ARXIV:2602.11656 · AUTONOMOUS DRIVING · SUBMITTED 19 MAR · 18:48 UTC · FRESHNESS STALE

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

SToRM: Supervised Token Reduction for Multi-modal LLMs toward efficient end-to-end autonomous driving

arXiv

SToRM offers a token reduction framework for efficient multi-modal LLMs in autonomous driving, promising reduced computational costs without sacrificing performance.

Blocked on Code›Score7.0Evidence unverified

Opportunity summary

Pain SToRM offers a token reduction framework for efficient multi-modal LLMs in autonomous driving, promising reduced computational costs without sacrificing performance.

Evidence 0 refs | 0 sources | 33% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

SToRM offers a token reduction framework for efficient multi-modal LLMs in autonomous driving, promising reduced computational costs without sacrificing performance. For safe driving in unexpected scenarios, these systems may additionally rely on human interventions…

METHOD

Full abstract

In autonomous driving, end-to-end (E2E) driving systems that predict control commands directly from sensor data have achieved significant advancements. For safe driving in unexpected scenarios, these systems may additionally rely on human interventions such as natural language instructions. Using a multi-modal large language model (MLLM) facilitates human-vehicle interaction and can improve performance in such scenarios. However, this approach requires substantial computational resources due to its reliance on an LLM and numerous visual tokens from sensor inputs, which are limited in autonomous vehicles. Many MLLM studies have explored reducing visual tokens, but often suffer end-task performance degradation compared to using all tokens. To enable efficient E2E driving while maintaining performance comparable to using all tokens, this paper proposes the first Supervised Token Reduction framework for multi-modal LLMs (SToRM). The proposed framework consists of three key elements. First, a lightweight importance predictor with short-term sliding windows estimates token importance scores. Second, a supervised training approach uses an auxiliary path to obtain pseudo-supervision signals from an all-token LLM pass. Third, an anchor-context merging module partitions tokens into anchors and context tokens, and merges context tokens into relevant anchors to reduce redundancy while minimizing information loss. Experiments on the LangAuto benchmark show that SToRM outperforms state-of-the-art E2E driving MLLMs under the same reduced-token budget, maintaining all-token performance while reducing computational cost by up to 30x.

RESULT

ScienceToStartup currently rates this 7.0/10 on the public viability pass. Using a multi-modal large language model (MLLM) facilitates human-vehicle interaction and can improve performance in such scenarios.

WHY NOW

Autonomous Driving moved forward this cycle; last verified April 2026. Public score 7.0/10.

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

Opportunity summary

Score7.0

PainSToRM offers a token reduction framework for efficient multi-modal LLMs in autonomous driving, promising reduced computational costs without sacrificing performance.

Evidence0 refs | 0 sources | 33% coverage

Blockermissing authors

Analysis summary

SToRM offers a token reduction framework for efficient multi-modal LLMs in autonomous driving, promising reduced computational costs without sacrificing performance.

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

ARXIV:2602.11656 · AUTONOMOUS DRIVING · SUBMITTED 19 MAR · 18:48 UTC · FRESHNESS STALE

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

SToRM: Supervised Token Reduction for Multi-modal LLMs toward efficient end-to-end autonomous driving

arXiv

SToRM offers a token reduction framework for efficient multi-modal LLMs in autonomous driving, promising reduced computational costs without sacrificing performance.

Blocked on Code›Score7.0Evidence unverified

Opportunity summary

Pain SToRM offers a token reduction framework for efficient multi-modal LLMs in autonomous driving, promising reduced computational costs without sacrificing performance.

Evidence 0 refs | 0 sources | 33% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

METHOD

Full abstract

RESULT

WHY NOW

Autonomous Driving moved forward this cycle; last verified April 2026. Public score 7.0/10.

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

Opportunity summary

Score7.0

PainSToRM offers a token reduction framework for efficient multi-modal LLMs in autonomous driving, promising reduced computational costs without sacrificing performance.

Evidence0 refs | 0 sources | 33% coverage

Blockermissing authors

Analysis summary

SToRM offers a token reduction framework for efficient multi-modal LLMs in autonomous driving, promising reduced computational costs without sacrificing performance.

