ARXIV:2603.04759 · LLM SCALABILITY · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

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

Stacked from One: Multi-Scale Self-Injection for Context Window Extension

arXiv

Introducing a scalable language model framework, enhancing context window capabilities with efficient compression for deep learning applications.

Blocked on Code›Score6.0Evidence unverified

Opportunity summary

Pain Introducing a scalable language model framework, enhancing context window capabilities with efficient compression for deep learning applications.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

Introducing a scalable language model framework, enhancing context window capabilities with efficient compression for deep learning applications. Although continual pre-training on long-context data offers a straightforward solution, it incurs prohibitive data acquisition and computational…

METHOD

Full abstract

The limited context window of contemporary large language models (LLMs) remains a primary bottleneck for their broader application across diverse domains. Although continual pre-training on long-context data offers a straightforward solution, it incurs prohibitive data acquisition and computational costs. To address this challenge, we propose~\modelname, a novel framework based on multi-grained context compression and query-aware information acquisition. SharedLLM comprises two stacked short-context LLMs: a lower model serving as a compressor and an upper model acting as a decoder. The lower model compresses long inputs into compact, multi-grained representations, which are then forwarded to the upper model for context-aware processing. To maximize efficiency, this information transfer occurs exclusively at the lowest layers, bypassing lengthy forward passes and redundant cross-attention operations. This entire process, wherein the upper and lower models are derived from the same underlying LLM layers, is termed~\textit{self-injection}. To support this architecture, a specialized tree-based data structure enables the efficient encoding and query-aware retrieval of contextual information. Despite being trained on sequences of only 8K tokens, \modelname~effectively generalizes to inputs exceeding 128K tokens. Across a comprehensive suite of long-context modeling and understanding benchmarks, \modelname~achieves performance superior or comparable to strong baselines, striking an optimal balance between efficiency and accuracy. Furthermore, these design choices allow \modelname~to substantially reduce the memory footprint and yield notable inference speedups ($2\times$ over streaming and $3\times$ over encoder-decoder architectures).

RESULT

ScienceToStartup currently rates this 6.0/10 on the public viability pass. To support this architecture, a specialized tree-based data structure enables the efficient encoding and query-aware retrieval of contextual information.

WHY NOW

LLM Scalability 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

PainIntroducing a scalable language model framework, enhancing context window capabilities with efficient compression for deep learning applications.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

Introducing a scalable language model framework, enhancing context window capabilities with efficient compression for deep learning applications.

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

ARXIV:2603.04759 · LLM SCALABILITY · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

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

Stacked from One: Multi-Scale Self-Injection for Context Window Extension

arXiv

Introducing a scalable language model framework, enhancing context window capabilities with efficient compression for deep learning applications.

Blocked on Code›Score6.0Evidence unverified

Opportunity summary

Pain Introducing a scalable language model framework, enhancing context window capabilities with efficient compression for deep learning 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

LLM Scalability 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

PainIntroducing a scalable language model framework, enhancing context window capabilities with efficient compression for deep learning applications.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

Introducing a scalable language model framework, enhancing context window capabilities with efficient compression for deep learning applications.

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

Paper Pack

10.48550/arXiv.2603.04759

Stacked from One: Multi-Scale Self-Injection for Context Window Extension

Introducing a scalable language model framework, enhancing context window capabilities with efficient compression for deep learning 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 fallback48 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

LLM Scalability 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
Introducing a scalable language model framework, enhancing context window capabilities with efficient compression for deep learning applications. Although continual pre-training on long-context data offers a straightforward solution, it incurs prohibitive data acquisition and computational costs.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
The limited context window of contemporary large language models (LLMs) remains a primary bottleneck for their broader application across diverse domains. Although continual pre-training on long-context data offers a straightforward solution, it incurs prohibitive data acquisition and computational costs.
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. To support this architecture, a specialized tree-based data structure enables the efficient encoding and query-aware retrieval of contextual information.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
LLM Scalability 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

LLM Scalability

Competitors

not indexed

Competitive landscape

Introducing a scalable language model framework, enhancing context window capabilities with efficient compression for deep learning applications.

