ARXIV:2602.12146 · DATA COMPRESSION · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

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

Seq2Seq2Seq: Lossless Data Compression via Discrete Latent Transformers and Reinforcement Learning

arXiv

Novel lossless compression method using Reinforcement Learning and T5 models to enhance data compression efficiency.

Blocked on Code›Score1.0Evidence unverified

Opportunity summary

Pain Novel lossless compression method using Reinforcement Learning and T5 models to enhance data compression efficiency.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

Novel lossless compression method using Reinforcement Learning and T5 models to enhance data compression efficiency. Traditional compression techniques, such as dictionary-based and statistical methods, often struggle to optimally exploit the structure and redundancy in…

METHOD

Full abstract

Efficient lossless compression is essential for minimizing storage costs and transmission overhead while preserving data integrity. Traditional compression techniques, such as dictionary-based and statistical methods, often struggle to optimally exploit the structure and redundancy in complex data formats. Recent advancements in deep learning have opened new avenues for compression; however, many existing approaches depend on dense vector representations that obscure the underlying token structure. To address these limitations, we propose a novel lossless compression method that leverages Reinforcement Learning applied to a T5 language model architecture. This approach enables the compression of data into sequences of tokens rather than traditional vector representations. Unlike auto-encoders, which typically encode information into continuous latent spaces, our method preserves the token-based structure, aligning more closely with the original data format. This preservation allows for higher compression ratios while maintaining semantic integrity. By training the model using an off-policy Reinforcement Learning algorithm, we optimize sequence length to minimize redundancy and enhance compression efficiency. Our method introduces an efficient and adaptive data compression system built upon advanced Reinforcement Learning techniques, functioning independently of external grammatical or world knowledge. This approach shows significant improvements in compression ratios compared to conventional methods. By leveraging the latent information within language models, our system effectively compresses data without requiring explicit content understanding, paving the way for more robust and practical compression solutions across various applications.

RESULT

ScienceToStartup currently rates this 1.0/10 on the public viability pass. This approach enables the compression of data into sequences of tokens rather than traditional vector representations.

WHY NOW

Data Compression moved forward this cycle; last verified April 2026. Public score 1.0/10.

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

Opportunity summary

Score1.0

PainNovel lossless compression method using Reinforcement Learning and T5 models to enhance data compression efficiency.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

Novel lossless compression method using Reinforcement Learning and T5 models to enhance data compression efficiency.

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

ARXIV:2602.12146 · DATA COMPRESSION · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

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

Seq2Seq2Seq: Lossless Data Compression via Discrete Latent Transformers and Reinforcement Learning

arXiv

Novel lossless compression method using Reinforcement Learning and T5 models to enhance data compression efficiency.

Blocked on Code›Score1.0Evidence unverified

Opportunity summary

Pain Novel lossless compression method using Reinforcement Learning and T5 models to enhance data compression efficiency.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

METHOD

Full abstract

RESULT

ScienceToStartup currently rates this 1.0/10 on the public viability pass. This approach enables the compression of data into sequences of tokens rather than traditional vector representations.

WHY NOW

Data Compression moved forward this cycle; last verified April 2026. Public score 1.0/10.

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

Opportunity summary

Score1.0

PainNovel lossless compression method using Reinforcement Learning and T5 models to enhance data compression efficiency.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

Novel lossless compression method using Reinforcement Learning and T5 models to enhance data compression efficiency.

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

Paper Pack

10.48550/arXiv.2602.12146

Seq2Seq2Seq: Lossless Data Compression via Discrete Latent Transformers and Reinforcement Learning

Novel lossless compression method using Reinforcement Learning and T5 models to enhance data compression efficiency.

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 fallback30 indexednot indexed

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

Viability

1.0

Time to MVP

MVP estimate missing

Commercial

No commercial flags on file

Export

Preparing verified analysis

lens / founder

PROBLEM

METHOD

RESULT

ScienceToStartup currently rates this 1.0/10 on the public viability pass. This approach enables the compression of data into sequences of tokens rather than traditional vector representations.

WHY NOW

Data Compression moved forward this cycle; last verified April 2026. Public score 1.0/10.

Claim map

Abstract-backed public claims while anchored extraction refreshes.

Strong 0Mixed 0Weak 4

Evidencepartial
Novel lossless compression method using Reinforcement Learning and T5 models to enhance data compression efficiency. Traditional compression techniques, such as dictionary-based and statistical methods, often struggle to optimally exploit the structure and redundancy in complex data formats.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Efficient lossless compression is essential for minimizing storage costs and transmission overhead while preserving data integrity. Traditional compression techniques, such as dictionary-based and statistical methods, often struggle to optimally exploit the structure and redundancy in complex data formats.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
ScienceToStartup currently rates this 1.0/10 on the public viability pass. This approach enables the compression of data into sequences of tokens rather than traditional vector representations.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Data Compression moved forward this cycle; last verified April 2026. Public score 1.0/10.
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

Data Compression

Competitors

not indexed

Competitive landscape

Novel lossless compression method using Reinforcement Learning and T5 models to enhance data compression efficiency.

