Papers › Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of...

Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities

22 Oct 2024arXiv:2410.17385archive 2025-07-28

Zheyuan Zhang, Fengyuan Hu, Jayjun Lee, Freda Shi, Parisa Kordjamshidi, Joyce Chai, Ziqiao Ma

Spatial expressions in situated communication can be ambiguous, as their meanings vary depending on the frames of reference (FoR) adopted by speakers and listeners. While spatial language understanding and reasoning by vision-language models (VLMs) have gained increasing attention, potential ambiguities in these models are still under-explored. To address this issue, we present the COnsistent Multilingual Frame Of Reference Test (COMFORT), an evaluation protocol to systematically assess the spatial reasoning capabilities of VLMs. We evaluate nine state-of-the-art VLMs using COMFORT. Despite showing some alignment with English conventions in resolving ambiguities, our experiments reveal significant shortcomings of VLMs: notably, the models (1) exhibit poor robustness and consistency, (2) lack the flexibility to accommodate multiple FoRs, and (3) fail to adhere to language-specific or culture-specific conventions in cross-lingual tests, as English tends to dominate other languages. With a growing effort to align vision-language models with human cognitive intuitions, we call for more attention to the ambiguous nature and cross-cultural diversity of spatial reasoning.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2410.17385")

Code

Syntology Ran 13 of 17 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran · fixture could not drive it; 11 ran with no contract checked.

By repository: official repository: 17 samples from 1 repository, 13 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

sled-group/COMFORT officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

17 samples harvested; 13 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
1ran · fixture could not drive it
11ran
4unverified

Licence: 17 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from sled-group/COMFORT. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

accuracy_metric sled-group/COMFORT/comfort_utils/accuracy_metric.py official repository ran no licence file found · pointer only · 119cf41aa9e4217f · report
build_transform sled-group/COMFORT/comfort_utils/model_utils/intern_vl.py official repository ran no licence file found · pointer only · 8cf510a10c5f26c3 · report
calculate_tokens_mean_attn sled-group/COMFORT/comfort_utils/helper.py official repository ran fingerprinted no licence file found · pointer only · e8579f20cd680a34 · report
clean_latex_dataframe sled-group/COMFORT/comfort_utils/convert_perspective_taking_results.py official repository ran no licence file found · pointer only · a721d26b902941ed · report
convert_to_dict sled-group/COMFORT/comfort_utils/convert_general_metrics_results.py official repository ran no licence file found · pointer only · d0aec2c5a6c35427 · report
dynamic_preprocess sled-group/COMFORT/comfort_utils/model_utils/intern_vl.py official repository ran · our draft was wrong no licence file found · pointer only · d610b5eabe0c9db1 · report
extract_table_data sled-group/COMFORT/comfort_utils/convert_general_metrics_results.py official repository ran no licence file found · pointer only · d3f911d03b9b9162 · report
find_closest_aspect_ratio sled-group/COMFORT/comfort_utils/model_utils/intern_vl.py official repository ran · fixture could not drive it no licence file found · pointer only · bd77f5f8067f18e9 · report
find_index_of_image_tokens sled-group/COMFORT/comfort_utils/helper.py official repository ran no licence file found · pointer only · 69b3b0492d912e11 · report
grounding_enc_processor sled-group/COMFORT/comfort_utils/model_utils/glamm_wrapper.py official repository ran fingerprinted no licence file found · pointer only · 55c9cd0497a84208 · report
latex_to_dataframe sled-group/COMFORT/comfort_utils/convert_perspective_taking_results.py official repository ran fingerprinted no licence file found · pointer only · 50dff60708886cd3 · report
sort_dataframe_by_model sled-group/COMFORT/comfort_utils/convert_perspective_taking_results.py official repository ran no licence file found · pointer only · c8d3c86f905b4d9a · report
sub_string_tokens_in_resp_token sled-group/COMFORT/comfort_utils/model_utils/gpt_wrapper.py official repository ran no licence file found · pointer only · 99bc5e82093e6f29 · report
accuracy_metric_object_frame sled-group/COMFORT/comfort_utils/accuracy_metric.py official repository unverified no licence file found · pointer only · 2846873087c38293 · report
accuracy_metric_old sled-group/COMFORT/comfort_utils/accuracy_metric.py official repository unverified no licence file found · pointer only · 0497e51919a7a2a6 · report
convention_metric sled-group/COMFORT/comfort_utils/convention_metric.py official repository unverified no licence file found · pointer only · c68d30db2cd63b2a · report
language_ambiguity_metric sled-group/COMFORT/comfort_utils/language_ambiguity_metric.py official repository unverified no licence file found · pointer only · c36a70c23b159d96 · report

Tasks

Spatial Reasoning

Datasets

Introduced by this paper, per the archive.

COMFORT

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALIGNAttentionSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections