ARXIV:2603.04971 · AI SCALABILITY · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

Mixture of Universal Experts: Scaling Virtual Width via Depth-Width Transformation

arXiv

An approach to increase the scalability of Mixture-of-Experts models by transforming depth into virtual width using a universal expert pool.

Blocked on Code›Score3.0Evidence unverified

Opportunity summary

Pain An approach to increase the scalability of Mixture-of-Experts models by transforming depth into virtual width using a universal expert pool.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

An approach to increase the scalability of Mixture-of-Experts models by transforming depth into virtual width using a universal expert pool. To overcome this, we propose Mixture of Universal Experts (MOUE),a MoE generalization introducing a…

METHOD

Full abstract

Mixture-of-Experts (MoE) decouples model capacity from per-token computation, yet their scalability remains limited by the physical dimensions of depth and width. To overcome this, we propose Mixture of Universal Experts (MOUE),a MoE generalization introducing a novel scaling dimension: Virtual Width. In general, MoUE aims to reuse a universal layer-agnostic expert pool across layers, converting depth into virtual width under a fixed per-token activation budget. However, two challenges remain: a routing path explosion from recursive expert reuse, and a mismatch between the exposure induced by reuse and the conventional load-balancing objectives. We address these with three core components: a Staggered Rotational Topology for structured expert sharing, a Universal Expert Load Balance for depth-aware exposure correction, and a Universal Router with lightweight trajectory state for coherent multi-step routing. Empirically, MoUE consistently outperforms matched MoE baselines by up to 1.3% across scaling regimes, enables progressive conversion of existing MoE checkpoints with up to 4.2% gains, and reveals a new scaling dimension for MoE architectures.

RESULT

ScienceToStartup currently rates this 3.0/10 on the public viability pass. Empirically, MoUE consistently outperforms matched MoE baselines by up to 1.3% across scaling regimes, enables progressive conversion of existing MoE checkpoints with up to…

WHY NOW

AI Scalability moved forward this cycle; last verified April 2026. Public score 3.0/10.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score3.0

PainAn approach to increase the scalability of Mixture-of-Experts models by transforming depth into virtual width using a universal expert pool.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

An approach to increase the scalability of Mixture-of-Experts models by transforming depth into virtual width using a universal expert pool.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

ARXIV:2603.04971 · AI SCALABILITY · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

Mixture of Universal Experts: Scaling Virtual Width via Depth-Width Transformation

arXiv

An approach to increase the scalability of Mixture-of-Experts models by transforming depth into virtual width using a universal expert pool.

Blocked on Code›Score3.0Evidence unverified

Opportunity summary

Pain An approach to increase the scalability of Mixture-of-Experts models by transforming depth into virtual width using a universal expert pool.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

METHOD

Full abstract

RESULT

WHY NOW

AI Scalability moved forward this cycle; last verified April 2026. Public score 3.0/10.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score3.0

PainAn approach to increase the scalability of Mixture-of-Experts models by transforming depth into virtual width using a universal expert pool.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

An approach to increase the scalability of Mixture-of-Experts models by transforming depth into virtual width using a universal expert pool.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

Paper Pack

10.48550/arXiv.2603.04971

Mixture of Universal Experts: Scaling Virtual Width via Depth-Width Transformation

An approach to increase the scalability of Mixture-of-Experts models by transforming depth into virtual width using a universal expert pool.

Abstract

Source availability

PDF linked

The paper record includes a public PDF URL.

Extraction status

Derived fallback

Read summaries are estimated from adjacent metadata, not verified extraction rows.

Proof status

unverified

0 refs; 0 sources; 17% coverage.

What was readable

linkedon filenot materializedderived fallback34 indexednot indexed

Derived fallback: Estimated from adjacent evidence; not verified from source.

Viability

3.0

Time to MVP

MVP estimate missing

Commercial

No commercial flags on file

Export

Preparing verified analysis

lens / founder

PROBLEM

METHOD

RESULT

WHY NOW

AI Scalability moved forward this cycle; last verified April 2026. Public score 3.0/10.

Claim map

Abstract-backed public claims while anchored extraction refreshes.

