Papers › DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and Objects

DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and Objects

3 Oct 2024arXiv:2410.02730archive 2025-07-28

Zhaowei Wang, Hongming Zhang, Tianqing Fang, Ye Tian, Yue Yang, Kaixin Ma, Xiaoman Pan, Yangqiu Song, Dong Yu

Object navigation in unknown environments is crucial for deploying embodied agents in real-world applications. While we have witnessed huge progress due to large-scale scene datasets, faster simulators, and stronger models, previous studies mainly focus on limited scene types and target objects. In this paper, we study a new task of navigating to diverse target objects in a large number of scene types. To benchmark the problem, we present a large-scale scene dataset, DivScene, which contains 4,614 scenes across 81 different types. With the dataset, we build an end-to-end embodied agent, NatVLM, by fine-tuning a Large Vision Language Model (LVLM) through imitation learning. The LVLM is trained to take previous observations from the environment and generate the next actions. We also introduce CoT explanation traces of the action prediction for better performance when tuning LVLMs. Our extensive experiments find that we can build a performant LVLM-based agent through imitation learning on the shortest paths constructed by a BFS planner without any human supervision. Our agent achieves a success rate that surpasses GPT-4o by over 20%. Meanwhile, we carry out various analyses showing the generalization ability of our agent. Our code and data are available at https://github.com/zhaowei-wang-nlp/DivScene.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 15 code samples harvested from 1 repository linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 8 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 15 ran (7 with no instrument failure; 8 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

zhaowei-wang-nlp/divscene officialmentioned in papermentioned on GitHubpytorchMITSyntology: 15 samples, 15 ran (8 instrument-failed) · 0 unverified 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

15 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 8 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
7ran · our draft was wrong
1ran; the contract check could not run
5ran

Licence: 0 of the 15 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 zhaowei-wang-nlp/divscene. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

zhaowei-wang-nlp/divscene official repository 15 samples, 15 ran (8 instrument-failed) · 0 unverified
calculate_path_length agent_inference/hf_idefics2_metric.py ran; the contract check could not run (RAISES) MIT (permissive) · c398e46c3e1c3747 · report fixture: signature path_list:list/1/tuple · returned float · level recorded 2026-09-24
convert_pair_to_str reformat_data/diff_utils.py ran · our draft was wrong MIT (permissive) · 4259267f7d4a7e91 · report fixture: signature pair:tuple/1/float · returned str · level recorded 2026-09-24
extract_object_type reformat_data/diff_utils.py ran · our draft was wrong fingerprinted MIT (permissive) · 005fdbd14f429fc0 · report fixture: signature object_id:str/0/str · returned str · level recorded 2026-09-24
format_args agent_inference/utils.py ran · our draft was wrong MIT (permissive) · f3f346ac0d3677e3 · report fixture: signature args:Args/0/? · returned str · level recorded 2026-09-24
get_cur_diff reformat_data/diff_utils.py ran MIT (permissive) · 9f5266890fdc41a6 · report fixture: signature r:int/0/int, p:tuple/1/float, target_agent_pos:tuple/1/float · returned tuple · level recorded 2026-09-24
get_cur_diff reformat_data/utils.py ran MIT (permissive) · 346ba3a0aa9a8e55 · report fixture: signature r:int/0/int, p_diff:ndarray/1/int · returned tuple · level recorded 2026-09-24
get_shortest_path_to_point agent_inference/hf_idefics2_online_client.py ran MIT (permissive) · 44465377eaacf505 · report fixture: signature controller:MockController/0/?, initial_position:dict/0/?, target_position:dict/0/? · returned list · level recorded 2026-09-24
get_type_dict agent_inference/hf_idefics2_gpt4o.py ran · our draft was wrong MIT (permissive) · b297d01d782e10b4 · report fixture: signature my_dict:dict/0/? · returned dict · level recorded 2026-09-24
init_logger in 50 papers agent_inference/utils.py ran MIT (permissive) · 4650a677e33f265a · report fixture: signature training_args:MinimalTrainingArgs/0/?, log_level:int/0/int · returned RootLogger · level recorded 2026-09-24
map_action_to_id agent_inference/hf_idefics2_gpt4o.py ran · honoured contract MIT (permissive) · b43f513176e6bbfe · report fixture: signature action_list:list/1/str · returned list · level recorded 2026-09-24
map_action_to_id agent_inference/hf_idefics2_server.py ran · honoured contract MIT (permissive) · e04797a75615b923 · report fixture: signature action_list:list/1/str · returned list · level recorded 2026-09-24
parse_action in 33 papers agent_inference/hf_idefics2_gpt4o.py ran · our draft was wrong fingerprinted MIT (permissive) · b6552010f6d8a287 · report fixture: signature output_str:str/0/str · returned str · level recorded 2026-09-24
parse_action in 33 papers agent_inference/hf_idefics2_online_client.py ran · our draft was wrong fingerprinted MIT (permissive) · 7a16f1f9f950f857 · report fixture: signature output_str:str/0/str · returned str · level recorded 2026-09-24
parse_action in 33 papers agent_inference/hf_idefics2_server.py ran · our draft was wrong fingerprinted MIT (permissive) · a24d87222eb1a622 · report fixture: signature output_str:str/0/str · returned str · level recorded 2026-09-24
revise_mnli_models agent_inference/utils.py ran MIT (permissive) · a7b36e290c6f5fc1 · report fixture: signature model_name_or_path:str/0/str, mnli_model:callable/0/?, neutral_id:int/0/int, entail_id:int/0/int · returned RobertaModel · level recorded 2026-09-24

Tasks

BenchmarkingImitation LearningLanguage Modelling

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Focus

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