ARXIV:2601.16622 · GRAPH NEURAL NETWORKS · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

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

E2Former-V2: On-the-Fly Equivariant Attention with Linear Activation Memory

arXiv

E2Former-V2 enhances scalable EGNNs for 3D atomistic modeling with 20x TFLOPS efficiency, making it accessible on standard GPUs.

Blocked on Code›Score5.0Evidence unverified

Opportunity summary

Pain E2Former-V2 enhances scalable EGNNs for 3D atomistic modeling with 20x TFLOPS efficiency, making it accessible on standard GPUs.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

E2Former-V2 enhances scalable EGNNs for 3D atomistic modeling with 20x TFLOPS efficiency, making it accessible on standard GPUs. However, mainstream architectures face critical scalability bottlenecks due to the explicit construction of geometric features or…

METHOD

Full abstract

Equivariant Graph Neural Networks (EGNNs) have become a widely used approach for modeling 3D atomistic systems. However, mainstream architectures face critical scalability bottlenecks due to the explicit construction of geometric features or dense tensor products on \textit{every} edge. To overcome this, we introduce \textbf{E2Former-V2}, a scalable architecture that integrates algebraic sparsity with hardware-aware execution. We first propose \textbf{E}quivariant \textbf{A}xis-\textbf{A}ligned \textbf{S}parsification (EAAS). EAAS builds on Wigner-$6j$ convolution by exploiting an $\mathrm{SO}(3) \rightarrow \mathrm{SO}(2)$ change of basis to transform computationally expensive dense tensor contractions into efficient, sparse parity re-indexing operations. Building on this representation, we introduce \textbf{On-the-Fly Equivariant Attention}, a fully node-centric mechanism implemented via a custom fused Triton kernel. By eliminating materialized edge tensors and maximizing SRAM utilization, our kernel achieves a \textbf{20$\times$ improvement in TFLOPS} compared to standard implementations. Extensive experiments on the SPICE and OMol25 datasets demonstrate that E2Former-V2 maintains comparable predictive performance while notably accelerating inference. This work demonstrates that large equivariant transformers can be trained efficiently using widely accessible GPU platforms. The code is avalible at https://github.com/IQuestLab/UBio-MolFM/tree/e2formerv2.

RESULT

ScienceToStartup currently rates this 5.0/10 on the public viability pass. By eliminating materialized edge tensors and maximizing SRAM utilization, our kernel achieves a \textbf{20$\times$ improvement in TFLOPS} compared to standard implementations.

WHY NOW

Graph Neural Networks moved forward this cycle; last verified April 2026. Public score 5.0/10.

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

Opportunity summary

Score5.0

PainE2Former-V2 enhances scalable EGNNs for 3D atomistic modeling with 20x TFLOPS efficiency, making it accessible on standard GPUs.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

E2Former-V2 enhances scalable EGNNs for 3D atomistic modeling with 20x TFLOPS efficiency, making it accessible on standard GPUs.

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

ARXIV:2601.16622 · GRAPH NEURAL NETWORKS · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

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

E2Former-V2: On-the-Fly Equivariant Attention with Linear Activation Memory

arXiv

E2Former-V2 enhances scalable EGNNs for 3D atomistic modeling with 20x TFLOPS efficiency, making it accessible on standard GPUs.

Blocked on Code›Score5.0Evidence unverified

Opportunity summary

Pain E2Former-V2 enhances scalable EGNNs for 3D atomistic modeling with 20x TFLOPS efficiency, making it accessible on standard GPUs.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

METHOD

Full abstract

RESULT

WHY NOW

Graph Neural Networks moved forward this cycle; last verified April 2026. Public score 5.0/10.

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

Opportunity summary

Score5.0

PainE2Former-V2 enhances scalable EGNNs for 3D atomistic modeling with 20x TFLOPS efficiency, making it accessible on standard GPUs.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

E2Former-V2 enhances scalable EGNNs for 3D atomistic modeling with 20x TFLOPS efficiency, making it accessible on standard GPUs.

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

Paper Pack

10.48550/arXiv.2601.16622

E2Former-V2: On-the-Fly Equivariant Attention with Linear Activation Memory

E2Former-V2 enhances scalable EGNNs for 3D atomistic modeling with 20x TFLOPS efficiency, making it accessible on standard GPUs.

Abstract

Source availability

PDF linked

The paper record includes a public PDF URL.

Extraction status

Parse run linked

A document parse run is attached to this paper.

Proof status

unverified

0 refs; 0 sources; 17% coverage.

What was readable

linkedon file20 anchorsderived fallback30 indexednot indexed

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

Viability

5.0

Time to MVP

MVP estimate missing

Commercial

No commercial flags on file

Export

Preparing verified analysis

lens / founder

PROBLEM

METHOD

RESULT

WHY NOW

Graph Neural Networks moved forward this cycle; last verified April 2026. Public score 5.0/10.

Claim map

Abstract-backed public claims while anchored extraction refreshes.

Strong 0Mixed 0Weak 4

Evidencepartial
E2Former-V2 enhances scalable EGNNs for 3D atomistic modeling with 20x TFLOPS efficiency, making it accessible on standard GPUs. However, mainstream architectures face critical scalability bottlenecks due to the explicit construction of geometric features or dense tensor products on \textit{every} edge.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Equivariant Graph Neural Networks (EGNNs) have become a widely used approach for modeling 3D atomistic systems. However, mainstream architectures face critical scalability bottlenecks due to the explicit construction of geometric features or dense tensor products on \textit{every} edge.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
ScienceToStartup currently rates this 5.0/10 on the public viability pass. By eliminating materialized edge tensors and maximizing SRAM utilization, our kernel achieves a \textbf{20$\times$ improvement in TFLOPS} compared to standard implementations.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Graph Neural Networks moved forward this cycle; last verified April 2026. Public score 5.0/10.
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 linkedDocument parse run

Markets

Graph Neural Networks

Competitors

not indexed

Competitive landscape

E2Former-V2 enhances scalable EGNNs for 3D atomistic modeling with 20x TFLOPS efficiency, making it accessible on standard GPUs.

Segment

Graph Neural Networks

Adoption evidence

No public code link in the paper record yet

Commercial read

5.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

Buzz

No indexed public discussion is attached to 2601.16622 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(30)

Reference metadata pending (fb731024778c6e9104fa719217865b574c3e887a)

Reference metadata pending (70f03e8e69e13d9f603e19a85138ac288615698a)

Reference metadata pending (cd7077ce7f80d6d21c2c53355731cd919e6e8305)

Reference metadata pending (c599e333a4fca84dbb6ce4273ac8c06d6884e90c)

Reference metadata pending (5d1ca53a0b41f4f5c960cd9997556d7180d6b88d)

Reference metadata pending (bbd83fa59a215b2917e43ec278defdff37cf6bd8)

Reference metadata pending (823ca4778e1027f2f0b356df051d762dcecaaba0)

Reference metadata pending (713a0269aa8ffa9f5e8f5671fddc3768a2da9ec5)

Reference metadata pending (fcb56c249d6a260ed360d4bc2fb19df7a76f674c)

Reference metadata pending (1ede15a0aa5204de1f3013d7616a93dbd46fd849)

Reference metadata pending (036aef17a8c2c03202170aa85fd7be1dba974202)

Reference metadata pending (87c5b281fa43e6f27191b20a8dd694eda1126336)

Reference metadata pending (aeb87738cf0058e1c85cad38d5cda241d420a455)

Reference metadata pending (7d81ecf81fd6455da1a5c615b2e2fe17a939d268)

Reference metadata pending (5542d0ff99767f75f8c8a329fc3d88d73ff470c3)

Reference metadata pending (00f39c314542902cd1b03842069e5d3ed441a5c3)

Reference metadata pending (7456dea3a3646f2df6392773a196a5abd0d53b11)

Reference metadata pending (3836ccb33191799e748e8e96f85a813eaf650ff8)

Reference metadata pending (63a513832f56addb67be81a2fa399b233f3030fc)

