Papers › Universal Visual Decomposer: Long-Horizon Manipulation Made Easy

Universal Visual Decomposer: Long-Horizon Manipulation Made Easy

12 Oct 2023arXiv:2310.08581archive 2025-07-28

Zichen Zhang, Yunshuang Li, Osbert Bastani, Abhishek Gupta, Dinesh Jayaraman, Yecheng Jason Ma, Luca Weihs

Real-world robotic tasks stretch over extended horizons and encompass multiple stages. Learning long-horizon manipulation tasks, however, is a long-standing challenge, and demands decomposing the overarching task into several manageable subtasks to facilitate policy learning and generalization to unseen tasks. Prior task decomposition methods require task-specific knowledge, are computationally intensive, and cannot readily be applied to new tasks. To address these shortcomings, we propose Universal Visual Decomposer (UVD), an off-the-shelf task decomposition method for visual long horizon manipulation using pre-trained visual representations designed for robotic control. At a high level, UVD discovers subgoals by detecting phase shifts in the embedding space of the pre-trained representation. Operating purely on visual demonstrations without auxiliary information, UVD can effectively extract visual subgoals embedded in the videos, while incurring zero additional training cost on top of standard visuomotor policy training. Goal-conditioned policies learned with UVD-discovered subgoals exhibit significantly improved compositional generalization at test time to unseen tasks. Furthermore, UVD-discovered subgoals can be used to construct goal-based reward shaping that jump-starts temporally extended exploration for reinforcement learning. We extensively evaluate UVD on both simulation and real-world tasks, and in all cases, UVD substantially outperforms baselines across imitation and reinforcement learning settings on in-domain and out-of-domain task sequences alike, validating the clear advantage of automated visual task decomposition within the simple, compact UVD framework.

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="2310.08581")

Code

Syntology Ran 1 of 12 code samples harvested from 1 repository linked to this paper; 11 have no recorded run. Of those that ran: 1 ran · honoured contract.

By repository: community (archive-listed): 12 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

zcczhang/uvd mentioned 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

12 samples harvested; 1 ran; 1 honoured the contract we drafted; 11 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
11unverified

Licence: 0 of the 12 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 zcczhang/uvd. “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.

find_multiple zcczhang/uvd/uvd/models/nn/transformer.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · aba86ffbed27ba65 · report
apply_rope zcczhang/uvd/uvd/models/nn/transformer.py community (archive-listed) unverified MIT (permissive) · 7137105772c52074 · report
build_rope_cache zcczhang/uvd/uvd/models/nn/transformer.py community (archive-listed) unverified MIT (permissive) · 1800f2d56d86239c · report
conv_output_dim zcczhang/uvd/uvd/models/nn/cnn.py community (archive-listed) unverified MIT (permissive) · 500bc4bac9e137be · report
convert_activation zcczhang/uvd/uvd/models/nn/mlp.py community (archive-listed) unverified MIT (permissive) · c6e37f289a08d025 · report
freeze_bn zcczhang/uvd/uvd/utils/module_utils.py community (archive-listed) unverified MIT (permissive) · db6ef2777063a4e7 · report
freeze_module zcczhang/uvd/uvd/utils/module_utils.py community (archive-listed) unverified MIT (permissive) · f853e708a1ad4005 · report
linear_random_skip zcczhang/uvd/uvd/decomp/decomp.py community (archive-listed) unverified MIT (permissive) · 70b1391de26bd225 · report
make_cnn zcczhang/uvd/uvd/models/nn/cnn.py community (archive-listed) unverified MIT (permissive) · 689ff668a5ab1ea1 · report
make_mlp_hidden zcczhang/uvd/uvd/models/nn/mlp.py community (archive-listed) unverified MIT (permissive) · e0a2f86a02349757 · report
one_layer_state_encoder zcczhang/uvd/uvd/models/nn/mlp.py community (archive-listed) unverified MIT (permissive) · 3ee87ea43e2af4bd · report
unfreeze_module zcczhang/uvd/uvd/utils/module_utils.py community (archive-listed) unverified MIT (permissive) · a60301aec2d7e6b6 · report

Tasks

reinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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