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

Paper Pack

10.48550/arXiv.2602.11656

SToRM: Supervised Token Reduction for Multi-modal LLMs toward efficient end-to-end autonomous driving

SToRM offers a token reduction framework for efficient multi-modal LLMs in autonomous driving, promising reduced computational costs without sacrificing performance.

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; 33% coverage.

What was readable

linkedon filenot materializedderived fallback24 indexednot indexed

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

Viability

7.0

Time to MVP

MVP estimate missing

Commercial

No commercial flags on file

Export

Preparing verified analysis

lens / founder

PROBLEM

METHOD

RESULT

WHY NOW

Autonomous Driving moved forward this cycle; last verified April 2026. Public score 7.0/10.

Claim map

Abstract-backed public claims while anchored extraction refreshes.

Strong 0Mixed 0Weak 4

Evidencepartial
SToRM offers a token reduction framework for efficient multi-modal LLMs in autonomous driving, promising reduced computational costs without sacrificing performance. For safe driving in unexpected scenarios, these systems may additionally rely on human interventions such as natural language instructions.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
In autonomous driving, end-to-end (E2E) driving systems that predict control commands directly from sensor data have achieved significant advancements. For safe driving in unexpected scenarios, these systems may additionally rely on human interventions such as natural language instructions.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
ScienceToStartup currently rates this 7.0/10 on the public viability pass. Using a multi-modal large language model (MLLM) facilitates human-vehicle interaction and can improve performance in such scenarios.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Autonomous Driving moved forward this cycle; last verified April 2026. Public score 7.0/10.
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

Autonomous Driving

Competitors

not indexed

Competitive landscape

SToRM offers a token reduction framework for efficient multi-modal LLMs in autonomous driving, promising reduced computational costs without sacrificing performance.

Segment

Autonomous Driving

Adoption evidence

No public code link in the paper record yet

Commercial read

7.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

Buzz

No indexed public discussion is attached to 2602.11656 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(24)

HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models

2025Kazi Hasan Ibn Arif, JinYi Yoon et al.

Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language Models

2025Zhihang Liu, Chen-Wei Xie et al.

DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models

2025Saeed Ranjbar Alvar, Gursimran Singh et al.

VisionZip: Longer is Better but Not Necessary in Vision Language Models

2024Senqiao Yang, Yukang Chen et al.

Generalizing End-To-End Autonomous Driving In Real-World Environments Using Zero-Shot LLMs

2024Zeyu Dong, Yimin Zhu et al.

LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models

2024Yuzhang Shang, Mu Cai et al.

TinyLLaVA: A Framework of Small-scale Large Multimodal Models

2024Baichuan Zhou, Ying Hu et al.

DriveLM: Driving with Graph Visual Question Answering

2023Chonghao Sima, Katrin Renz et al.

LMDrive: Closed-Loop End-to-End Driving with Large Language Models

2023Hao Shao, Yuxuan Hu et al.

Vision Language Models in Autonomous Driving: A Survey and Outlook

2023Xingcheng Zhou, Mingyu Liu et al.

Recent Advancements in End-to-End Autonomous Driving Using Deep Learning: A Survey

2023Pranav Singh Chib, Pravendra Singh

ReasonNet: End-to-End Driving with Temporal and Global Reasoning

2023Hao Shao, Letian Wang et al.

Visual Instruction Tuning

2023Haotian Liu, Chunyuan Li et al.

BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models

2023Junnan Li, Dongxu Li et al.

Token Merging: Your ViT But Faster

2022Daniel Bolya, Cheng-Yang Fu et al.

GroupViT: Semantic Segmentation Emerges from Text Supervision

2022Jiarui Xu, Shalini De Mello et al.

MLP-Mixer: An all-MLP Architecture for Vision

2021I. Tolstikhin, N. Houlsby et al.

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

2020Alexey Dosovitskiy, Lucas Beyer et al.

SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing

2018Taku Kudo, John Richardson

Neural Discrete Representation Learning

2017Aäron van den Oord, O. Vinyals et al.