Reference metadata pending (462d01edc820ac0d4f4460ed133b0f59a292ff9e)

Showing 20 of 30 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 WorkOn Efficient Scaling of GNNs via IO-Aware Layers Implementations

5.0

Extension

Builds On ThisEquiformerV3: Scaling Efficient, Expressive, and General SE(3)-Equivariant Graph Attention Transformers

3.0

Builds On ThisGe$^\text{2}$mS-T: Multi-Dimensional Grouping for Ultra-High Energy Efficiency in Spiking Transformer

4.0

Commercially relevant

Higher ViabilityVecFormer: Towards Efficient and Generalizable Graph Transformer with Graph Token Attention

6.0

Higher ViabilityNexusformer: Nonlinear Attention Expansion for Stable and Inheritable Transformer Scaling

7.0

Higher ViabilityFlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scaling

7.0

Higher ViabilityPreserving Continuous Symmetry in Discrete Spaces: Geometric-Aware Quantization for SO(3)-Equivariant GNNs

8.0

Higher ViabilityAttention Editing: A Versatile Framework for Cross-Architecture Attention Conversion

7.0

Higher ViabilityFrom Complex Dynamics to DynFormer: Rethinking Transformers for PDEs

6.0

Higher ViabilityAn Efficient Hybrid Sparse Attention with CPU-GPU Parallelism for Long-Context Inference

7.0

Conflicting

none indexed

Related Resources

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: 2601.16622
Route: /paper/e2former-v2-on-the-fly-equivariant-attention-with-linear-activation-memory
Active tab: read
Artifact: e2former-v2-on-the-fly-equivariant-attention-with-linear-activation-memory

Available agents

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

API/MCP endpoints

REST paper pack API/api/v1/paper/e2former-v2-on-the-fly-equivariant-attention-with-linear-activation-memory/paper-pack
REST build passport API/api/v1/paper/e2former-v2-on-the-fly-equivariant-attention-with-linear-activation-memory/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": "33292d75-14d5-40f2-a2c7-e2c984436a90",
  "arxiv_id": "2601.16622",
  "canonical_route": "/paper/e2former-v2-on-the-fly-equivariant-attention-with-linear-activation-memory",
  "active_tab": "synced from current hash by the drawer client",
  "selected_artifact": "e2former-v2-on-the-fly-equivariant-attention-with-linear-activation-memory",
  "endpoints": {
    "paper_pack": "/api/v1/paper/e2former-v2-on-the-fly-equivariant-attention-with-linear-activation-memory/paper-pack",
    "build_passport": "/api/v1/paper/e2former-v2-on-the-fly-equivariant-attention-with-linear-activation-memory/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/e2former-v2-on-the-fly-equivariant-attention-with-linear-activation-memory

stale

Proof freshness: stale
Proof status: unverified
Display score: 5/10
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

E2Former-V2: On-the-Fly Equivariant Attention with Linear Activation Memory

Canonical ID e2former-v2-on-the-fly-equivariant-attention-with-linear-activation-memory | Route /paper/e2former-v2-on-the-fly-equivariant-attention-with-linear-activation-memory

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/paper/e2former-v2-on-the-fly-equivariant-attention-with-linear-activation-memory

MCP example

{
  "tool": "get_paper",
  "arguments": {
    "arxiv_id": "2601.16622"
  }
}

source_context

{
  "surface": "paper",
  "mode": "paper",
  "query": "E2Former-V2: On-the-Fly Equivariant Attention with Linear Activation Memory",
  "normalized_query": "2601.16622",
  "route": "/paper/e2former-v2-on-the-fly-equivariant-attention-with-linear-activation-memory",
  "paper_ref": "e2former-v2-on-the-fly-equivariant-attention-with-linear-activation-memory",
  "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

Watch and verify: E2Former-V2: On-the-Fly Equivariant Attention with Linear Activation Memory

/buildability/e2former-v2-on-the-fly-equivariant-attention-with-linear-activation-memory

Watchwatch

Subject: E2Former-V2: On-the-Fly Equivariant Attention with Linear Activation Memory

Verdict

Watch

Verdict is Watch because viability or proof quality is intermediate and should be re-evaluated before execution.

