ARXIV:2605.31590 · GENERATIVE VIDEO · SUBMITTED 01 JUN · 20:21 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedVerifiedPaperPack: citation fields availablePartialProof: unverified proof status

TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation

Ruotong Liao · Guowen Huang · Qing Cheng · Guangyao Zhai · Lei Zhang · Xun Xiao · +3 at arXiv

A training-free method to progressively steer diffusion transformers for multi-event video generation by partitioning events and fusing prompts.

Ship in 2-4 weeks›Score7.0Evidence unverified

Opportunity summary

Pain A training-free method to progressively steer diffusion transformers for multi-event video generation by partitioning events and fusing prompts.

Evidence 0 refs | 4 sources | 50% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

A training-free method to progressively steer diffusion transformers for multi-event video generation by partitioning events and fusing prompts. Inspired by the intrinsics of the diffusion process, we probe video diffusion transformers (DiTs) and uncover…

METHOD

Full abstract

Text-to-video (T2V) generation faces challenging questions when generating videos with long horizons containing multiple events. Inspired by the intrinsics of the diffusion process, we probe video diffusion transformers (DiTs) and uncover intrinsic turning points in the DiT denoising trajectory where conditioning text affects generation from global layout to fine-grained details. Building on this finding, we present TunerDiT, a simple yet effective progressive steering method that requires no additional training for multi-event generation. TunerDiT comprises two steering handles: (1) Event-Partitioned Masking that enforces event boundaries while allowing cross-event transition bands; (2) Cross-Event Prompt Fusion that injects neighboring event semantics for late-stage refinement. We contribute a self-curated prompt suite for benchmarking multi-event generation, i.e., Meve. TunerDiT achieves state-of-the-art performance across 8 metrics and offers a tunable trade-off between video consistency and event separation, compared with other training-free methods. The improvement in text alignment increases with the event count, indicating a scaling possibility with increasing event count.

RESULT

ScienceToStartup currently rates this 7.0/10 on the public viability pass. TunerDiT achieves state-of-the-art performance across 8 metrics and offers a tunable trade-off between video consistency and event separation, compared with other training-free methods. A…

WHY NOW

Generative Video moved forward this cycle; last verified June 2026. Public score 7.0/10. Implementation evidence is present through a linked repository.

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

Opportunity summary

Score7.0

PainA training-free method to progressively steer diffusion transformers for multi-event video generation by partitioning events and fusing prompts.

Evidence0 refs | 4 sources | 50% coverage

Blockerno shell-level blocker reported

Analysis summary

A training-free method to progressively steer diffusion transformers for multi-event video generation by partitioning events and fusing prompts.

VerifiedSource: PDF linkedVerifiedPaperPack: citation fields availablePartialProof: unverified proof status

ARXIV:2605.31590 · GENERATIVE VIDEO · SUBMITTED 01 JUN · 20:21 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedVerifiedPaperPack: citation fields availablePartialProof: unverified proof status

TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation

Ruotong Liao · Guowen Huang · Qing Cheng · Guangyao Zhai · Lei Zhang · Xun Xiao · +3 at arXiv

A training-free method to progressively steer diffusion transformers for multi-event video generation by partitioning events and fusing prompts.

Ship in 2-4 weeks›Score7.0Evidence unverified

Opportunity summary

Pain A training-free method to progressively steer diffusion transformers for multi-event video generation by partitioning events and fusing prompts.

Evidence 0 refs | 4 sources | 50% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

METHOD

Full abstract

RESULT

WHY NOW

Generative Video moved forward this cycle; last verified June 2026. Public score 7.0/10. Implementation evidence is present through a linked repository.

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

Opportunity summary

Score7.0

PainA training-free method to progressively steer diffusion transformers for multi-event video generation by partitioning events and fusing prompts.

Evidence0 refs | 4 sources | 50% coverage

Blockerno shell-level blocker reported

Analysis summary

A training-free method to progressively steer diffusion transformers for multi-event video generation by partitioning events and fusing prompts.

VerifiedSource: PDF linkedVerifiedPaperPack: citation fields availablePartialProof: unverified proof status

Paper Pack

10.48550/arXiv.2605.31590

TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation

A training-free method to progressively steer diffusion transformers for multi-event video generation by partitioning events and fusing prompts.

Abstract

Source availability

PDF linked

The paper record includes a public PDF URL.

