Papers › GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields

GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields

31 Aug 2023arXiv:2308.16891archive 2025-07-28

Yanjie Ze, Ge Yan, Yueh-Hua Wu, Annabella Macaluso, Yuying Ge, Jianglong Ye, Nicklas Hansen, Li Erran Li, Xiaolong Wang

It is a long-standing problem in robotics to develop agents capable of executing diverse manipulation tasks from visual observations in unstructured real-world environments. To achieve this goal, the robot needs to have a comprehensive understanding of the 3D structure and semantics of the scene. In this work, we present GNFactor, a visual behavior cloning agent for multi-task robotic manipulation with Generalizable Neural feature Fields. GNFactor jointly optimizes a generalizable neural field (GNF) as a reconstruction module and a Perceiver Transformer as a decision-making module, leveraging a shared deep 3D voxel representation. To incorporate semantics in 3D, the reconstruction module utilizes a vision-language foundation model (e.g., Stable Diffusion) to distill rich semantic information into the deep 3D voxel. We evaluate GNFactor on 3 real robot tasks and perform detailed ablations on 10 RLBench tasks with a limited number of demonstrations. We observe a substantial improvement of GNFactor over current state-of-the-art methods in seen and unseen tasks, demonstrating the strong generalization ability of GNFactor. Our project website is https://yanjieze.com/GNFactor/ .

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="2308.16891")

Code

Syntology Ran 7 of 10 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 7 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

YanjieZe/GNFactor officialmentioned 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

10 samples harvested; 7 ran; 0 honoured the contract we drafted; 3 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.

7ran
3unverified

Licence: 0 of the 10 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 YanjieZe/GNFactor. “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.

act_layer YanjieZe/GNFactor/GNFactor/helpers/network_utils.py official repository ran MIT (permissive) · c99fb7b9654ea364 · report
find_minimum_difference YanjieZe/GNFactor/GNFactor/helpers/demo_loading_utils.py official repository ran fingerprinted MIT (permissive) · 0a61ee3eb30e145f · report
loss_weights YanjieZe/GNFactor/GNFactor/helpers/utils.py official repository ran MIT (permissive) · e8c79c7ee37f3772 · report
norm_layer1d YanjieZe/GNFactor/GNFactor/helpers/network_utils.py official repository ran MIT (permissive) · 9ed9933be23b28a5 · report
norm_layer2d YanjieZe/GNFactor/GNFactor/helpers/network_utils.py official repository ran MIT (permissive) · d0264b5831943fb9 · report
normalize_quaternion YanjieZe/GNFactor/GNFactor/helpers/utils.py official repository ran fingerprinted MIT (permissive) · f6a528fb2776e15a · report
stack_on_channel YanjieZe/GNFactor/GNFactor/helpers/utils.py official repository ran fingerprinted MIT (permissive) · 2a6ead00d93a9c6c · report
create_language_model YanjieZe/GNFactor/GNFactor/helpers/language_model.py official repository unverified MIT (permissive) · 6b4c7c09aa0a03b0 · report
perturb_se3 YanjieZe/GNFactor/GNFactor/voxel/augmentation.py official repository unverified MIT (permissive) · 16715f86251e9358 · report
perturb_se3_camera_pose YanjieZe/GNFactor/GNFactor/voxel/augmentation.py official repository unverified MIT (permissive) · 4ebb32574c99584c · report

Tasks

Decision Making

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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