Segment

LLM Scalability

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 2603.04759 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(48)

Qwen3 Technical Report

2025An Yang, Anfeng Li et al.

M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models

2025Junxiong Wang, Wen-Ding Li et al.

A Comprehensive Survey on Long Context Language Modeling

2025Jiaheng Liu, Dawei Zhu et al.

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

2025Adam Suma, Sam Dauncey

UniICL: An Efficient ICL Framework Unifying Compression, Selection, and Generation

2025Jun Gao, Qi Lv et al.

The Llama 3 Herd of Models

2024Abhimanyu Dubey, Abhinav Jauhri et al.

ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools

2024Team Glm Aohan Zeng, Bin Xu et al.

Extending Llama-3's Context Ten-Fold Overnight

2024Peitian Zhang, Ninglu Shao et al.

SnapKV: LLM Knows What You are Looking for Before Generation

2024Yuhong Li, Yingbing Huang et al.

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length

2024Xuezhe Ma, Xiaomeng Yang et al.

RULER: What's the Real Context Size of Your Long-Context Language Models?

2024Cheng-Ping Hsieh, Simeng Sun et al.

Training-Free Long-Context Scaling of Large Language Models

2024Chen An, Fei Huang et al.

Long-Context Language Modeling with Parallel Context Encoding

2024Howard Yen, Tianyu Gao et al.

∞Bench: Extending Long Context Evaluation Beyond 100K Tokens

2024Xinrong Zhang, Yingfa Chen et al.

Data Engineering for Scaling Language Models to 128K Context

2024Yao Fu, Rameswar Panda et al.

Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation

2024Zhenyu He, Guhao Feng et al.

Long Context Compression with Activation Beacon

2024Peitian Zhang, Zheng Liu et al.

InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Memory

2024Chaojun Xiao, Pengle Zhang et al.

MemGPT: Towards LLMs as Operating Systems

2023Charles Packer, Vivian Fang et al.

Mistral 7B

2023Albert Qiaochu Jiang, Alexandre Sablayrolles et al.

Showing 20 of 48 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 WorkEscaping the Context Bottleneck: Active Context Curation for LLM Agents via Reinforcement Learning

6.0

Extension

Builds On ThisEnd-to-End Context Compression at Scale

0.0

Builds On ThisLong Context, Less Focus: A Scaling Gap in LLMs Revealed through Privacy and Personalization

5.0

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

5.0

Builds On ThisRetrieval and Multi-Hop Reasoning in 1M-Token Context Windows: Evaluating LLMs on Classical Chinese Text

4.0

Commercially relevant

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

7.0

Higher ViabilityHow to Train Your Long-Context Visual Document Model

7.0

Higher ViabilityLarge Language Model as Token Compressor and Decompressor

7.0

Higher ViabilityParallel In-context Learning for Large Vision Language Models

7.0

Higher ViabilityContext Training with Active Information Seeking

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: 2603.04759
Route: /paper/stacked-from-one-multi-scale-self-injection-for-context-window-extension
Active tab: read
Artifact: stacked-from-one-multi-scale-self-injection-for-context-window-extension

Available agents

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

API/MCP endpoints

REST paper pack API/api/v1/paper/stacked-from-one-multi-scale-self-injection-for-context-window-extension/paper-pack
REST build passport API/api/v1/paper/stacked-from-one-multi-scale-self-injection-for-context-window-extension/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": "e429ced8-f990-4e15-8ae6-fa3a1107459f",
  "arxiv_id": "2603.04759",
  "canonical_route": "/paper/stacked-from-one-multi-scale-self-injection-for-context-window-extension",
  "active_tab": "synced from current hash by the drawer client",
  "selected_artifact": "stacked-from-one-multi-scale-self-injection-for-context-window-extension",
  "endpoints": {
    "paper_pack": "/api/v1/paper/stacked-from-one-multi-scale-self-injection-for-context-window-extension/paper-pack",
    "build_passport": "/api/v1/paper/stacked-from-one-multi-scale-self-injection-for-context-window-extension/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/stacked-from-one-multi-scale-self-injection-for-context-window-extension