Extraction status

Parse run linked

A document parse run is attached to this paper.

Proof status

unverified

0 refs; 4 sources; 50% coverage.

What was readable

linkedon file18 anchors1 extracted38 indexednot indexed

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

Viability

7.0

Time to MVP

MVP estimate missing

Commercial

coderepo url

Export

Preparing verified analysis

lens / founder

PROBLEM

METHOD

RESULT

WHY NOW

Generative Video moved forward this cycle; last verified June 2026. Public score 7.0/10. Implementation evidence is present through a linked repository.

Claim map

Strong 1Mixed 0Weak 0

Evidencepartial
{"file name": "input.pdf", "number of pages": 17, "author": "Ruotong Liao; Guowen Huang; Qing Cheng; Guangyao Zhai; Lei Zhang; Xun Xiao; Thomas Seidl; Daniel Cremers; Volker Tresp"
Implicationmissing
Implication not extracted yet.
Verificationpartial
partial

Constellation map

Paper-native neighborhood for concepts, methods, materials, markets, and competitors. Missing lanes stay labeled instead of disappearing behind commercialization gates.

Open full Signal Canvas

Concepts

not indexed

Methods

Materials

PDF linkedDocument parse run

Markets

Generative Video

Competitors

not indexed

Competitive landscape

A training-free method to progressively steer diffusion transformers for multi-event video generation by partitioning events and fusing prompts.

Segment

Generative Video

Adoption evidence

Public code linked for build inspection

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 2605.31590 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(38)

InstaDrive: Instance-Aware Driving World Models for Realistic and Consistent Video Generation

2025Zhuoran Yang, Xi Guo et al.

When and Where do Events Switch in Multi-Event Video Generation?

2025Ruotong Liao, Guowen Huang et al.

WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception

2025Zhiheng Liu, Xueqing Deng et al.

ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Models

2025Ozgur Kara, K. Singh et al.

WorldScore: A Unified Evaluation Benchmark for World Generation

2025Haoyi Duan, Hong-Xing Yu et al.

VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness

2025Dian Zheng, Ziqi Huang et al.

Wan: Open and Advanced Large-Scale Video Generative Models

2025Ang Wang, Baole Ai et al.

Mask2DiT: Dual Mask-based Diffusion Transformer for Multi-Scene Long Video Generation

2025Tianhao Qi, Jian-min Yuan et al.

WorldModelBench: Judging Video Generation Models As World Models

2025Dacheng Li, Yunhao Fang et al.

MagicComp: Training-free Dual-Phase Refinement for Compositional Video Generation

2025Hongyu Zhang, Yufan Deng et al.

DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation

2024Minghong Cai, Xiaodong Cun et al.

Evaluation Agent: Efficient and Promptable Evaluation Framework for Visual Generative Models

2024Fan Zhang, Shulin Tian et al.

Mind the Time: Temporally-Controlled Multi-Event Video Generation

2024Ziyi Wu, Aliaksandr Siarohin et al.

Open-Sora Plan: Open-Source Large Video Generation Model

2024Bin Lin, Yunyang Ge et al.

WF-VAE: Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model

2024Zongjian Li, Bin Lin et al.

How Far is Video Generation from World Model: A Physical Law Perspective

2024Bingyi Kang, Yang Yue et al.

Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent

2024Tencent Hunyuan Team

VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs

2024Ruotong Liao, Max Erler et al.

CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer

2024Zhuoyi Yang, Jiayan Teng et al.

FIFO-Diffusion: Generating Infinite Videos from Text without Training

2024Jihwan Kim, Junoh Kang et al.

Showing 20 of 38 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 WorkTIDE: Text-Informed Dynamic Extrapolation with Step-Aware Temperature Control for Diffusion Transformers

7.0

Extension

Builds On ThisAccelerating Diffusion-based Video Editing via Heterogeneous Caching: Beyond Full Computing at Sampled Denoising Timestep

5.0

Builds On ThisDDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers

6.0

Builds On ThisBeyond Few-Step Inference: Accelerating Video Diffusion Transformer Model Serving with Inter-Request Caching Reuse

5.0

Commercially relevant

Higher ViabilityViFeEdit: A Video-Free Tuner of Your Video Diffusion Transformer

8.0

Higher ViabilityDiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Control

8.0

Conflicting

Competing ApproachFrameDiT: Diffusion Transformer with Frame-Level Matrix Attention for Efficient Video Generation

