Papers › Otter: A Multi-Modal Model with In-Context Instruction Tuning
Otter: A Multi-Modal Model with In-Context Instruction Tuning
Bo Li, Yuanhan Zhang, Liangyu Chen, Jinghao Wang, Jingkang Yang, Ziwei Liu
Large language models (LLMs) have demonstrated significant universal capabilities as few/zero-shot learners in various tasks due to their pre-training on vast amounts of text data, as exemplified by GPT-3, which boosted to InstrctGPT and ChatGPT, effectively following natural language instructions to accomplish real-world tasks. In this paper, we propose to introduce instruction tuning into multi-modal models, motivated by the Flamingo model's upstream interleaved format pretraining dataset. We adopt a similar approach to construct our MultI-Modal In-Context Instruction Tuning (MIMIC-IT) dataset. We then introduce Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following ability and in-context learning. We also optimize OpenFlamingo's implementation for researchers, democratizing the required training resources from 1× A100 GPU to 4× RTX-3090 GPUs, and integrate both OpenFlamingo and Otter into Huggingface Transformers for more researchers to incorporate the models into their customized training and inference pipelines.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_citation_path(paper_1="2305.03726", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2305.03726")
Code
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.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
1 archive task tag without a task page not shown.
Datasets
Introduced by this paper, per the archive.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Visual Question Answering | BenchLMM | Otter-7B | GPT-3.5 score | 39.13 | #8 of 10 | Archive leaderboard | report |
| Visual Question Answering (VQA) | InfiMM-Eval | Otter | Abductive | 33.64 | #10 of 14 | Archive leaderboard | report |
| Visual Question Answering (VQA) | InfiMM-Eval | Otter | Analogical | 13.33 | #10 of 14 | Archive leaderboard | report |
| Visual Question Answering (VQA) | InfiMM-Eval | Otter | Deductive | 22.49 | #10 of 14 | Archive leaderboard | report |
| Visual Question Answering (VQA) | InfiMM-Eval | Otter | Overall score | 22.69 | #10 of 14 | Archive leaderboard | report |
| Visual Question Answering (VQA) | InfiMM-Eval | Otter | Params | 7B | #10 of 14 | 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
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