ARXIV:2602.05191 · EFFICIENT LLM ATTENTION · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

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

Double-P: Hierarchical Top-P Sparse Attention for Long-Context LLMs

arXiv

Double-P enhances LLMs with a scalable attention mechanism that significantly improves inference efficiency for long-context applications.

Blocked on Code›Score6.0Evidence unverified

Opportunity summary

Pain Double-P enhances LLMs with a scalable attention mechanism that significantly improves inference efficiency for long-context applications.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

Double-P enhances LLMs with a scalable attention mechanism that significantly improves inference efficiency for long-context applications. Fixed-budget top-k sparse attention cannot adapt to heterogeneous attention distributions across heads and layers, whereas top-p sparse attention…

METHOD

Full abstract

As long-context inference becomes central to large language models (LLMs), attention over growing key-value caches emerges as a dominant decoding bottleneck, motivating sparse attention for scalable inference. Fixed-budget top-k sparse attention cannot adapt to heterogeneous attention distributions across heads and layers, whereas top-p sparse attention directly preserves attention mass and provides stronger accuracy guarantees. Existing top-p methods, however, fail to jointly optimize top-p accuracy, selection overhead, and sparse attention cost, which limits their overall efficiency. We present Double-P, a hierarchical sparse attention framework that optimizes all three stages. Double-P first performs coarse-grained top-p estimation at the cluster level using size-weighted centroids, then adaptively refines computation through a second top-p stage that allocates token-level attention only when needed. Across long-context benchmarks, Double-P consistently achieves near-zero accuracy drop, reducing attention computation overhead by up to 1.8x and delivers up to 1.3x end-to-end decoding speedup over state-of-the-art fixed-budget sparse attention methods.

RESULT

ScienceToStartup currently rates this 6.0/10 on the public viability pass. Across long-context benchmarks, Double-P consistently achieves near-zero accuracy drop, reducing attention computation overhead by up to 1.8x and delivers up to 1.3x end-to-end decoding…

WHY NOW

Efficient LLM Attention moved forward this cycle; last verified April 2026. Public score 6.0/10.

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

Opportunity summary

Score6.0

PainDouble-P enhances LLMs with a scalable attention mechanism that significantly improves inference efficiency for long-context applications.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

Double-P enhances LLMs with a scalable attention mechanism that significantly improves inference efficiency for long-context applications.

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

ARXIV:2602.05191 · EFFICIENT LLM ATTENTION · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

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

Double-P: Hierarchical Top-P Sparse Attention for Long-Context LLMs

arXiv

Double-P enhances LLMs with a scalable attention mechanism that significantly improves inference efficiency for long-context applications.

Blocked on Code›Score6.0Evidence unverified

Opportunity summary

Pain Double-P enhances LLMs with a scalable attention mechanism that significantly improves inference efficiency for long-context applications.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

METHOD

Full abstract

RESULT

WHY NOW

Efficient LLM Attention moved forward this cycle; last verified April 2026. Public score 6.0/10.

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

Opportunity summary

Score6.0

PainDouble-P enhances LLMs with a scalable attention mechanism that significantly improves inference efficiency for long-context applications.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

Double-P enhances LLMs with a scalable attention mechanism that significantly improves inference efficiency for long-context applications.

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

Paper Pack

10.48550/arXiv.2602.05191

Double-P: Hierarchical Top-P Sparse Attention for Long-Context LLMs

Double-P enhances LLMs with a scalable attention mechanism that significantly improves inference efficiency for long-context applications.

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 fallback45 indexednot indexed

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

Viability

6.0

Time to MVP

MVP estimate missing

Commercial

No commercial flags on file

Export

Preparing verified analysis

lens / founder

PROBLEM

METHOD

RESULT

WHY NOW

Efficient LLM Attention moved forward this cycle; last verified April 2026. Public score 6.0/10.

Claim map

Abstract-backed public claims while anchored extraction refreshes.