Showing 20 of 24 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 WorkLLM-MLFFN: Multi-Level Autonomous Driving Behavior Feature Fusion via Large Language Model

7.0

Prior WorkLATS: Large Language Model Assisted Teacher-Student Framework for Multi-Agent Reinforcement Learning in Traffic Signal Control

7.0

Prior WorkVLM-AutoDrive: Post-Training Vision-Language Models for Safety-Critical Autonomous Driving Events

7.0

Prior WorkBridging Perception and Reasoning: Token Reweighting for RLVR in Multimodal LLMs

7.0

Prior WorkRethinking Token Reduction for Large Vision-Language Models

7.0

Extension

Builds On ThisUnified Spatio-Temporal Token Scoring for Efficient Video VLMs

3.0

Commercially relevant

Higher ViabilityLMGenDrive: Bridging Multimodal Understanding and Generative World Modeling for End-to-End Driving

8.0

Higher ViabilityAutoMoT: A Unified Vision-Language-Action Model with Asynchronous Mixture-of-Transformers for End-to-End Autonomous Driving

8.0

Higher ViabilityAdaptToken: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding

8.0

Higher ViabilityDriveVLM-RL: Neuroscience-Inspired Reinforcement Learning with Vision-Language Models for Safe and Deployable Autonomous Driving

8.0

Conflicting

none indexed

Related Resources

What are the implications of AI in autonomous driving?(question)
What are the implications of AI in autonomous driving?(question)
What are the implications of AI in autonomous driving?(question)
Autonomous Driving – Use Cases(use_case)

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: 2602.11656
Route: /paper/storm-supervised-token-reduction-for-multi-modal-llms-toward-efficient-end-to-end-autonomous-driving
Active tab: read
Artifact: storm-supervised-token-reduction-for-multi-modal-llms-toward-efficient-end-to-end-autonomous-driving

Available agents

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

API/MCP endpoints

REST paper pack API/api/v1/paper/storm-supervised-token-reduction-for-multi-modal-llms-toward-efficient-end-to-end-autonomous-driving/paper-pack
REST build passport API/api/v1/paper/storm-supervised-token-reduction-for-multi-modal-llms-toward-efficient-end-to-end-autonomous-driving/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": "20f5b7c4-ce3f-48b6-818f-d99fe3806d3a",
  "arxiv_id": "2602.11656",
  "canonical_route": "/paper/storm-supervised-token-reduction-for-multi-modal-llms-toward-efficient-end-to-end-autonomous-driving",
  "active_tab": "synced from current hash by the drawer client",
  "selected_artifact": "storm-supervised-token-reduction-for-multi-modal-llms-toward-efficient-end-to-end-autonomous-driving",
  "endpoints": {
    "paper_pack": "/api/v1/paper/storm-supervised-token-reduction-for-multi-modal-llms-toward-efficient-end-to-end-autonomous-driving/paper-pack",
    "build_passport": "/api/v1/paper/storm-supervised-token-reduction-for-multi-modal-llms-toward-efficient-end-to-end-autonomous-driving/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/storm-supervised-token-reduction-for-multi-modal-llms-toward-efficient-end-to-end-autonomous-driving

stale

Proof freshness: stale
Proof status: unverified
Display score: 7/10
Last proof check: 2026-03-19
Score updated: 2026-04-02
Score fresh until: 2026-05-02
References: 0
Source count: 0
Coverage: 33%

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

SToRM: Supervised Token Reduction for Multi-modal LLMs toward efficient end-to-end autonomous driving

Canonical ID storm-supervised-token-reduction-for-multi-modal-llms-toward-efficient-end-to-end-autonomous-driving | Route /paper/storm-supervised-token-reduction-for-multi-modal-llms-toward-efficient-end-to-end-autonomous-driving

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/paper/storm-supervised-token-reduction-for-multi-modal-llms-toward-efficient-end-to-end-autonomous-driving

MCP example

{
  "tool": "get_paper",
  "arguments": {
    "arxiv_id": "2602.11656"
  }
}

source_context

{
  "surface": "paper",
  "mode": "paper",
  "query": "SToRM: Supervised Token Reduction for Multi-modal LLMs toward efficient end-to-end autonomous driving",
  "normalized_query": "2602.11656",
  "route": "/paper/storm-supervised-token-reduction-for-multi-modal-llms-toward-efficient-end-to-end-autonomous-driving",
  "paper_ref": "storm-supervised-token-reduction-for-multi-modal-llms-toward-efficient-end-to-end-autonomous-driving",
  "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: SToRM: Supervised Token Reduction for Multi-modal LLMs toward efficient end-to-end autonomous driving

