Papers › Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-guided...

Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-guided 3D Policy

2 Oct 2024arXiv:2410.01345archive 2025-07-28

Ricardo Garcia, ShiZhe Chen, Cordelia Schmid

Generalizing language-conditioned robotic policies to new tasks remains a significant challenge, hampered by the lack of suitable simulation benchmarks. In this paper, we address this gap by introducing GemBench, a novel benchmark to assess generalization capabilities of vision-language robotic manipulation policies. GemBench incorporates seven general action primitives and four levels of generalization, spanning novel placements, rigid and articulated objects, and complex long-horizon tasks. We evaluate state-of-the-art approaches on GemBench and also introduce a new method. Our approach 3D-LOTUS leverages rich 3D information for action prediction conditioned on language. While 3D-LOTUS excels in both efficiency and performance on seen tasks, it struggles with novel tasks. To address this, we present 3D-LOTUS++, a framework that integrates 3D-LOTUS's motion planning capabilities with the task planning capabilities of LLMs and the object grounding accuracy of VLMs. 3D-LOTUS++ achieves state-of-the-art performance on novel tasks of GemBench, setting a new standard for generalization in robotic manipulation. The benchmark, codes and trained models are available at https://www.di.ens.fr/willow/research/gembench/.

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="2410.01345")

Code

Syntology Ran 1 of 1 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran with no contract checked.

By repository: official repository: 1 sample 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.

vlc-robot/robot-3dlotus 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

1 sample harvested; 1 ran; 0 honoured the contract we drafted; 0 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

Licence: 1 of the 1 sample is 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 vlc-robot/robot-3dlotus. “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.

get_prompts_from_label vlc-robot/robot-3dlotus/genrobo3d/vlm_models/clip_encoder.py official repository ran fingerprinted no licence file found · pointer only · 284e52af67401746 · report

Tasks

Motion PlanningRobot ManipulationRobot Manipulation GeneralizationTask Planning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Robot Manipulation RLBench 3D-LOTUS Inference Speed (fps) 9.5 #4 of 18 Archive leaderboard report
Robot Manipulation RLBench 3D-LOTUS Input Image Size 256 #4 of 18 Archive leaderboard report
Robot Manipulation RLBench 3D-LOTUS Succ. Rate (18 tasks, 100 demo/task) 83.1 #4 of 18 Archive leaderboard report
Robot Manipulation RLBench 3D-LOTUS Training Time (A100 x hour) 40 #4 of 18 Archive leaderboard report
Robot Manipulation RLBench 3D-LOTUS Training Time (V100 x 8 x day) 0.28 #4 of 18 Archive leaderboard report
Robot Manipulation Generalization GEMBench 3D-LOTUS++ Average Success Rate 48.0 #1 of 6 Archive leaderboard report
Robot Manipulation Generalization GEMBench 3D-LOTUS++ Average Success Rate (L1) 68.7±0.6 #1 of 6 Archive leaderboard report
Robot Manipulation Generalization GEMBench 3D-LOTUS++ Average Success Rate (L2) 64.5±0.9 #1 of 6 Archive leaderboard report
Robot Manipulation Generalization GEMBench 3D-LOTUS++ Average Success Rate (L3) 41.5±1.8 #1 of 6 Archive leaderboard report
Robot Manipulation Generalization GEMBench 3D-LOTUS++ Average Success Rate (L4) 17.4±0.4 #1 of 6 Archive leaderboard report
Robot Manipulation Generalization GEMBench 3D-LOTUS Average Success Rate 45.7 #2 of 6 Archive leaderboard report
Robot Manipulation Generalization GEMBench 3D-LOTUS Average Success Rate (L1) 94.3±1.4 #2 of 6 Archive leaderboard report
Robot Manipulation Generalization GEMBench 3D-LOTUS Average Success Rate (L2) 49.9±2.2 #2 of 6 Archive leaderboard report
Robot Manipulation Generalization GEMBench 3D-LOTUS Average Success Rate (L3) 38.1±1.1 #2 of 6 Archive leaderboard report
Robot Manipulation Generalization GEMBench 3D-LOTUS Average Success Rate (L4) 0.3±0.3 #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.

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