Strong 0Mixed 0Weak 4

Evidencepartial
Double-P enhances LLMs with a scalable attention mechanism that significantly improves inference efficiency for long-context applications. Fixed-budget top-k sparse attention cannot adapt to heterogeneous attention distributions across heads and layers, whereas top-p sparse attention directly preserves attention mass and provides stronger accuracy guarantees.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
As long-context inference becomes central to large language models (LLMs), attention over growing key-value caches emerges as a dominant decoding bottleneck, motivating sparse attention for scalable inference. Fixed-budget top-k sparse attention cannot adapt to heterogeneous attention distributions across heads and layers, whereas top-p sparse attention directly preserves attention mass and provides stronger accuracy guarantees.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
ScienceToStartup currently rates this 6.0/10 on the public viability pass. Across long-context benchmarks, Double-P consistently achieves near-zero accuracy drop, reducing attention computation overhead by up to 1.8x and delivers up to 1.3x end-to-end decoding speedup over state-of-the-art fixed-budget sparse attention methods.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Efficient LLM Attention moved forward this cycle; last verified April 2026. Public score 6.0/10.
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

Efficient LLM Attention

Competitors

not indexed

Competitive landscape

Double-P enhances LLMs with a scalable attention mechanism that significantly improves inference efficiency for long-context applications.

Segment

Efficient LLM Attention

Adoption evidence

No public code link in the paper record yet

Commercial read

6.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

Buzz

No indexed public discussion is attached to 2602.05191 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(45)

Reference metadata pending (c703d8ded12a5b92f1608ef6da2e51fcab0e3187)

Reference metadata pending (1dc2281d4df5bd34f66aeb10e5b4741a27e23a9a)

Reference metadata pending (53268ab7afe3d39225b32f039304572274ac5f44)

Reference metadata pending (d2d84d56f730f81d276a02b48d5d44db5bde0b4a)

Reference metadata pending (6f6b7796134c628a25ac713f141dd2af38b81ada)

Reference metadata pending (b4ab74dfafb9a84b2452fe6945e063c79e005d7e)

Reference metadata pending (868b0fae53bf74ac05503620ef64be20921c1ba8)

Reference metadata pending (d73db365dfd3902149d07409214855c16230f29e)

Reference metadata pending (d281440cd94ed477c4a07e63d3149c377eaa0798)

Reference metadata pending (3ac83dc35e519e5fbdddc0e90eb3c56467fb22c6)

Reference metadata pending (23c2e21b6a5789724715f2986fdc586a517ffe57)

Reference metadata pending (3b430f665a04e8ccc5fac30ff39b42d4c6cc893d)

Reference metadata pending (71b7a18e75dc540c889be080f4206460359ea20d)

Reference metadata pending (087d9aeb81d56bfcc526888bd002ccf956b0ac63)

Reference metadata pending (6027d9b7f875a42a36029e2d3b7308be6fa88bb1)

Reference metadata pending (ca0bf57f025fbcc993f282b7f130ddc2fd985e7d)

Reference metadata pending (8f3d959238e67bf6b9bc9818025d0d2e403e478f)

Reference metadata pending (63f2c402f5ddcdc65145b6cde29ad724e1923329)

Reference metadata pending (61166a7545c7cadb1ec79c4744c348bac7644d41)

Reference metadata pending (40e8af970329135ec95057d73e239dab805ad128)

Showing 20 of 45 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 WorkSparseBalance: Load-Balanced Long Context Training with Dynamic Sparse Attention

6.0

Extension

Builds On ThisFrom Rigid to Dynamic: Entropy-Guided Adaptive Inference for Long-Context LLMs

0.0

Builds On ThisYou Only Index Once: Cross-Layer Sparse Attention with Shared Routing

0.0

Builds On ThisIndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

3.0

Builds On ThisHASTE: Training-Free Video Diffusion Acceleration via Head-Wise Adaptive Sparse Attention

3.0

Builds On ThisMiniCPM-SALA: Hybridizing Sparse and Linear Attention for Efficient Long-Context Modeling

5.0

Commercially relevant

Higher ViabilityLycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding

7.0

Higher ViabilityStem: Rethinking Causal Information Flow in Sparse Attention

7.0

Higher ViabilityParallax: Parameterized Local Linear Attention for Language Modeling

8.0

Higher ViabilityPair-In, Pair-Out: Latent Multi-Token Prediction for Efficient LLMs

7.0

Conflicting

none indexed

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: 2602.05191
Route: /paper/double-p-hierarchical-top-p-sparse-attention-for-long-context-llms
Active tab: read
Artifact: double-p-hierarchical-top-p-sparse-attention-for-long-context-llms