/buildability/storm-supervised-token-reduction-for-multi-modal-llms-toward-efficient-end-to-end-autonomous-driving

Watchwatch

Subject: SToRM: Supervised Token Reduction for Multi-modal LLMs toward efficient end-to-end autonomous driving

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/storm-supervised-token-reduction-for-multi-modal-llms-toward-efficient-end-to-end-autonomous-driving

Paper ref

storm-supervised-token-reduction-for-multi-modal-llms-toward-efficient-end-to-end-autonomous-driving

arXiv id

2602.11656

Freshness

Generated at

2026-03-19T18:48:05.835Z

Evidence freshness

stale

Last verification

2026-03-19T18:48:05.835Z

Sources

References

Coverage

33%

Hash state

Lineage hash

06c41ab4ffa91989e037d09aab5a32ecdefe5dc8190adfad20a38a7d6ae343a5

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: distribution_readiness_scores
Missing: paper_extraction_scorecards
Unknown: distribution readiness has not been computed 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/storm-supervised-token-reduction-for-multi-modal-llms-toward-efficient-end-to-end-autonomous-driving#webpage",
      "url": "https://sciencetostartup.com/paper/storm-supervised-token-reduction-for-multi-modal-llms-toward-efficient-end-to-end-autonomous-driving",
      "name": "SToRM: Supervised Token Reduction for Multi-modal LLMs toward efficient end-to-end autonomous driving",
      "description": "SToRM offers a token reduction framework for efficient multi-modal LLMs in autonomous driving, promising reduced computational costs without sacrificing performance.",
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      }
    },
    {
      "@type": "ScholarlyArticle",
      "@id": "https://sciencetostartup.com/paper/storm-supervised-token-reduction-for-multi-modal-llms-toward-efficient-end-to-end-autonomous-driving#scholarlyArticle",
      "headline": "SToRM: Supervised Token Reduction for Multi-modal LLMs toward efficient end-to-end autonomous driving",
      "description": "SToRM offers a token reduction framework for efficient multi-modal LLMs in autonomous driving, promising reduced computational costs without sacrificing performance.",
      "url": "https://sciencetostartup.com/paper/storm-supervised-token-reduction-for-multi-modal-llms-toward-efficient-end-to-end-autonomous-driving",
      "sameAs": "https://arxiv.org/abs/2602.11656",
      "identifier": {
        "@type": "PropertyValue",
        "propertyID": "arXiv",
        "value": "2602.11656"
      },
      "isAccessibleForFree": true,
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      },
      "datePublished": "2026-02-12T07:21:24.000Z",
      "citation": [
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "5be8aa6aa5d2b8f88214ef4fe484159e5d42b2d5"
          },
          "url": "https://www.semanticscholar.org/paper/5be8aa6aa5d2b8f88214ef4fe484159e5d42b2d5"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "cbf326517d8983aeb3c4c12d68b4444582c0307a"
          },
          "url": "https://www.semanticscholar.org/paper/cbf326517d8983aeb3c4c12d68b4444582c0307a"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "4465715eeaee19283aaf96a557ac6682fdd09217"
          },
          "url": "https://www.semanticscholar.org/paper/4465715eeaee19283aaf96a557ac6682fdd09217"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "ab36ffad0a5364b17d3a73ea3258c5ae4068c341"
          },
          "url": "https://www.semanticscholar.org/paper/ab36ffad0a5364b17d3a73ea3258c5ae4068c341"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "d381b1cce7a552e8391303b86fe2ed088df05ae1"
          },
          "url": "https://www.semanticscholar.org/paper/d381b1cce7a552e8391303b86fe2ed088df05ae1"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "c0ef72d02b93065e77c506e23ce9acbbcd945893"
          },
          "url": "https://www.semanticscholar.org/paper/c0ef72d02b93065e77c506e23ce9acbbcd945893"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "6a6751f59c5dbc80823b3cf47c3aaae063991b86"
          },
