pith. sign in
Pith Number

pith:RFRSJ5YL

pith:2023:RFRSJ5YLLMIJLAMZFAPJE43BNM
not attested not anchored not stored refs resolved

PandaGPT: One Model To Instruction-Follow Them All

Deng Cai, Huayang Li, Jialu Xu, Tian Lan, Yan Wang, Yixuan Su

A single model trained only on image-text pairs can follow instructions on video, audio, depth, and thermal inputs by composing their meanings in a shared embedding space.

arxiv:2305.16355 v1 · 2023-05-25 · cs.CL · cs.CV

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{RFRSJ5YLLMIJLAMZFAPJE43BNM}

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

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

PandaGPT displays emergent, i.e. zero-shot, cross-modal behaviors for data other than image and text (e.g., video, audio, depth, thermal, and IMU) and can take multimodal inputs simultaneously and compose their semantics naturally.

C2weakest assumption

That ImageBind's embedding space is already semantically rich enough for the language model to compose meanings across modalities without any further alignment training on those modalities.

C3one line summary

A single model trained only on image-text pairs gains instruction-following ability across images, video, and audio by routing all modalities through ImageBind's shared embedding space into Vicuna.

References

32 extracted · 32 resolved · 8 Pith anchors

[1] Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, et al. 2022. Flamingo: a visual language model 2022
[2] Jean-Baptiste Alayrac, Adria Recasens, Rosalia Schneider, Relja Arandjelovi´c, Jason Rama- puram, Jeffrey De Fauw, Lucas Smaira, Sander Dieleman, and Andrew Zisserman. 2020. Self-supervised multimodal 2020
[3] Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot lear 2020
[4] Gonzalez, Ion Stoica, and Eric P 2023
[5] Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the N 2019

Formal links

2 machine-checked theorem links

Cited by

29 papers in Pith

Receipt and verification
First computed 2026-05-17T23:38:48.430132Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

896324f70b5b10958199281e9273616b3b1c9cba067746a5a493e96d395ec151

Aliases

arxiv: 2305.16355 · arxiv_version: 2305.16355v1 · doi: 10.48550/arxiv.2305.16355 · pith_short_12: RFRSJ5YLLMIJ · pith_short_16: RFRSJ5YLLMIJLAMZ · pith_short_8: RFRSJ5YL
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/RFRSJ5YLLMIJLAMZFAPJE43BNM \
  | 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: 896324f70b5b10958199281e9273616b3b1c9cba067746a5a493e96d395ec151
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "a33eb1f75754eee664c50c5a05cfef2ea5b7c32e181ab55bcafee2f43fdb58d5",
    "cross_cats_sorted": [
      "cs.CV"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2023-05-25T04:16:07Z",
    "title_canon_sha256": "bbbc8f4530482ee4a7ed90c8764467b8790d3a9d3a102881526d4cdb5d5655bd"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2305.16355",
    "kind": "arxiv",
    "version": 1
  }
}