Pith Number

pith:SNWXRQHX

pith:2026:SNWXRQHXSMFC5Q3I7ZQ6NH25HL

not attested not anchored not stored refs pending

Symbiotic-MoE: Unlocking the Synergy between Generation and Understanding

Liefeng Bo, Miles Yang, Ping Tan, Xiangyue Liu, Zhao Zhong, Zijian Zhang

Symbiotic-MoE lets generative training improve rather than degrade understanding in multimodal models through shared experts and staged optimization.

arxiv:2604.07753 v2 · 2026-04-09 · cs.CV · cs.CL · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{SNWXRQHXSMFC5Q3I7ZQ6NH25HL}

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

Symbiotic-MoE resolves task interference within a native multimodal Mixture-of-Experts (MoE) Transformers architecture with zero-parameter overhead... boosting inherent understanding with remarkable gains on MMLU and OCRBench.

C2weakest assumption

That partitioning experts into task-specific groups with shared experts as a semantic bridge will allow generative signals to enrich understanding without routing collapse or negative interference, and that the progressive training will reliably convert early volatility into constructive feedback.

C3one line summary

Symbiotic-MoE introduces modality-aware expert disentanglement and progressive training in a multimodal MoE to achieve synergistic generation and understanding without task interference or extra parameters.

Formal links

2 machine-checked theorem links

Cited by

1 paper in Pith

Rosetta: Composable Native Multimodal Pretraining

Receipt and verification

First computed	2026-06-30T01:16:29.829478Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

936d78c0f7930a2ec368fe61e69f5d3afb5a4639ef0e54b8377f30f5dae4d64b

Aliases

arxiv: 2604.07753 · arxiv_version: 2604.07753v2 · doi: 10.48550/arxiv.2604.07753 · pith_short_12: SNWXRQHXSMFC · pith_short_16: SNWXRQHXSMFC5Q3I · pith_short_8: SNWXRQHX

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/SNWXRQHXSMFC5Q3I7ZQ6NH25HL \
  | 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: 936d78c0f7930a2ec368fe61e69f5d3afb5a4639ef0e54b8377f30f5dae4d64b

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "3a7c974c957afe2e91fedebdfd41e359a41e6a1d67db357c3637d33c3051d304",
    "cross_cats_sorted": [
      "cs.CL",
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-04-09T03:19:26Z",
    "title_canon_sha256": "bbbeb227bfdec82715f3263b3028322eae1c86f51cd9433d03095c3e13b8bd4e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.07753",
    "kind": "arxiv",
    "version": 2
  }
}