Strong 0Mixed 0Weak 4

Evidencepartial
An approach to increase the scalability of Mixture-of-Experts models by transforming depth into virtual width using a universal expert pool. To overcome this, we propose Mixture of Universal Experts (MOUE),a MoE generalization introducing a novel scaling dimension: Virtual Width.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Mixture-of-Experts (MoE) decouples model capacity from per-token computation, yet their scalability remains limited by the physical dimensions of depth and width. To overcome this, we propose Mixture of Universal Experts (MOUE),a MoE generalization introducing a novel scaling dimension: Virtual Width.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
ScienceToStartup currently rates this 3.0/10 on the public viability pass. Empirically, MoUE consistently outperforms matched MoE baselines by up to 1.3% across scaling regimes, enables progressive conversion of existing MoE checkpoints with up to 4.2% gains, and reveals a new scaling dimension for MoE architectures.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
AI Scalability moved forward this cycle; last verified April 2026. Public score 3.0/10.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial

Constellation map

Paper-native neighborhood for concepts, methods, materials, markets, and competitors. Missing lanes stay labeled instead of disappearing behind commercialization gates.

Open full Signal Canvas

Concepts

not indexed

Methods

Materials

PDF linked

Markets

AI Scalability

Competitors

not indexed

Competitive landscape

An approach to increase the scalability of Mixture-of-Experts models by transforming depth into virtual width using a universal expert pool.

Segment

AI Scalability

Adoption evidence

No public code link in the paper record yet

Commercial read

3.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

Buzz

No indexed public discussion is attached to 2603.04971 yet. That is a visibility signal, not a blank module: the monitor is watching the public channels below.

Hacker News

Not indexed yet

Bluesky

Not indexed yet

PDF

Preview the source document here, or use the hero PDF action for a new tab.

References(34)

Elastic MoE: Unlocking the Inference-Time Scalability of Mixture-of-Experts

2025Naibin Gu, Zhenyu Zhang et al.

DIVE into MoE: Diversity-Enhanced Reconstruction of Large Language Models from Dense into Mixture-of-Experts

2025Yuchen Feng, Bowen Shen et al.

Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking

2025Yilong Chen, Junyuan Shang et al.

Mixture of Hidden-Dimensions: Not All Hidden-States' Dimensions are Needed in Transformer

2025Yilong Chen, Junyuan Shang et al.

Training Large Language Models to Reason in a Continuous Latent Space

2024Shibo Hao, Sainbayar Sukhbaatar et al.

Loop Neural Networks for Parameter Sharing

2024Kei-Sing Ng, Qingchen Wang

OLMoE: Open Mixture-of-Experts Language Models

2024Niklas Muennighoff, Luca Soldaini et al.

DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion

2024Yilong Chen, Linhao Zhang et al.

JetMoE: Reaching Llama2 Performance with 0.1M Dollars

2024Yikang Shen, Zhen Guo et al.

Scaling Laws for Fine-Grained Mixture of Experts

2024Jakub Krajewski, Jan Ludziejewski et al.

Mixtral of Experts

2024Albert Q. Jiang, Alexandre Sablayrolles et al.

LEMON: Reviving Stronger and Smaller LMs from Larger LMs with Linear Parameter Fusion

2024Yilong Chen, Junyuan Shang et al.

Implicit Chain of Thought Reasoning via Knowledge Distillation

2023Yuntian Deng, K. Prasad et al.

From Sparse to Soft Mixtures of Experts

2023J. Puigcerver, C. Riquelme et al.

Accelerating Distributed MoE Training and Inference with Lina

2022Jiamin Li, Yimin Jiang et al.

Training Compute-Optimal Large Language Models

2022Jordan Hoffmann, Sebastian Borgeaud et al.

Mixture-of-Experts with Expert Choice Routing

2022Yan-Quan Zhou, Tao Lei et al.

Hash Layers For Large Sparse Models

2021Stephen Roller, Sainbayar Sukhbaatar et al.

BASE Layers: Simplifying Training of Large, Sparse Models

2021M. Lewis, Shruti Bhosale et al.

Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity

2021W. Fedus, Barret Zoph et al.

Showing 20 of 34 references

CITED BY

No citing papers are indexed in the public S2S graph yet. This is an explicit zero-signal state, not a hidden lookup.

Foundation

Prior WorkExpert Upcycling: Shifting the Compute-Efficient Frontier of Mixture-of-Experts

3.0

Prior WorkHolistic Scaling Laws for Optimal Mixture-of-Experts Architecture Optimization

3.0

Prior WorkEfficient Quantization of Mixture-of-Experts with Theoretical Generalization Guarantees

3.0

Extension

Builds On ThisGeneralization and Scaling Laws for Mixture-of-Experts Transformers

2.0

Commercially relevant

Higher ViabilityMoE Lens -- An Expert Is All You Need

7.0

Higher ViabilityPath-Constrained Mixture-of-Experts

7.0

Higher ViabilityDynaMoE: Dynamic Token-Level Expert Activation with Layer-Wise Adaptive Capacity for Mixture-of-Experts Neural Networks

6.0

Higher ViabilityRouting-Free Mixture-of-Experts

7.0

Higher ViabilityOmniMoE: An Efficient MoE by Orchestrating Atomic Experts at Scale

7.0

Higher ViabilityPruning and Distilling Mixture-of-Experts into Dense Language Models

6.0

Conflicting

none indexed

Related Resources

How can commercial challenges in AI scalability be overcome with model optimization?(question)

Owned Distribution

Subscribe to the weekly brief

Get the weekly shortlist of commercializable papers, benchmark movers, and proof receipts that matter for product execution.

Agent drawer

5 surfaces preserved for agents. Humans can ignore.

Developer contracts, payload previews, evidence maps, and run controls stay here instead of the Read, Build, and Track workspace.

Run context

Paper: 2603.04971
Route: /paper/mixture-of-universal-experts-scaling-virtual-width-via-depth-width-transformation
Active tab: read
Artifact: mixture-of-universal-experts-scaling-virtual-width-via-depth-width-transformation

Available agents

Read extractor
Build planner
Track monitor
Competitive mapper
Related-paper scout

API/MCP endpoints

REST paper pack API/api/v1/paper/mixture-of-universal-experts-scaling-virtual-width-via-depth-width-transformation/paper-pack
REST build passport API/api/v1/paper/mixture-of-universal-experts-scaling-virtual-width-via-depth-width-transformation/build-passport
REST OpenAPI/api/openapi.json
MCP descriptor/api/mcp
MCP resourcesciencetostartup://surfaces/paper-workspace

Tool contracts

paper_packbuild_passportopportunity_kernelforesightsource_proofevidence_state

Payload preview

Inspect payload

{
  "contract_version": "paper-r2",
  "paper_id": "bdc2fa47-7549-4bdb-acc5-b7ca7e6ae45c",
  "arxiv_id": "2603.04971",
  "canonical_route": "/paper/mixture-of-universal-experts-scaling-virtual-width-via-depth-width-transformation",
  "active_tab": "synced from current hash by the drawer client",
  "selected_artifact": "mixture-of-universal-experts-scaling-virtual-width-via-depth-width-transformation",
  "endpoints": {
    "paper_pack": "/api/v1/paper/mixture-of-universal-experts-scaling-virtual-width-via-depth-width-transformation/paper-pack",
    "build_passport": "/api/v1/paper/mixture-of-universal-experts-scaling-virtual-width-via-depth-width-transformation/build-passport",
    "mcp_resource": "sciencetostartup://surfaces/paper-workspace"
  }
}

Schema validation

paper-r2 contract: present
JSON-LD twin: SSR emitted
OpenAPI path parity: /api/openapi.json
MCP resource parity: paper-workspace

Job trace

queued: drawer opened by user action
running: inspect or copy payload
succeeded: payload available in SSR
failed: route errors appear in evidence cards

Evidence map

sources used: page freshness, source proof anchors, JSON-LD
missing sources: exposed by PaperPack and EvidenceState chips
derived fallbacks: marked unverified before handoff

Page Freshness

Canonical route, proof status, last verified, refs, sources, and coverage.

Page Freshness

Paper proof surface

Canonical route: /paper/mixture-of-universal-experts-scaling-virtual-width-via-depth-width-transformation

stale

Proof freshness: stale
Proof status: unverified
Display score: 3/10
Last proof check: 2026-04-02
Score updated: 2026-04-02
Score fresh until: 2026-05-02
References: 0
Source count: 0
Coverage: 17%

This page is showing the last landed evidence receipt and score bundle because the latest proof data is outside the freshness window.

OpenAlex: pending — this preprint is not yet indexed by OpenAlex.

Agent Handoff

Endpoint list, payload shape, route context, and copyable handoff data.

Agent Handoff

Mixture of Universal Experts: Scaling Virtual Width via Depth-Width Transformation

Canonical ID mixture-of-universal-experts-scaling-virtual-width-via-depth-width-transformation | Route /paper/mixture-of-universal-experts-scaling-virtual-width-via-depth-width-transformation

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/paper/mixture-of-universal-experts-scaling-virtual-width-via-depth-width-transformation

MCP example

{
  "tool": "get_paper",
  "arguments": {
    "arxiv_id": "2603.04971"
  }
}

source_context

{
  "surface": "paper",
  "mode": "paper",
  "query": "Mixture of Universal Experts: Scaling Virtual Width via Depth-Width Transformation",
  "normalized_query": "2603.04971",
  "route": "/paper/mixture-of-universal-experts-scaling-virtual-width-via-depth-width-transformation",
  "paper_ref": "mixture-of-universal-experts-scaling-virtual-width-via-depth-width-transformation",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Buildability Receipt

Verdict, compute envelope, blockers, signature state, and receipt links.

Paper proof page receipt window

Not build-ready: Mixture of Universal Experts: Scaling Virtual Width via Depth-Width Transformation

/buildability/mixture-of-universal-experts-scaling-virtual-width-via-depth-width-transformation

Ignoreblocked

Subject: Mixture of Universal Experts: Scaling Virtual Width via Depth-Width Transformation

Verdict

Ignore

Verdict is Ignore because current viability and proof state do not clear the buildability gate.

Time to first demo

Insufficient data

No first-demo timestamp, owner estimate, or elapsed demo receipt is attached to this surface.

Compute envelope

Structured compute envelope

Insufficient data

No data, compute, hardware, memory, latency, dependency, or serving requirement receipt is attached.

Evidence ids

Receipt path

/buildability/mixture-of-universal-experts-scaling-virtual-width-via-depth-width-transformation

Paper ref

mixture-of-universal-experts-scaling-virtual-width-via-depth-width-transformation

arXiv id

2603.04971

Freshness

Generated at

2026-04-02T02:30:40.136Z

Evidence freshness

stale

Last verification

2026-04-02T02:30:40.136Z

Sources

References

Coverage

17%

Hash state

Lineage hash

336bbbb22efd1878aa24eb8697e2b0dcea99f48b9b845b6ea87cd1c8e6ecf88e

Canonical opportunity-kernel lineage hash.

Signature state

External signature

unsigned_external

No founder, registry, pilot, or production-adoption signature is attached to this receipt.

Verification

not_verified

Verification is blocked until an external signature is provided.

Blockers

Missing: repo_url
Missing: references
Missing: proof_status
Missing: distribution_readiness_scores
Missing: paper_extraction_scorecards
Unknown: distribution readiness has not been computed yet
Unknown: proof verification has not been recorded yet

Verification pending / evidence receipt incomplete

repo_url

references

Missing proof, requirement, signature, approval, adoption, or telemetry fields are blockers and must not be inferred.

Open receipt API receipt Build Loop Signal Canvas Proof divergence Divergence API Brier outcomes API

Source Proof anchors

Visual citations from the paper document graph.

JSON-LD twin

The application/ld+json payload rendered for agents.

{
  "@context": "https://schema.org",
  "@graph": [
    {
      "@type": "WebPage",
      "@id": "https://sciencetostartup.com/paper/mixture-of-universal-experts-scaling-virtual-width-via-depth-width-transformation#webpage",
      "url": "https://sciencetostartup.com/paper/mixture-of-universal-experts-scaling-virtual-width-via-depth-width-transformation",
      "name": "Mixture of Universal Experts: Scaling Virtual Width via Depth-Width Transformation",
      "description": "An approach to increase the scalability of Mixture-of-Experts models by transforming depth into virtual width using a universal expert pool.",
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      }
    },
    {
      "@type": "ScholarlyArticle",
      "@id": "https://sciencetostartup.com/paper/mixture-of-universal-experts-scaling-virtual-width-via-depth-width-transformation#scholarlyArticle",
      "headline": "Mixture of Universal Experts: Scaling Virtual Width via Depth-Width Transformation",
      "description": "An approach to increase the scalability of Mixture-of-Experts models by transforming depth into virtual width using a universal expert pool.",
      "url": "https://sciencetostartup.com/paper/mixture-of-universal-experts-scaling-virtual-width-via-depth-width-transformation",
      "sameAs": "https://arxiv.org/abs/2603.04971",
      "identifier": {
        "@type": "PropertyValue",
        "propertyID": "arXiv",
        "value": "2603.04971"
      },
      "isAccessibleForFree": true,
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      },
      "datePublished": "2026-03-05T09:07:45.000Z",
      "citation": [
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "1a1a5ecbfc527612fccfec520b185e289684f0e3"
          },
          "url": "https://www.semanticscholar.org/paper/1a1a5ecbfc527612fccfec520b185e289684f0e3"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "0ff61e24cd87d29d5d2d1df4f486775ff9d82430"
          },
          "url": "https://www.semanticscholar.org/paper/0ff61e24cd87d29d5d2d1df4f486775ff9d82430"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "b7486c55d0e0082916719b6e4d7632fd98316a2b"
          },
          "url": "https://www.semanticscholar.org/paper/b7486c55d0e0082916719b6e4d7632fd98316a2b"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "673fbdd957cada770d10dffca5e45b53da43a3c6"
          },
          "url": "https://www.semanticscholar.org/paper/673fbdd957cada770d10dffca5e45b53da43a3c6"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "ea710f561197638d10066758307213f634fc7808"
          },
          "url": "https://www.semanticscholar.org/paper/ea710f561197638d10066758307213f634fc7808"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "817632c42e735911e14b89e851ceaf54ba2ad25f"
          },
          "url": "https://www.semanticscholar.org/paper/817632c42e735911e14b89e851ceaf54ba2ad25f"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "c7557bdeb8a63bc675e8a24c62a30052895e1c1f"
          },
          "url": "https://www.semanticscholar.org/paper/c7557bdeb8a63bc675e8a24c62a30052895e1c1f"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "c9ff9fbbe21985b35d6a070b67f22a0e065c4328"
          },
          "url": "https://www.semanticscholar.org/paper/c9ff9fbbe21985b35d6a070b67f22a0e065c4328"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "9548bacc4c7714151b674748dc86e2cc185a4955"
          },
          "url": "https://www.semanticscholar.org/paper/9548bacc4c7714151b674748dc86e2cc185a4955"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "411114f989a3d1083d90afd265103132fee94ebe"
          },
          "url": "https://www.semanticscholar.org/paper/411114f989a3d1083d90afd265103132fee94ebe"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "4411e6b32865933cab87696c2738cb7a204e4240"
          },
          "url": "https://www.semanticscholar.org/paper/4411e6b32865933cab87696c2738cb7a204e4240"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "2edccb8fa562ed52cd49ea6fc67ed32db6218247"
          },
          "url": "https://www.semanticscholar.org/paper/2edccb8fa562ed52cd49ea6fc67ed32db6218247"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "6d088e8d785a57b50c2b0e465e2460e09ced48d7"
          },
          "url": "https://www.semanticscholar.org/paper/6d088e8d785a57b50c2b0e465e2460e09ced48d7"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "8342b592fe238f3d230e4959b06fd10153c45db1"
          },
          "url": "https://www.semanticscholar.org/paper/8342b592fe238f3d230e4959b06fd10153c45db1"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "bbc57e1b3cf90e09b64377f13de455793bc81ad5"
          },
          "url": "https://www.semanticscholar.org/paper/bbc57e1b3cf90e09b64377f13de455793bc81ad5"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "0611d2f2ea6a3c8fb8534f42758a5a3e9c7bc8fe"
          },
          "url": "https://www.semanticscholar.org/paper/0611d2f2ea6a3c8fb8534f42758a5a3e9c7bc8fe"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "b15ea460c77a4ee8aa159a30ab0331deedfcf392"
          },
          "url": "https://www.semanticscholar.org/paper/b15ea460c77a4ee8aa159a30ab0331deedfcf392"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "fdacf2a732f55befdc410ea927091cad3b791f13"
          },
          "url": "https://www.semanticscholar.org/paper/fdacf2a732f55befdc410ea927091cad3b791f13"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "1882f194cb43828852cc052887671e55a80f945a"
          },
          "url": "https://www.semanticscholar.org/paper/1882f194cb43828852cc052887671e55a80f945a"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "e6c561d02500b2596a230b341a8eb8b921ca5bf2"
          },
          "url": "https://www.semanticscholar.org/paper/e6c561d02500b2596a230b341a8eb8b921ca5bf2"
        }
      ],
      "additionalProperty": [
        {
          "@type": "PropertyValue",
          "propertyID": "viabilityScore",
          "value": 3
        },
        {
          "@type": "PropertyValue",
          "propertyID": "researchDomain",
          "value": "AI Scalability"
        }
      ]
    },
    {
      "@type": "BreadcrumbList",
      "itemListElement": [
        {
          "@type": "ListItem",
          "position": 1,
          "name": "Home",
          "item": "https://sciencetostartup.com"
        },
        {
          "@type": "ListItem",
          "position": 2,
          "name": "AI Scalability",
          "item": "https://sciencetostartup.com/topics"
        },
        {
          "@type": "ListItem",
          "position": 3,
          "name": "Mixture of Universal Experts: Scaling Virtual Width via Dept",
          "item": "https://sciencetostartup.com/paper/mixture-of-universal-experts-scaling-virtual-width-via-depth-width-transformation"
        }
      ]
    }
  ]
}

Mixture of Universal Experts: Scaling Virtual Width via Depth-Width Transformation

Mixture of Universal Experts: Scaling Virtual Width via Depth-Width Transformation

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(34)

Related Papers

Related Resources

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(34)

Related Papers

Related Resources

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline