Papers › OtterHD: A High-Resolution Multi-modality Model

OtterHD: A High-Resolution Multi-modality Model

7 Nov 2023arXiv:2311.04219archive 2025-07-28

Bo Li, Peiyuan Zhang, Jingkang Yang, Yuanhan Zhang, Fanyi Pu, Ziwei Liu

In this paper, we present OtterHD-8B, an innovative multimodal model evolved from Fuyu-8B, specifically engineered to interpret high-resolution visual inputs with granular precision. Unlike conventional models that are constrained by fixed-size vision encoders, OtterHD-8B boasts the ability to handle flexible input dimensions, ensuring its versatility across various inference requirements. Alongside this model, we introduce MagnifierBench, an evaluation framework designed to scrutinize models' ability to discern minute details and spatial relationships of small objects. Our comparative analysis reveals that while current leading models falter on this benchmark, OtterHD-8B, particularly when directly processing high-resolution inputs, outperforms its counterparts by a substantial margin. The findings illuminate the structural variances in visual information processing among different models and the influence that the vision encoders' pre-training resolution disparities have on model effectiveness within such benchmarks. Our study highlights the critical role of flexibility and high-resolution input capabilities in large multimodal models and also exemplifies the potential inherent in the Fuyu architecture's simplicity for handling complex visual data.

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="2311.04219")

Code

Syntology Ran 11 of 14 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 10 ran with no contract checked.

By repository: official repository: 14 samples from 1 repository, 11 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

luodian/otter officialmentioned in papermentioned 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

14 samples harvested; 11 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.

1ran · our draft was wrong
10ran
3unverified

Licence: 0 of the 14 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 luodian/otter. “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.

dropout_add luodian/otter/src/otter_ai/models/falcon/modelling_RW.py official repository ran MIT (permissive) · 6ef9ea8bea823588 · report
extract_frames luodian/otter/pipeline/demos/interactive/otter_video.py official repository ran MIT (permissive) · 029892ebb4321050 · report
get_cast_dtype luodian/otter/pipeline/benchmarks/public_datasets_suite/models/otter.py official repository ran · our draft was wrong MIT (permissive) · dcd422d66b0581d8 · report
get_content_type luodian/otter/pipeline/demos/interactive/otter_image.py official repository ran fingerprinted MIT (permissive) · 3614ed4764f65f90 · report
get_formatted_forward_prompt luodian/otter/pipeline/benchmarks/models/otter_image.py official repository ran fingerprinted MIT (permissive) · 34167f78172c1abe · report
get_formatted_prompt luodian/otter/pipeline/benchmarks/models/otter_image.py official repository ran fingerprinted MIT (permissive) · b48b9a381723c691 · report
get_formatted_prompt luodian/otter/pipeline/demos/interactive/otter_image_incontext.py official repository ran MIT (permissive) · 53f85a97033ac702 · report
get_image luodian/otter/pipeline/demos/interactive/otter_image.py official repository ran MIT (permissive) · fe65bfdd78032556 · report
get_image luodian/otter/pipeline/demos/interactive/otter_video.py official repository ran MIT (permissive) · bdd50d5971d6d069 · report
get_pil_image luodian/otter/pipeline/benchmarks/models/otter_image.py official repository ran MIT (permissive) · 9679b4832e5de332 · report
rotate_half luodian/otter/src/otter_ai/models/falcon/modelling_RW.py official repository ran fingerprinted MIT (permissive) · 2502f906145be7f6 · report
build_alibi_tensor luodian/otter/src/otter_ai/models/falcon/modelling_RW.py official repository unverified MIT (permissive) · b4acc4f0962c97ca · report
get_autocast luodian/otter/pipeline/benchmarks/public_datasets_suite/models/otter.py official repository unverified MIT (permissive) · 94a4076103662faf · report
get_image luodian/otter/pipeline/demos/interactive/otter_image_incontext.py official repository unverified MIT (permissive) · 8dab437d86150725 · report

Tasks

Visual Question Answeringmodel

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Question Answering MM-Vet OtterHD-8B GPT-4 score 26.3 #219 of 231 Archive leaderboard report
Visual Question Answering MM-Vet OtterHD-8B Params 8B #219 of 231 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.

Methods

High-resolution input

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