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

Stacked from One: Multi-Scale Self-Injection for Context Window Extension

Canonical ID stacked-from-one-multi-scale-self-injection-for-context-window-extension | Route /paper/stacked-from-one-multi-scale-self-injection-for-context-window-extension

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/paper/stacked-from-one-multi-scale-self-injection-for-context-window-extension

MCP example

{
  "tool": "get_paper",
  "arguments": {
    "arxiv_id": "2603.04759"
  }
}

source_context

{
  "surface": "paper",
  "mode": "paper",
  "query": "Stacked from One: Multi-Scale Self-Injection for Context Window Extension",
  "normalized_query": "2603.04759",
  "route": "/paper/stacked-from-one-multi-scale-self-injection-for-context-window-extension",
  "paper_ref": "stacked-from-one-multi-scale-self-injection-for-context-window-extension",
  "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: Stacked from One: Multi-Scale Self-Injection for Context Window Extension

/buildability/stacked-from-one-multi-scale-self-injection-for-context-window-extension

Watchwatch

Subject: Stacked from One: Multi-Scale Self-Injection for Context Window Extension

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/stacked-from-one-multi-scale-self-injection-for-context-window-extension

Paper ref

stacked-from-one-multi-scale-self-injection-for-context-window-extension

arXiv id

2603.04759

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

e9e3c541096d7c0407408b6398b7e84ce93ba2ed620be7ab1ff406d3f7a4640a

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/stacked-from-one-multi-scale-self-injection-for-context-window-extension#webpage",
      "url": "https://sciencetostartup.com/paper/stacked-from-one-multi-scale-self-injection-for-context-window-extension",
      "name": "Stacked from One: Multi-Scale Self-Injection for Context Window Extension",
      "description": "Introducing a scalable language model framework, enhancing context window capabilities with efficient compression for deep learning applications.",
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      }
    },
    {
      "@type": "ScholarlyArticle",
      "@id": "https://sciencetostartup.com/paper/stacked-from-one-multi-scale-self-injection-for-context-window-extension#scholarlyArticle",
      "headline": "Stacked from One: Multi-Scale Self-Injection for Context Window Extension",
      "description": "Introducing a scalable language model framework, enhancing context window capabilities with efficient compression for deep learning applications.",
      "url": "https://sciencetostartup.com/paper/stacked-from-one-multi-scale-self-injection-for-context-window-extension",
      "sameAs": "https://arxiv.org/abs/2603.04759",
      "identifier": {
        "@type": "PropertyValue",
        "propertyID": "arXiv",
        "value": "2603.04759"
      },
      "isAccessibleForFree": true,
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      },
      "datePublished": "2026-03-05T03:16:16.000Z",
      "citation": [
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "d2d84d56f730f81d276a02b48d5d44db5bde0b4a"
          },
          "url": "https://www.semanticscholar.org/paper/d2d84d56f730f81d276a02b48d5d44db5bde0b4a"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "bb18fd3f21ece2b48257c8294c17a49b00807a74"
          },
          "url": "https://www.semanticscholar.org/paper/bb18fd3f21ece2b48257c8294c17a49b00807a74"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "263098ed520eefbac9194470471903d79809ac02"
          },
          "url": "https://www.semanticscholar.org/paper/263098ed520eefbac9194470471903d79809ac02"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "40e8af970329135ec95057d73e239dab805ad128"
          },
          "url": "https://www.semanticscholar.org/paper/40e8af970329135ec95057d73e239dab805ad128"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "c7f9706898bdfa3241601e075b1305649b174ff1"
          },
          "url": "https://www.semanticscholar.org/paper/c7f9706898bdfa3241601e075b1305649b174ff1"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "ebbee4cf985f7a9eaf2ee944f5ec8cb59a9679a0"
          },
