Pith Number

pith:KDPB7COA

pith:2026:KDPB7COALUCQHG2XI4EMMWPISE

not attested not anchored not stored refs resolved

N-vium: Mixture-of-Exits Transformer for Accelerated Exact Generation

Aleksander Lorenc, Fr\'ed\'eric Berdoz, Jo\"el Mathys, Roger Wattenhofer

N-vium mixture-of-exits transformers reach 57.9 percent wall-clock speedup at identical perplexity by routing tokens to multiple exit depths

arxiv:2605.13190 v1 · 2026-05-13 · cs.LG · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{KDPB7COALUCQHG2XI4EMMWPISE}

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

Our largest model reaches 57.9% wall-clock speedup over a parameter- and data-matched standard transformer at no perplexity cost.

C2weakest assumption

That a learned mixture over multiple exit heads can be trained to exactly match the perplexity of the full-depth model while enabling the described parallelization, cache deferral, and exact sampling without introducing any quality degradation or training instability.

C3one line summary

N-vium achieves 57.9% wall-clock speedup over matched standard transformers at no perplexity cost by mixing exact predictions from multiple model depths.

References

63 extracted · 63 resolved · 11 Pith anchors

[1] J. Ainslie, J. Lee-Thorp, M. de Jong, Y. Zemlyanskiy, F. Lebron, and S. Sanghai. GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints. InProceedings of the 2023 Confere 2023

[2] K. Alizadeh-Vahid, S. I. Mirzadeh, H. Shahrkokhi, D. Belenko, F. Sun, M. Cho, et al. Duo-LLM: A Framework for Studying Adaptive Computation in Large Language Models. InProceedings of The 4th NeurIPS E 2024

[3] S. Bae, J. Ko, H. Song, and S.-Y. Yun. Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding. InProceedings of the 2023 Conference on Empirical 2023

[4] S. Bae, Y. Kim, R. Bayat, S. Kim, J. Ha, T. Schuster, et al. Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation. InAd- vances in Neural Information Processin 2025

[5] H. Bai, W. Zhang, L. Hou, L. Shang, J. Jin, X. Jiang, et al. BinaryBERT: Pushing the Limit of BERT Quantization. InProceedings of the 59th Annual Meeting of the Association for Computational Linguisti 2021

Receipt and verification

First computed	2026-05-18T03:08:56.145858Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

50de1f89c05d05039b574708c659e89120d4f19409f9ee45ac890b2f319f3913

Aliases

arxiv: 2605.13190 · arxiv_version: 2605.13190v1 · doi: 10.48550/arxiv.2605.13190 · pith_short_12: KDPB7COALUCQ · pith_short_16: KDPB7COALUCQHG2X · pith_short_8: KDPB7COA

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/KDPB7COALUCQHG2XI4EMMWPISE \
  | 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: 50de1f89c05d05039b574708c659e89120d4f19409f9ee45ac890b2f319f3913

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "1e1ac88a055099cfdb6e12170cef87de7ecc32b4cb9e7972ff004652fd01905c",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T08:46:17Z",
    "title_canon_sha256": "3d9415796db25435ae41ab4a4cd2e87e32e056dc649fabfd0cbc9e28ed2ec808"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13190",
    "kind": "arxiv",
    "version": 1
  }
}