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/e2former-v2-on-the-fly-equivariant-attention-with-linear-activation-memory

Paper ref

e2former-v2-on-the-fly-equivariant-attention-with-linear-activation-memory

arXiv id

2601.16622

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

b3a8d82cb80d5a48748ccebe9cfd3e25eabc38f0c2139b3a0507797735276249

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.

Source proof

Visual citation anchors from the paper document graph.

20 anchors

proof blockPage 382%

This equation captures one of the core mathematical components of the system. products (⊗) and their Wigner-6j counterparts (⊗6j), tra-

Page and bbox are available; crop image is pending.

proof blockPage 382%

This equation captures one of the core mathematical components of the system. Under a rotation R ∈SO(3), features of degree ℓtransform

Page and bbox are available; crop image is pending.

proof blockPage 382%

This equation captures one of the core mathematical components of the system. using solid spherical harmonics R(ℓ)(⃗r) ∈R2ℓ+1, defined

Page and bbox are available; crop image is pending.

JSON-LD twin

The application/ld+json payload rendered for agents.

{
  "@context": "https://schema.org",
  "@graph": [
    {
      "@type": "WebPage",
      "@id": "https://sciencetostartup.com/paper/e2former-v2-on-the-fly-equivariant-attention-with-linear-activation-memory#webpage",
      "url": "https://sciencetostartup.com/paper/e2former-v2-on-the-fly-equivariant-attention-with-linear-activation-memory",
      "name": "E2Former-V2: On-the-Fly Equivariant Attention with Linear Activation Memory",
      "description": "E2Former-V2 enhances scalable EGNNs for 3D atomistic modeling with 20x TFLOPS efficiency, making it accessible on standard GPUs.",
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      }
    },
    {
      "@type": "ScholarlyArticle",
      "@id": "https://sciencetostartup.com/paper/e2former-v2-on-the-fly-equivariant-attention-with-linear-activation-memory#scholarlyArticle",
      "headline": "E2Former-V2: On-the-Fly Equivariant Attention with Linear Activation Memory",
      "description": "E2Former-V2 enhances scalable EGNNs for 3D atomistic modeling with 20x TFLOPS efficiency, making it accessible on standard GPUs.",
      "url": "https://sciencetostartup.com/paper/e2former-v2-on-the-fly-equivariant-attention-with-linear-activation-memory",
      "sameAs": "https://arxiv.org/abs/2601.16622",
      "identifier": {
        "@type": "PropertyValue",
        "propertyID": "arXiv",
        "value": "2601.16622"
      },
      "isAccessibleForFree": true,
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      },
      "datePublished": "2026-01-23T10:20:08.000Z",
      "citation": [
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "fb731024778c6e9104fa719217865b574c3e887a"
          },
          "url": "https://www.semanticscholar.org/paper/fb731024778c6e9104fa719217865b574c3e887a"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "70f03e8e69e13d9f603e19a85138ac288615698a"
          },
          "url": "https://www.semanticscholar.org/paper/70f03e8e69e13d9f603e19a85138ac288615698a"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "cd7077ce7f80d6d21c2c53355731cd919e6e8305"
          },
          "url": "https://www.semanticscholar.org/paper/cd7077ce7f80d6d21c2c53355731cd919e6e8305"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "c599e333a4fca84dbb6ce4273ac8c06d6884e90c"
          },
          "url": "https://www.semanticscholar.org/paper/c599e333a4fca84dbb6ce4273ac8c06d6884e90c"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "5d1ca53a0b41f4f5c960cd9997556d7180d6b88d"
          },
          "url": "https://www.semanticscholar.org/paper/5d1ca53a0b41f4f5c960cd9997556d7180d6b88d"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "bbd83fa59a215b2917e43ec278defdff37cf6bd8"
          },
          "url": "https://www.semanticscholar.org/paper/bbd83fa59a215b2917e43ec278defdff37cf6bd8"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "823ca4778e1027f2f0b356df051d762dcecaaba0"
          },