Available agents

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

API/MCP endpoints

REST paper pack API/api/v1/paper/double-p-hierarchical-top-p-sparse-attention-for-long-context-llms/paper-pack
REST build passport API/api/v1/paper/double-p-hierarchical-top-p-sparse-attention-for-long-context-llms/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": "7ff8ed0a-496d-49dd-ae09-b00ee0c45e2f",
  "arxiv_id": "2602.05191",
  "canonical_route": "/paper/double-p-hierarchical-top-p-sparse-attention-for-long-context-llms",
  "active_tab": "synced from current hash by the drawer client",
  "selected_artifact": "double-p-hierarchical-top-p-sparse-attention-for-long-context-llms",
  "endpoints": {
    "paper_pack": "/api/v1/paper/double-p-hierarchical-top-p-sparse-attention-for-long-context-llms/paper-pack",
    "build_passport": "/api/v1/paper/double-p-hierarchical-top-p-sparse-attention-for-long-context-llms/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/double-p-hierarchical-top-p-sparse-attention-for-long-context-llms

stale

Proof freshness: stale
Proof status: unverified
Display score: 6/10
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

Double-P: Hierarchical Top-P Sparse Attention for Long-Context LLMs

Canonical ID double-p-hierarchical-top-p-sparse-attention-for-long-context-llms | Route /paper/double-p-hierarchical-top-p-sparse-attention-for-long-context-llms

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/paper/double-p-hierarchical-top-p-sparse-attention-for-long-context-llms

MCP example

{
  "tool": "get_paper",
  "arguments": {
    "arxiv_id": "2602.05191"
  }
}

source_context

{
  "surface": "paper",
  "mode": "paper",
  "query": "Double-P: Hierarchical Top-P Sparse Attention for Long-Context LLMs",
  "normalized_query": "2602.05191",
  "route": "/paper/double-p-hierarchical-top-p-sparse-attention-for-long-context-llms",
  "paper_ref": "double-p-hierarchical-top-p-sparse-attention-for-long-context-llms",
  "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: Double-P: Hierarchical Top-P Sparse Attention for Long-Context LLMs

/buildability/double-p-hierarchical-top-p-sparse-attention-for-long-context-llms

Watchwatch

Subject: Double-P: Hierarchical Top-P Sparse Attention for Long-Context LLMs

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/double-p-hierarchical-top-p-sparse-attention-for-long-context-llms

