Papers › Towards Learning a Generalist Model for Embodied Navigation

Towards Learning a Generalist Model for Embodied Navigation

4 Dec 2023CVPR 2024 1arXiv:2312.02010archive 2025-07-28

Duo Zheng, Shijia Huang, Lin Zhao, Yiwu Zhong, LiWei Wang

Building a generalist agent that can interact with the world is the intriguing target of AI systems, thus spurring the research for embodied navigation, where an agent is required to navigate according to instructions or respond to queries. Despite the major progress attained, previous works primarily focus on task-specific agents and lack generalizability to unseen scenarios. Recently, LLMs have presented remarkable capabilities across various fields, and provided a promising opportunity for embodied navigation. Drawing on this, we propose the first generalist model for embodied navigation, NaviLLM. It adapts LLMs to embodied navigation by introducing schema-based instruction. The schema-based instruction flexibly casts various tasks into generation problems, thereby unifying a wide range of tasks. This approach allows us to integrate diverse data sources from various datasets into the training, equipping NaviLLM with a wide range of capabilities required by embodied navigation. We conduct extensive experiments to evaluate the performance and generalizability of our model. The experimental results demonstrate that our unified model achieves state-of-the-art performance on CVDN, SOON, and ScanQA. Specifically, it surpasses the previous stats-of-the-art method by a significant margin of 29% in goal progress on CVDN. Moreover, our model also demonstrates strong generalizability and presents impressive results on unseen tasks, e.g., embodied question answering and 3D captioning.

PaperPDFConference PDFCodeCode 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="2312.02010")

Code

Syntology Ran 10 of 15 code samples harvested from 2 repositories linked to this paper; 5 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 1 ran · our draft was wrong; 2 ran · fixture could not drive it; 5 ran with no contract checked.

By repository: official repository: 15 samples from 2 repositories, 10 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

lavi-lab/navillm officialmentioned in papermentioned on GitHubpytorchMIT report
zd11024/NaviLLM officialmentioned in papermentioned on GitHubpytorchMIT 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; 10 ran; 1 honoured the contract we drafted; 5 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 · honoured contract
1ran · violated contract
1ran · our draft was wrong
2ran · fixture could not drive it
5ran
5unverified

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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

swish lavi-lab/navillm/models/vln_bert.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 0f786c407fb1ee4c · report
build_dataloader lavi-lab/navillm/tasks/loaders.py official repository ran MIT (permissive) · dd2ac0ab9c587094 · report
calc_position_distance lavi-lab/navillm/models/graph_utils.py official repository ran · violated contract fingerprinted MIT (permissive) · c362aaed2935ceff · report
calculate_vp_rel_pos_fts lavi-lab/navillm/models/graph_utils.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 168e35f8ed1ad0ce · report
create_feature_db lavi-lab/navillm/tasks/feature_db.py official repository ran MIT (permissive) · 98a915bad0a2f94d · report
extend_neg_masks lavi-lab/navillm/models/ops.py official repository ran MIT (permissive) · 91e1742acf23aa57 · report
gelu zd11024/NaviLLM/models/vln_bert.py official repository ran · honoured contract fingerprinted MIT (permissive) · c2f0705ed8e6f7e6 · report
gen_seq_masks lavi-lab/navillm/models/ops.py official repository ran MIT (permissive) · d9c76c6dc9976905 · report
get_angle_fts lavi-lab/navillm/models/graph_utils.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · dac1993f5ce8e12e · report
move_to_cuda lavi-lab/navillm/tasks/loaders.py official repository ran MIT (permissive) · a581dc0bf92d2ee5 · report
build_transformer lavi-lab/navillm/models/detr_transformer.py official repository unverified MIT (permissive) · df2919fd1dad1d43 · report
create_dataloaders lavi-lab/navillm/tasks/loaders.py official repository unverified MIT (permissive) · 1a2aa37d868fb374 · report
create_transformer_encoder lavi-lab/navillm/models/ops.py official repository unverified MIT (permissive) · bdc0b119cec4f508 · report
init_vis_config lavi-lab/navillm/models/nav_model.py official repository unverified MIT (permissive) · 7d0ae7f5c781116b · report
llama_model_in_debug_model lavi-lab/navillm/models/vln_bert.py official repository unverified MIT (permissive) · 6288ee4b92b46305 · report

Tasks

3D Question Answering (3D-QA)Embodied Question AnsweringNavigateQuestion AnsweringVisual Navigation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Question Answering (3D-QA) ScanQA Test w/ objects NaviLLM BLEU-1 39.73 #5 of 18 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects NaviLLM BLEU-4 13.90 #5 of 18 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects NaviLLM CIDEr 80.77 #5 of 18 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects NaviLLM Exact Match 26.27 #5 of 18 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects NaviLLM METEOR 16.56 #5 of 18 Archive leaderboard report
3D Question Answering (3D-QA) ScanQA Test w/ objects NaviLLM ROUGE 40.23 #5 of 18 Archive leaderboard report
Visual Navigation Cooperative Vision-and-Dialogue Navigation NaviLLM dist_to_end_reduction 7.90 #1 of 19 Archive leaderboard report
Visual Navigation Cooperative Vision-and-Dialogue Navigation NaviLLM spl 0.09 #1 of 19 Archive leaderboard report
Visual Navigation R2R NaviLLM spl 0.60 #4 of 11 Archive leaderboard report
Visual Navigation SOON Test NaviLLM Nav-SPL 26.26 #2 of 6 Archive leaderboard report
Visual Navigation SOON Test NaviLLM SR 35.04 #2 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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