Segment

Data Compression

Adoption evidence

No public code link in the paper record yet

Commercial read

1.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

Buzz

No indexed public discussion is attached to 2602.12146 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)

A comparative analysis on using GPT and BERT for automated vulnerability scoring

2025Seyedeh Leili Mirtaheri, Andrea Pugliese et al.

Hidden-layer configurations in reinforcement learning models for stock portfolio optimization

2024Patrick Kevin Aritonang, S. Wiryono et al.

Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Data

2024David Heurtel-Depeiges, Anian Ruoss et al.

T5-Based Model for Abstractive Summarization: A Semi-Supervised Learning Approach with Consistency Loss Functions

2023Mingye Wang, Pan Xie et al.

MLAE2: Metareasoning for Latency-Aware Energy-Efficient Autonomous Nano-Drones

2023Mozhgan Navardi, T. Mohsenin

Compression And Decompression Of Files Without Loss Of Quality

2023K. Anand, M. Priyadharshini et al.

Transformer Language Models without Positional Encodings Still Learn Positional Information

2022Adi Haviv, Ori Ram et al.

Recursive Least Squares Advantage Actor-Critic Algorithms

2022Yuan Wang, Chunyuan Zhang et al.

Question Generation using Knowledge Graphs with the T5 Language Model and Masked Self-Attention

2021Kosuke Aigo, Takashi Tsunakawa et al.

DECORE: Deep Compression with Reinforcement Learning

2021Manoj Alwani, Vashisht Madhavan et al.

Multimedia Data Summarization Using Joint Integer Linear Programming

2021Sidhant Allawadi, Ritika et al.

State-Temporal Compression in Reinforcement Learning With the Reward-Restricted Geodesic Metric

2021Shangqi Guo, Qianyu Yan et al.

Reinforcement Learning with Prototypical Representations

2021Denis Yarats, R. Fergus et al.

An advantage actor-critic algorithm for robotic motion planning in dense and dynamic scenarios

2021Chengmin Zhou, Bingding Huang et al.

Studying the Usage of Text-To-Text Transfer Transformer to Support Code-Related Tasks

2021A. Mastropaolo, Simone Scalabrino et al.

NNCP v2: Lossless Data Compression with Transformer

2021Fabrice Bellard

Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

2019Colin Raffel, Noam Shazeer et al.

HAQ: Hardware-Aware Automated Quantization With Mixed Precision

2018Kuan Wang, Zhijian Liu et al.

Attention is All you Need

2017Ashish Vaswani, Noam Shazeer et al.

Adam: A Method for Stochastic Optimization

2014Diederik P. Kingma, Jimmy Ba

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

none indexed

Extension

Builds On ThisSemanticZip: A Pilot Framework for Lossy Text Compression with LLMs as Semantic Decompressors

0.0

Builds On ThisEnd-to-End Context Compression at Scale

0.0

Builds On ThisLLMCodec: Adapting Video Codecs for Efficient Weight Compression of Large Language Models

0.0

Builds On ThisA general tensor-structured compression scheme for efficient large language models

0.0

Commercially relevant

Higher ViabilityDynamic Token Compression for Efficient Video Understanding through Reinforcement Learning

7.0

Higher ViabilityLearning is Forgetting: LLM Training As Lossy Compression

2.0

Higher ViabilityLarge Language Model as Token Compressor and Decompressor

7.0

Higher ViabilityRethinking the Role of Tensor Decompositions in Post-Training LLM Compression

4.0

Higher ViabilityUnified Spatiotemporal Token Compression for Video-LLMs at Ultra-Low Retention

7.0

Higher ViabilityZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression

3.0

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: 2602.12146
Route: /paper/seq2seq2seq-lossless-data-compression-via-discrete-latent-transformers-and-reinforcement-learning
Active tab: read
Artifact: seq2seq2seq-lossless-data-compression-via-discrete-latent-transformers-and-reinforcement-learning