Paper ref

double-p-hierarchical-top-p-sparse-attention-for-long-context-llms

arXiv id

2602.05191

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

ddde9294d8dea8488dd7ebb1ec5fce40af008ce5e624d8608c76fb9bb152a4b5

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/double-p-hierarchical-top-p-sparse-attention-for-long-context-llms#webpage",
      "url": "https://sciencetostartup.com/paper/double-p-hierarchical-top-p-sparse-attention-for-long-context-llms",
      "name": "Double-P: Hierarchical Top-P Sparse Attention for Long-Context LLMs",
      "description": "Double-P enhances LLMs with a scalable attention mechanism that significantly improves inference efficiency for long-context applications.",
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      }
    },
    {
      "@type": "ScholarlyArticle",
      "@id": "https://sciencetostartup.com/paper/double-p-hierarchical-top-p-sparse-attention-for-long-context-llms#scholarlyArticle",
      "headline": "Double-P: Hierarchical Top-P Sparse Attention for Long-Context LLMs",
      "description": "Double-P enhances LLMs with a scalable attention mechanism that significantly improves inference efficiency for long-context applications.",
      "url": "https://sciencetostartup.com/paper/double-p-hierarchical-top-p-sparse-attention-for-long-context-llms",
      "sameAs": "https://arxiv.org/abs/2602.05191",
      "identifier": {
        "@type": "PropertyValue",
        "propertyID": "arXiv",
        "value": "2602.05191"
      },
      "isAccessibleForFree": true,
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      },
      "datePublished": "2026-02-05T01:37:10.000Z",
      "citation": [
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "c703d8ded12a5b92f1608ef6da2e51fcab0e3187"
          },
          "url": "https://www.semanticscholar.org/paper/c703d8ded12a5b92f1608ef6da2e51fcab0e3187"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "1dc2281d4df5bd34f66aeb10e5b4741a27e23a9a"
          },
          "url": "https://www.semanticscholar.org/paper/1dc2281d4df5bd34f66aeb10e5b4741a27e23a9a"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "53268ab7afe3d39225b32f039304572274ac5f44"
          },
          "url": "https://www.semanticscholar.org/paper/53268ab7afe3d39225b32f039304572274ac5f44"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "d2d84d56f730f81d276a02b48d5d44db5bde0b4a"
          },
          "url": "https://www.semanticscholar.org/paper/d2d84d56f730f81d276a02b48d5d44db5bde0b4a"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "6f6b7796134c628a25ac713f141dd2af38b81ada"
          },
          "url": "https://www.semanticscholar.org/paper/6f6b7796134c628a25ac713f141dd2af38b81ada"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "b4ab74dfafb9a84b2452fe6945e063c79e005d7e"
          },
          "url": "https://www.semanticscholar.org/paper/b4ab74dfafb9a84b2452fe6945e063c79e005d7e"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "868b0fae53bf74ac05503620ef64be20921c1ba8"
          },
          "url": "https://www.semanticscholar.org/paper/868b0fae53bf74ac05503620ef64be20921c1ba8"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "d73db365dfd3902149d07409214855c16230f29e"
          },
          "url": "https://www.semanticscholar.org/paper/d73db365dfd3902149d07409214855c16230f29e"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "d281440cd94ed477c4a07e63d3149c377eaa0798"
          },
          "url": "https://www.semanticscholar.org/paper/d281440cd94ed477c4a07e63d3149c377eaa0798"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "3ac83dc35e519e5fbdddc0e90eb3c56467fb22c6"
          },
          "url": "https://www.semanticscholar.org/paper/3ac83dc35e519e5fbdddc0e90eb3c56467fb22c6"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "23c2e21b6a5789724715f2986fdc586a517ffe57"
          },
          "url": "https://www.semanticscholar.org/paper/23c2e21b6a5789724715f2986fdc586a517ffe57"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "3b430f665a04e8ccc5fac30ff39b42d4c6cc893d"
          },
          "url": "https://www.semanticscholar.org/paper/3b430f665a04e8ccc5fac30ff39b42d4c6cc893d"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "71b7a18e75dc540c889be080f4206460359ea20d"
          },
          "url": "https://www.semanticscholar.org/paper/71b7a18e75dc540c889be080f4206460359ea20d"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "087d9aeb81d56bfcc526888bd002ccf956b0ac63"
          },
          "url": "https://www.semanticscholar.org/paper/087d9aeb81d56bfcc526888bd002ccf956b0ac63"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "6027d9b7f875a42a36029e2d3b7308be6fa88bb1"
          },
          "url": "https://www.semanticscholar.org/paper/6027d9b7f875a42a36029e2d3b7308be6fa88bb1"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "ca0bf57f025fbcc993f282b7f130ddc2fd985e7d"
          },
          "url": "https://www.semanticscholar.org/paper/ca0bf57f025fbcc993f282b7f130ddc2fd985e7d"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "8f3d959238e67bf6b9bc9818025d0d2e403e478f"
          },
          "url": "https://www.semanticscholar.org/paper/8f3d959238e67bf6b9bc9818025d0d2e403e478f"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "63f2c402f5ddcdc65145b6cde29ad724e1923329"
          },
          "url": "https://www.semanticscholar.org/paper/63f2c402f5ddcdc65145b6cde29ad724e1923329"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "61166a7545c7cadb1ec79c4744c348bac7644d41"
          },
          "url": "https://www.semanticscholar.org/paper/61166a7545c7cadb1ec79c4744c348bac7644d41"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "40e8af970329135ec95057d73e239dab805ad128"
          },
          "url": "https://www.semanticscholar.org/paper/40e8af970329135ec95057d73e239dab805ad128"
        }
      ],
      "additionalProperty": [
        {
          "@type": "PropertyValue",
          "propertyID": "viabilityScore",
          "value": 6
        },
        {
          "@type": "PropertyValue",
          "propertyID": "researchDomain",
          "value": "Efficient LLM Attention"
        }
      ]
    },
    {
      "@type": "BreadcrumbList",
      "itemListElement": [
        {
          "@type": "ListItem",
          "position": 1,
          "name": "Home",
          "item": "https://sciencetostartup.com"
        },
        {
          "@type": "ListItem",
          "position": 2,
          "name": "Efficient LLM Attention",
          "item": "https://sciencetostartup.com/topics"
        },
        {
          "@type": "ListItem",
          "position": 3,
          "name": "Double-P: Hierarchical Top-P Sparse Attention for Long-Conte",
          "item": "https://sciencetostartup.com/paper/double-p-hierarchical-top-p-sparse-attention-for-long-context-llms"
        }
      ]
    }
  ]
}

Double-P: Hierarchical Top-P Sparse Attention for Long-Context LLMs

Double-P: Hierarchical Top-P Sparse Attention for Long-Context LLMs

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(45)

Related Papers

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(45)

Related Papers

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline