licence: NONE) · get_code("5887c86feaa968f6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, siyuanhuang95/manipvqa 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.

collate_fn Ran
ran; our contract draft was wrong, not the code
siyuanhuang95/manipvqa/accessory/eval_manip.py
pointer only (licence: NONE); the stored copy get_code serves, from changhaonan/a3vlm, is pointer only (licence: NONE) · get_code("583539928cd10b3c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, siyuanhuang95/manipvqa 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_bounding_box Ran
ran, honoured the contract we drafted
siyuanhuang95/manipvqa/accessory/get_ap_tool.py
pointer only (licence: NONE) · get_code("c40d295f8be78649")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, siyuanhuang95/manipvqa 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.

format_bounding_box Ran
ran, honoured the contract we drafted
siyuanhuang95/manipvqa/accessory/get_ap_tool.py
pointer only (licence: NONE) · get_code("cfdf6b9fc39c9664")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, siyuanhuang95/manipvqa 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_json_file_list Ran
ran; our contract draft was wrong, not the code
siyuanhuang95/manipvqa/dataset/dataset_utils.py
pointer only (licence: NONE) · get_code("877b4942dbab7ce4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, siyuanhuang95/manipvqa 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.

normalize_number Ran
ran, honoured the contract we drafted
siyuanhuang95/manipvqa/accessory/eval_manip.py
pointer only (licence: NONE); the stored copy get_code serves, from changhaonan/a3vlm, is pointer only (licence: NONE) · get_code("f4e43fb4d725358d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, siyuanhuang95/manipvqa 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.

probe_tokenizer_path_from_pretrained Ran
ran; our contract draft was wrong, not the code
siyuanhuang95/manipvqa/accessory/model/tokenizer.py
pointer only (licence: NONE) · get_code("476ee9ec95271a06")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, siyuanhuang95/manipvqa 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.

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, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 5 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
collate_fn 1 other paper
1 later
2406.07549 (2024-06)
A3VLM: Actionable Articulation-Aware Vision Language Model
normalize_number 1 other paper
1 later
2406.07549 (2024-06)
A3VLM: Actionable Articulation-Aware Vision Language Model
probe_tokenizer_path_from_pretrained 1 other paper
1 later
2506.05302 (2025-06)
Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos

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

While the integration of Multi-modal Large Language Models (MLLMs) with robotic systems has significantly improved robots' ability to understand and execute natural language instructions, their performance in manipulation tasks remains limited due to a lack of robotics-specific knowledge. Conventional MLLMs are typically trained on generic image-text pairs, leaving them deficient in understanding affordances and physical concepts crucial for manipulation. To address this gap, we propose ManipVQA, a novel framework that infuses MLLMs with manipulation-centric knowledge through a Visual Question-Answering (VQA) format. This approach encompasses tool detection, affordance recognition, and a broader understanding of physical concepts. We curated a diverse dataset of images depicting interactive objects, to challenge robotic understanding in tool detection, affordance prediction, and physical concept comprehension. To effectively integrate this robotics-specific knowledge with the inherent vision-reasoning capabilities of MLLMs, we leverage a unified VQA format and devise a fine-tuning strategy. This strategy preserves the original vision-reasoning abilities while incorporating the newly acquired robotic insights. Empirical evaluations conducted in robotic simulators and across various vision task benchmarks demonstrate the robust performance of ManipVQA. The code and dataset are publicly available at https://github.com/SiyuanHuang95/ManipVQA.

For agents

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

get_harvested_code_for_paper("2403.11289")
get_code_for_paper("2403.11289")
have("2403.11289")

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

curl https://syntology.ai/api/ran/2403.11289.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.11289.svg)](https://syntology.ai/paper/2403.11289)

Connect an agent — have() is free.