Pith Number

pith:SZRBHSLR

pith:2023:SZRBHSLRNVZDJUEZMF5UBKC4W5

not attested not anchored not stored refs resolved

Otter: A Multi-Modal Model with In-Context Instruction Tuning

Bo Li, Fanyi Pu, Jinghao Wang, Jingkang Yang, Joshua Adrian Cahyono, Liangyu Chen, Yuanhan Zhang, Ziwei Liu

Otter improves multi-modal instruction following by training on in-context examples from both text and images or videos.

arxiv:2305.03726 v2 · 2023-05-05 · cs.CV · cs.CL

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{SZRBHSLRNVZDJUEZMF5UBKC4W5}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

instruction tuning with these in-context examples substantially enhances model convergence and generalization capabilities. Notably, the extensive scenario coverage provided by the MIMIC-IT dataset empowers the Otter model to excel in tasks involving complex video and multi-image understanding.

C2weakest assumption

That the MIMIC-IT dataset's curation of diverse in-context examples across images and videos produces genuine generalization gains rather than dataset-specific improvements, and that the base Flamingo Perceiver architecture seamlessly supports the added multi-modal in-context inputs without hidden limitations.

C3one line summary

Otter is a multi-modal model instruction-tuned on the MIMIC-IT dataset of over 3 million in-context instruction-response pairs to improve convergence and generalization on tasks with multiple images and videos.

References

104 extracted · 104 resolved · 30 Pith anchors

[1] https://commoncrawl.org/ 2023

[2] What learning algorithm is in-context learning? Investigations with linear models · arXiv:2211.15661

[3] Flamingo: a visual language model for few-shot learning 2022

[4] Flamingo: a visual language model for few-shot learning 2022

[5] Vqa: Visual question answering 2015

Formal links

2 machine-checked theorem links

Cited by

35 papers in Pith

MM-LIMA: Less Is More for Alignment in Multi-Modal Datasets

Q-Agent: Quality-Driven Chain-of-Thought Image Restoration Agent through Robust Multimodal Large Language Model

EntropyScan: Towards Model-level Backdoor Detection in LVLMs via Visual Attention Entropy

AffectVerse: Emotional World Models for Multimodal Affective Computing

Deep Pre-Alignment for VLMs

Receipt and verification

First computed	2026-05-17T23:38:53.781237Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

966213c9716d7234d099617b40a85cb77984fc3acbebb3591451c6e67aa9b5b8

Aliases

arxiv: 2305.03726 · arxiv_version: 2305.03726v2 · doi: 10.48550/arxiv.2305.03726 · pith_short_12: SZRBHSLRNVZD · pith_short_16: SZRBHSLRNVZDJUEZ · pith_short_8: SZRBHSLR

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/SZRBHSLRNVZDJUEZMF5UBKC4W5 \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 966213c9716d7234d099617b40a85cb77984fc3acbebb3591451c6e67aa9b5b8

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "f66dfa86f6dda71fb473e6f79af6934e8e44dc9ecb4cee8807ff533506874aec",
    "cross_cats_sorted": [
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2023-05-05T17:59:46Z",
    "title_canon_sha256": "7f1ada7a3f996e919f83d304f27b98700115314307b314a7a04bb90566b62030"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2305.03726",
    "kind": "arxiv",
    "version": 2
  }
}