          "url": "https://www.semanticscholar.org/paper/ebbee4cf985f7a9eaf2ee944f5ec8cb59a9679a0"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "1784c987e681d60c634765fe64c8d9c26f73d5ff"
          },
          "url": "https://www.semanticscholar.org/paper/1784c987e681d60c634765fe64c8d9c26f73d5ff"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "e9484cf633985ccef70b0ce46866ce232a81ca4b"
          },
          "url": "https://www.semanticscholar.org/paper/e9484cf633985ccef70b0ce46866ce232a81ca4b"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "ac5824e9ff924a937d9eef379d0b581de2417678"
          },
          "url": "https://www.semanticscholar.org/paper/ac5824e9ff924a937d9eef379d0b581de2417678"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "cf7ab5df804575bad88a9fcf0fbf7707bf500944"
          },
          "url": "https://www.semanticscholar.org/paper/cf7ab5df804575bad88a9fcf0fbf7707bf500944"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "2330035c7586a0dc0b1f09e9c00106b295acf543"
          },
          "url": "https://www.semanticscholar.org/paper/2330035c7586a0dc0b1f09e9c00106b295acf543"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "f05e84702562cb693dd68d3d1c88072519a7bd71"
          },
          "url": "https://www.semanticscholar.org/paper/f05e84702562cb693dd68d3d1c88072519a7bd71"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "f288e2238ac8725baa7ca9874bbc3fed1e89a632"
          },
          "url": "https://www.semanticscholar.org/paper/f288e2238ac8725baa7ca9874bbc3fed1e89a632"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "9d932de1d2f51067b6481745f28a2db345293d48"
          },
          "url": "https://www.semanticscholar.org/paper/9d932de1d2f51067b6481745f28a2db345293d48"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "f69f494ab691481ec353da4be480b334fada6607"
          },
          "url": "https://www.semanticscholar.org/paper/f69f494ab691481ec353da4be480b334fada6607"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "908dad62c0e43d80e3e3cb3c0402f7c71c70499c"
          },
          "url": "https://www.semanticscholar.org/paper/908dad62c0e43d80e3e3cb3c0402f7c71c70499c"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "db633c6b1c286c0386f0078d8a2e6224e03a6227"
          },
          "url": "https://www.semanticscholar.org/paper/db633c6b1c286c0386f0078d8a2e6224e03a6227"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "6c323c535365e1c7cbfd9703cbec3b5650a3346b"
          },
          "url": "https://www.semanticscholar.org/paper/6c323c535365e1c7cbfd9703cbec3b5650a3346b"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "fdc53c2c10742464087c0525f77e32604827a21d"
          },
          "url": "https://www.semanticscholar.org/paper/fdc53c2c10742464087c0525f77e32604827a21d"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "5e0cb1c4b91a7486e1c2b15a44a0be56bd74bdc0"
          },
          "url": "https://www.semanticscholar.org/paper/5e0cb1c4b91a7486e1c2b15a44a0be56bd74bdc0"
        }
      ],
      "additionalProperty": [
        {
          "@type": "PropertyValue",
          "propertyID": "viabilityScore",
          "value": 6
        },
        {
          "@type": "PropertyValue",
          "propertyID": "researchDomain",
          "value": "LLM Scalability"
        }
      ]
    },
    {
      "@type": "BreadcrumbList",
      "itemListElement": [
        {
          "@type": "ListItem",
          "position": 1,
          "name": "Home",
          "item": "https://sciencetostartup.com"
        },
        {
          "@type": "ListItem",
          "position": 2,
          "name": "LLM Scalability",
          "item": "https://sciencetostartup.com/topics"
        },
        {
          "@type": "ListItem",
          "position": 3,
          "name": "Stacked from One: Multi-Scale Self-Injection for Context Win",
          "item": "https://sciencetostartup.com/paper/stacked-from-one-multi-scale-self-injection-for-context-window-extension"
        }
      ]
    }
  ]
}

Stacked from One: Multi-Scale Self-Injection for Context Window Extension

Stacked from One: Multi-Scale Self-Injection for Context Window Extension

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(48)

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(48)

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