          "url": "https://www.semanticscholar.org/paper/823ca4778e1027f2f0b356df051d762dcecaaba0"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "713a0269aa8ffa9f5e8f5671fddc3768a2da9ec5"
          },
          "url": "https://www.semanticscholar.org/paper/713a0269aa8ffa9f5e8f5671fddc3768a2da9ec5"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "fcb56c249d6a260ed360d4bc2fb19df7a76f674c"
          },
          "url": "https://www.semanticscholar.org/paper/fcb56c249d6a260ed360d4bc2fb19df7a76f674c"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "1ede15a0aa5204de1f3013d7616a93dbd46fd849"
          },
          "url": "https://www.semanticscholar.org/paper/1ede15a0aa5204de1f3013d7616a93dbd46fd849"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "036aef17a8c2c03202170aa85fd7be1dba974202"
          },
          "url": "https://www.semanticscholar.org/paper/036aef17a8c2c03202170aa85fd7be1dba974202"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "87c5b281fa43e6f27191b20a8dd694eda1126336"
          },
          "url": "https://www.semanticscholar.org/paper/87c5b281fa43e6f27191b20a8dd694eda1126336"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "aeb87738cf0058e1c85cad38d5cda241d420a455"
          },
          "url": "https://www.semanticscholar.org/paper/aeb87738cf0058e1c85cad38d5cda241d420a455"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "7d81ecf81fd6455da1a5c615b2e2fe17a939d268"
          },
          "url": "https://www.semanticscholar.org/paper/7d81ecf81fd6455da1a5c615b2e2fe17a939d268"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "5542d0ff99767f75f8c8a329fc3d88d73ff470c3"
          },
          "url": "https://www.semanticscholar.org/paper/5542d0ff99767f75f8c8a329fc3d88d73ff470c3"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "00f39c314542902cd1b03842069e5d3ed441a5c3"
          },
          "url": "https://www.semanticscholar.org/paper/00f39c314542902cd1b03842069e5d3ed441a5c3"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "7456dea3a3646f2df6392773a196a5abd0d53b11"
          },
          "url": "https://www.semanticscholar.org/paper/7456dea3a3646f2df6392773a196a5abd0d53b11"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "3836ccb33191799e748e8e96f85a813eaf650ff8"
          },
          "url": "https://www.semanticscholar.org/paper/3836ccb33191799e748e8e96f85a813eaf650ff8"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "63a513832f56addb67be81a2fa399b233f3030fc"
          },
          "url": "https://www.semanticscholar.org/paper/63a513832f56addb67be81a2fa399b233f3030fc"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "462d01edc820ac0d4f4460ed133b0f59a292ff9e"
          },
          "url": "https://www.semanticscholar.org/paper/462d01edc820ac0d4f4460ed133b0f59a292ff9e"
        }
      ],
      "additionalProperty": [
        {
          "@type": "PropertyValue",
          "propertyID": "viabilityScore",
          "value": 5
        },
        {
          "@type": "PropertyValue",
          "propertyID": "researchDomain",
          "value": "Graph Neural Networks"
        }
      ]
    },
    {
      "@type": "BreadcrumbList",
      "itemListElement": [
        {
          "@type": "ListItem",
          "position": 1,
          "name": "Home",
          "item": "https://sciencetostartup.com"
        },
        {
          "@type": "ListItem",
          "position": 2,
          "name": "Graph Neural Networks",
          "item": "https://sciencetostartup.com/topics"
        },
        {
          "@type": "ListItem",
          "position": 3,
          "name": "E2Former-V2: On-the-Fly Equivariant Attention with Linear Ac",
          "item": "https://sciencetostartup.com/paper/e2former-v2-on-the-fly-equivariant-attention-with-linear-activation-memory"
        }
      ]
    }
  ]
}

E2Former-V2: On-the-Fly Equivariant Attention with Linear Activation Memory

E2Former-V2: On-the-Fly Equivariant Attention with Linear Activation Memory

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(30)

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(30)

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