SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.07973 · 2024

Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 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; 4 failures of our instrument; 1 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/2404.07973.json · badge: /api/ran/2404.07973.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
copy not recorded community
not in the paper's declared repositories
4 ran · 1 no recorded run
FunctionStatusWhere it lives
generate_mask_for_feature Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from apple/ml-ferret
pointer only; the stored copy get_code serves, from apple/ml-ferret, is pointer only (licence: NOASSERTION) · get_code("974d957b09ee69d2")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

point_sample Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from apple/ml-ferret
pointer only; the stored copy get_code serves, from apple/ml-ferret, is pointer only (licence: NOASSERTION) · get_code("55e4e4a151814912")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

rand_sample Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from apple/ml-ferret
pointer only; the stored copy get_code serves, from apple/ml-ferret, is pointer only (licence: NOASSERTION) · get_code("490cd3fba7ed0f15")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

rand_sample_repeat Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from apple/ml-ferret
pointer only; the stored copy get_code serves, from apple/ml-ferret, is pointer only (licence: NOASSERTION) · get_code("7f94db7c29cc4f44")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

draw_box Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from apple/ml-ferret
pointer only; the stored copy get_code serves, from apple/ml-ferret, is pointer only (licence: NOASSERTION) · get_code("a449641f4bef63f1")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 2 later) and 0 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
draw_box 2 other papers
1 dated earlier, 1 later
2310.07704 (2023-10)
Ferret: Refer and Ground Anything Anywhere at Any Granularity
2409.06277 (2024-09)
Ferret: Federated Full-Parameter Tuning at Scale for Large Language Models
generate_mask_for_feature 2 other papers
1 dated earlier, 1 later
2310.07704 (2023-10)
Ferret: Refer and Ground Anything Anywhere at Any Granularity
2409.06277 (2024-09)
Ferret: Federated Full-Parameter Tuning at Scale for Large Language Models
point_sample 1 other paper
1 dated earlier
2310.07704 (2023-10)
Ferret: Refer and Ground Anything Anywhere at Any Granularity
rand_sample 1 other paper
1 dated earlier
2310.07704 (2023-10)
Ferret: Refer and Ground Anything Anywhere at Any Granularity
rand_sample_repeat 1 other paper
1 dated earlier
2310.07704 (2023-10)
Ferret: Refer and Ground Anything Anywhere at Any Granularity

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

While Ferret seamlessly integrates regional understanding into the Large Language Model (LLM) to facilitate its referring and grounding capability, it poses certain limitations: constrained by the pre-trained fixed visual encoder and failed to perform well on broader tasks. In this work, we unveil Ferret-v2, a significant upgrade to Ferret, with three key designs. (1) Any resolution grounding and referring: A flexible approach that effortlessly handles higher image resolution, improving the model's ability to process and understand images in greater detail. (2) Multi-granularity visual encoding: By integrating the additional DINOv2 encoder, the model learns better and diverse underlying contexts for global and fine-grained visual information. (3) A three-stage training paradigm: Besides image-caption alignment, an additional stage is proposed for high-resolution dense alignment before the final instruction tuning. Experiments show that Ferret-v2 provides substantial improvements over Ferret and other state-of-the-art methods, thanks to its high-resolution scaling and fine-grained visual processing.

For agents

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

get_harvested_code_for_paper("2404.07973")
get_code_for_paper("2404.07973")
have("2404.07973")

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

curl https://syntology.ai/api/ran/2404.07973.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.07973.svg)](https://syntology.ai/paper/2404.07973)

Connect an agent — have() is free.