          "url": "https://www.semanticscholar.org/paper/6a6751f59c5dbc80823b3cf47c3aaae063991b86"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "3c8cc9a5ee373d51e0bf71621b6eb6901c762e8f"
          },
          "url": "https://www.semanticscholar.org/paper/3c8cc9a5ee373d51e0bf71621b6eb6901c762e8f"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "e0b05e314372ed580d9612ef5f0ee672b17ad2e4"
          },
          "url": "https://www.semanticscholar.org/paper/e0b05e314372ed580d9612ef5f0ee672b17ad2e4"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "f2665e9d29836166beef6afccd9378030b352a2c"
          },
          "url": "https://www.semanticscholar.org/paper/f2665e9d29836166beef6afccd9378030b352a2c"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "8ac98f4ca139781a0b000c40fa6cdd2af7592b7f"
          },
          "url": "https://www.semanticscholar.org/paper/8ac98f4ca139781a0b000c40fa6cdd2af7592b7f"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "fc2f1d2ca7c28e75a258de484892958d1daf53be"
          },
          "url": "https://www.semanticscholar.org/paper/fc2f1d2ca7c28e75a258de484892958d1daf53be"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "a5036f31f0e629dc661f120b8c3b1f374d479ab8"
          },
          "url": "https://www.semanticscholar.org/paper/a5036f31f0e629dc661f120b8c3b1f374d479ab8"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "3f5b31c4f7350dc88002c121aecbdc82f86eb5bb"
          },
          "url": "https://www.semanticscholar.org/paper/3f5b31c4f7350dc88002c121aecbdc82f86eb5bb"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "1dff6b1b35e2d45d4db57c8b4e4395486c3e365f"
          },
          "url": "https://www.semanticscholar.org/paper/1dff6b1b35e2d45d4db57c8b4e4395486c3e365f"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "0b5f27a5766c5d1394a6282ad94fec21d620bd6b"
          },
          "url": "https://www.semanticscholar.org/paper/0b5f27a5766c5d1394a6282ad94fec21d620bd6b"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "67571d29190faea9fbd104acd16274f8c4edf254"
          },
          "url": "https://www.semanticscholar.org/paper/67571d29190faea9fbd104acd16274f8c4edf254"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "268d347e8a55b5eb82fb5e7d2f800e33c75ab18a"
          },
          "url": "https://www.semanticscholar.org/paper/268d347e8a55b5eb82fb5e7d2f800e33c75ab18a"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "b5246fa284f86b544a7c31f050b3bd0defd053fd"
          },
          "url": "https://www.semanticscholar.org/paper/b5246fa284f86b544a7c31f050b3bd0defd053fd"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "f466157848d1a7772fb6d02cdac9a7a5e7ef982e"
          },
          "url": "https://www.semanticscholar.org/paper/f466157848d1a7772fb6d02cdac9a7a5e7ef982e"
        }
      ],
      "additionalProperty": [
        {
          "@type": "PropertyValue",
          "propertyID": "viabilityScore",
          "value": 7
        },
        {
          "@type": "PropertyValue",
          "propertyID": "researchDomain",
          "value": "Autonomous Driving"
        }
      ]
    },
    {
      "@type": "BreadcrumbList",
      "itemListElement": [
        {
          "@type": "ListItem",
          "position": 1,
          "name": "Home",
          "item": "https://sciencetostartup.com"
        },
        {
          "@type": "ListItem",
          "position": 2,
          "name": "Autonomous Driving",
          "item": "https://sciencetostartup.com/topics"
        },
        {
          "@type": "ListItem",
          "position": 3,
          "name": "SToRM: Supervised Token Reduction for Multi-modal LLMs towar",
          "item": "https://sciencetostartup.com/paper/storm-supervised-token-reduction-for-multi-modal-llms-toward-efficient-end-to-end-autonomous-driving"
        }
      ]
    }
  ]
}

SToRM: Supervised Token Reduction for Multi-modal LLMs toward efficient end-to-end autonomous driving

SToRM: Supervised Token Reduction for Multi-modal LLMs toward efficient end-to-end autonomous driving

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(24)

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(24)

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