Available agents

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

API/MCP endpoints

REST paper pack API/api/v1/paper/seq2seq2seq-lossless-data-compression-via-discrete-latent-transformers-and-reinforcement-learning/paper-pack
REST build passport API/api/v1/paper/seq2seq2seq-lossless-data-compression-via-discrete-latent-transformers-and-reinforcement-learning/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": "38febb54-3dba-49b8-97c9-8d0be7e29b4d",
  "arxiv_id": "2602.12146",
  "canonical_route": "/paper/seq2seq2seq-lossless-data-compression-via-discrete-latent-transformers-and-reinforcement-learning",
  "active_tab": "synced from current hash by the drawer client",
  "selected_artifact": "seq2seq2seq-lossless-data-compression-via-discrete-latent-transformers-and-reinforcement-learning",
  "endpoints": {
    "paper_pack": "/api/v1/paper/seq2seq2seq-lossless-data-compression-via-discrete-latent-transformers-and-reinforcement-learning/paper-pack",
    "build_passport": "/api/v1/paper/seq2seq2seq-lossless-data-compression-via-discrete-latent-transformers-and-reinforcement-learning/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/seq2seq2seq-lossless-data-compression-via-discrete-latent-transformers-and-reinforcement-learning

stale

Proof freshness: stale
Proof status: unverified
Display score: 1/10
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

Seq2Seq2Seq: Lossless Data Compression via Discrete Latent Transformers and Reinforcement Learning

Canonical ID seq2seq2seq-lossless-data-compression-via-discrete-latent-transformers-and-reinforcement-learning | Route /paper/seq2seq2seq-lossless-data-compression-via-discrete-latent-transformers-and-reinforcement-learning

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/paper/seq2seq2seq-lossless-data-compression-via-discrete-latent-transformers-and-reinforcement-learning

MCP example

{
  "tool": "get_paper",
  "arguments": {
    "arxiv_id": "2602.12146"
  }
}

source_context

{
  "surface": "paper",
  "mode": "paper",
  "query": "Seq2Seq2Seq: Lossless Data Compression via Discrete Latent Transformers and Reinforcement Learning",
  "normalized_query": "2602.12146",
  "route": "/paper/seq2seq2seq-lossless-data-compression-via-discrete-latent-transformers-and-reinforcement-learning",
  "paper_ref": "seq2seq2seq-lossless-data-compression-via-discrete-latent-transformers-and-reinforcement-learning",
  "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: Seq2Seq2Seq: Lossless Data Compression via Discrete Latent Transformers and Reinforcement Learning

/buildability/seq2seq2seq-lossless-data-compression-via-discrete-latent-transformers-and-reinforcement-learning

Ignoreblocked

Subject: Seq2Seq2Seq: Lossless Data Compression via Discrete Latent Transformers and Reinforcement Learning

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/seq2seq2seq-lossless-data-compression-via-discrete-latent-transformers-and-reinforcement-learning

Paper ref

seq2seq2seq-lossless-data-compression-via-discrete-latent-transformers-and-reinforcement-learning

