SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.01942 · ECCV · 2024

Visual Grounding for Object-Level Generalization in Reinforcement Learning

Zongqing Lu, Haobin Jiang

arXiv · PDF · Open in the Atlas

Code that ran

1 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2408.01942.json · badge: /api/ran/2408.01942.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
PKU-RL/COPL community
Papers with Code archive
1 ran · 3 no recorded run
FunctionStatusWhere it lives
get_model_full_name Ran
ran; our contract draft was wrong, not the code
PKU-RL/COPL/src/envs/clip.py
code served (permissive licence) · get_code("1304ba63cfc56f2f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function get_model_full_name takes a single parameter: model_name (a string)
# It checks if model_name matches certain known model names and returns the full name
# No complex objects needed - just a string parameter

ARGS = {
    'model_name': 'bert'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
CLIPReward Not yet run
unverified (harvested, no recorded run)
PKU-RL/COPL/src/envs/clip.py
code served (permissive licence) · get_code("b15b62f8c22d642c")
How it ran

no invocation recorded.

get_tokenizer Not yet run
unverified (harvested, no recorded run)
PKU-RL/COPL/src/envs/clip.py
code served (permissive licence) · get_code("166dbbe98faad862")
How it ran

no invocation recorded.

tokenize_batch Not yet run
unverified (harvested, no recorded run)
PKU-RL/COPL/src/envs/clip.py
code served (permissive licence) · get_code("fd1002da079932d1")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
CLIPReward
brick of this paper's assembly: entry
1 other paper
1 dated earlier
2206.08853 (2022-06)
MINEDOJO: Building Open-Ended Embodied Agents with Internet-Scale Knowledge

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Generalization is a pivotal challenge for agents following natural language instructions. To approach this goal, we leverage a visionlanguage model (VLM) for visual grounding and transfer its visionlanguage knowledge into reinforcement learning (RL) for object-centric tasks, which makes the agent capable of zero-shot generalization to unseen objects and instructions. By visual grounding, we obtain an objectgrounded confidence map for the target object indicated in the instruction. Based on this map, we introduce two routes to transfer VLM knowledge into RL. Firstly, we propose an object-grounded intrinsic reward function derived from the confidence map to more effectively guide the agent towards the target object. Secondly, the confidence map offers a more unified, accessible task representation for the agent's policy, compared to language embeddings. This enables the agent to process unseen objects and instructions through comprehensible visual confidence maps, facilitating zero-shot object-level generalization. Single-task experiments prove that our intrinsic reward significantly improves performance on challenging skill learning. In multi-task experiments, through testing on tasks beyond the training set, we show that the agent, when provided with the confidence map as the task representation, possesses better generalization capabilities than language-based conditioning. The code is available at https://github.com/PKU-RL/COPL.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2408.01942")
get_code_for_paper("2408.01942")
have("2408.01942")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2408.01942.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2408.01942.svg)](https://syntology.ai/paper/2408.01942)

Connect an agent — have() is free.