arXiv id

2602.12146

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

bbc420a3e105bc3f54e96a52fed4c290de1caa86bdbfd4cb627b4691bebbd7a4

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/seq2seq2seq-lossless-data-compression-via-discrete-latent-transformers-and-reinforcement-learning#webpage",
      "url": "https://sciencetostartup.com/paper/seq2seq2seq-lossless-data-compression-via-discrete-latent-transformers-and-reinforcement-learning",
      "name": "Seq2Seq2Seq: Lossless Data Compression via Discrete Latent Transformers and Reinforcement Learning",
      "description": "Novel lossless compression method using Reinforcement Learning and T5 models to enhance data compression efficiency.",
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      }
    },
    {
      "@type": "ScholarlyArticle",
      "@id": "https://sciencetostartup.com/paper/seq2seq2seq-lossless-data-compression-via-discrete-latent-transformers-and-reinforcement-learning#scholarlyArticle",
      "headline": "Seq2Seq2Seq: Lossless Data Compression via Discrete Latent Transformers and Reinforcement Learning",
      "description": "Novel lossless compression method using Reinforcement Learning and T5 models to enhance data compression efficiency.",
      "url": "https://sciencetostartup.com/paper/seq2seq2seq-lossless-data-compression-via-discrete-latent-transformers-and-reinforcement-learning",
      "sameAs": "https://arxiv.org/abs/2602.12146",
      "identifier": {
        "@type": "PropertyValue",
        "propertyID": "arXiv",
        "value": "2602.12146"
      },
      "isAccessibleForFree": true,
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      },
      "datePublished": "2026-02-12T16:30:55.000Z",
      "citation": [
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "b3390acc0d9c377d698c6e410354b876c4ba1735"
          },
          "url": "https://www.semanticscholar.org/paper/b3390acc0d9c377d698c6e410354b876c4ba1735"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "02b5be92a6b30fea011bd709dfc54cf92f085bf1"
          },
          "url": "https://www.semanticscholar.org/paper/02b5be92a6b30fea011bd709dfc54cf92f085bf1"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "433c86e4fe0126756e40a0951a1e1fe336c692f0"
          },
          "url": "https://www.semanticscholar.org/paper/433c86e4fe0126756e40a0951a1e1fe336c692f0"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "e458e0bdfc0377cba060896082e7469fcd2b09c2"
          },
          "url": "https://www.semanticscholar.org/paper/e458e0bdfc0377cba060896082e7469fcd2b09c2"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "4886cc573543bcd7b4baa72a93935270bbc5b7e0"
          },
          "url": "https://www.semanticscholar.org/paper/4886cc573543bcd7b4baa72a93935270bbc5b7e0"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "83e36d51fdd6a1ae68698bbf51f102a184288707"
          },
          "url": "https://www.semanticscholar.org/paper/83e36d51fdd6a1ae68698bbf51f102a184288707"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "a2fc77f075f666b462d9350e7576f0ba9845c61b"
          },
          "url": "https://www.semanticscholar.org/paper/a2fc77f075f666b462d9350e7576f0ba9845c61b"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "504d893ee347a7a5e7320a31a2a237b8ddf11f0d"
          },
          "url": "https://www.semanticscholar.org/paper/504d893ee347a7a5e7320a31a2a237b8ddf11f0d"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "853889876a165df623e40a9d5a306b5c1552b080"
          },
          "url": "https://www.semanticscholar.org/paper/853889876a165df623e40a9d5a306b5c1552b080"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "49a2c9c12a2ff95cf65a3630317fe745ed593cc2"
          },
          "url": "https://www.semanticscholar.org/paper/49a2c9c12a2ff95cf65a3630317fe745ed593cc2"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "b466f7c1781a06758ea75a35a4c3d1adc2caaacf"
          },
          "url": "https://www.semanticscholar.org/paper/b466f7c1781a06758ea75a35a4c3d1adc2caaacf"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "03f4f05139f2e7a543671db7c09bd2d56d1122ce"
          },
          "url": "https://www.semanticscholar.org/paper/03f4f05139f2e7a543671db7c09bd2d56d1122ce"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "a50f7bcf8a998f3de11bc085b0f4dea32be19783"
          },
          "url": "https://www.semanticscholar.org/paper/a50f7bcf8a998f3de11bc085b0f4dea32be19783"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "f4cbec048d2261c528a3279e1eb29a1f5ecbde3e"
          },
          "url": "https://www.semanticscholar.org/paper/f4cbec048d2261c528a3279e1eb29a1f5ecbde3e"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "c2c7233293d55f201fe5b496234bed1914eea70e"
          },
          "url": "https://www.semanticscholar.org/paper/c2c7233293d55f201fe5b496234bed1914eea70e"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "6c4b76232bb72897685d19b3d264c6ee3005bc2b"
          },
          "url": "https://www.semanticscholar.org/paper/6c4b76232bb72897685d19b3d264c6ee3005bc2b"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "54c4642d017830e1faddbb49f0377228d2b01493"
          },
          "url": "https://www.semanticscholar.org/paper/54c4642d017830e1faddbb49f0377228d2b01493"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "204e3073870fae3d05bcbc2f6a8e263d9b72e776"
          },
          "url": "https://www.semanticscholar.org/paper/204e3073870fae3d05bcbc2f6a8e263d9b72e776"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "a6cb366736791bcccc5c8639de5a8f9636bf87e8"
          },
          "url": "https://www.semanticscholar.org/paper/a6cb366736791bcccc5c8639de5a8f9636bf87e8"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "13fd400e737dc9c0627cf8f97565fa18441ace9b"
          },
          "url": "https://www.semanticscholar.org/paper/13fd400e737dc9c0627cf8f97565fa18441ace9b"
        }
      ],
      "additionalProperty": [
        {
          "@type": "PropertyValue",
          "propertyID": "viabilityScore",
          "value": 1
        },
        {
          "@type": "PropertyValue",
          "propertyID": "researchDomain",
          "value": "Data Compression"
        }
      ]
    },
    {
      "@type": "BreadcrumbList",
      "itemListElement": [
        {
          "@type": "ListItem",
          "position": 1,
          "name": "Home",
          "item": "https://sciencetostartup.com"
        },
        {
          "@type": "ListItem",
          "position": 2,
          "name": "Data Compression",
          "item": "https://sciencetostartup.com/topics"
        },
        {
          "@type": "ListItem",
          "position": 3,
          "name": "Seq2Seq2Seq: Lossless Data Compression via Discrete Latent T",
          "item": "https://sciencetostartup.com/paper/seq2seq2seq-lossless-data-compression-via-discrete-latent-transformers-and-reinforcement-learning"
        }
      ]
    }
  ]
}

Seq2Seq2Seq: Lossless Data Compression via Discrete Latent Transformers and Reinforcement Learning

Seq2Seq2Seq: Lossless Data Compression via Discrete Latent Transformers and Reinforcement Learning

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(30)

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(30)

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