7.0

Competing ApproachRetrieval, Refinement, and Ranking for Text-to-Video Generation via Prompt Optimization and Test-Time Scaling

6.0

Competing ApproachFAIRT2V: Training-Free Debiasing for Text-to-Video Diffusion Models

6.0

Competing ApproachRobust and Generalizable Safety Steering for Text-to-Image Diffusion Transformers

4.0

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: 2605.31590
Route: /paper/tunerdit-training-free-progressive-steering-of-diffusion-transformer-for-multi-event-video-generation
Active tab: read
Artifact: tunerdit-training-free-progressive-steering-of-diffusion-transformer-for-multi-event-video-generation

Available agents

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

API/MCP endpoints

REST paper pack API/api/v1/paper/tunerdit-training-free-progressive-steering-of-diffusion-transformer-for-multi-event-video-generation/paper-pack
REST build passport API/api/v1/paper/tunerdit-training-free-progressive-steering-of-diffusion-transformer-for-multi-event-video-generation/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": "dabaab48-b2fc-41cb-84ba-f00127ab89df",
  "arxiv_id": "2605.31590",
  "canonical_route": "/paper/tunerdit-training-free-progressive-steering-of-diffusion-transformer-for-multi-event-video-generation",
  "active_tab": "synced from current hash by the drawer client",
  "selected_artifact": "tunerdit-training-free-progressive-steering-of-diffusion-transformer-for-multi-event-video-generation",
  "endpoints": {
    "paper_pack": "/api/v1/paper/tunerdit-training-free-progressive-steering-of-diffusion-transformer-for-multi-event-video-generation/paper-pack",
    "build_passport": "/api/v1/paper/tunerdit-training-free-progressive-steering-of-diffusion-transformer-for-multi-event-video-generation/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/tunerdit-training-free-progressive-steering-of-diffusion-transformer-for-multi-event-video-generation

stale

Proof freshness: stale
Proof status: unverified
Display score: 7/10
Last proof check: 2026-06-01
Score updated: 2026-06-01
Score fresh until: 2026-07-01
References: 0
Source count: 4
Coverage: 50%

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

TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation

Canonical ID tunerdit-training-free-progressive-steering-of-diffusion-transformer-for-multi-event-video-generation | Route /paper/tunerdit-training-free-progressive-steering-of-diffusion-transformer-for-multi-event-video-generation

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/paper/tunerdit-training-free-progressive-steering-of-diffusion-transformer-for-multi-event-video-generation

MCP example

{
  "tool": "get_paper",
  "arguments": {
    "arxiv_id": "2605.31590"
  }
}

source_context

{
  "surface": "paper",
  "mode": "paper",
  "query": "TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation",
  "normalized_query": "2605.31590",
  "route": "/paper/tunerdit-training-free-progressive-steering-of-diffusion-transformer-for-multi-event-video-generation",
  "paper_ref": "tunerdit-training-free-progressive-steering-of-diffusion-transformer-for-multi-event-video-generation",
  "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

Ready for execution: TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation

/buildability/tunerdit-training-free-progressive-steering-of-diffusion-transformer-for-multi-event-video-generation

Build Nowready

Subject: TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation

Verdict

Build Now

Verdict is Build Now because viability and implementation proof cleared the Wave 1 scaffold thresholds.

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/tunerdit-training-free-progressive-steering-of-diffusion-transformer-for-multi-event-video-generation

Paper ref

tunerdit-training-free-progressive-steering-of-diffusion-transformer-for-multi-event-video-generation

arXiv id

2605.31590

Freshness

Generated at

2026-06-01T20:21:18.318Z

Evidence freshness

stale

Last verification

2026-06-01T20:21:18.318Z

Sources

References

Coverage

50%

Hash state

Lineage hash

0ded81b382e31659334d714494e0c3b59857e46883d9a126052178dd20508aac

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: references
Missing: proof_status
Missing: paper_extraction_scorecards
Unknown: proof verification has not been recorded yet

Pending verification refs / 4 sources / Verification pending

references

proof_status

Missing proof, requirement, signature, approval, adoption, or telemetry fields are blockers and must not be inferred.

Open receipt API receipt Build Loop Signal Canvas Proof divergence Divergence API Brier outcomes API

Source Proof anchors

Visual citations from the paper document graph.

Source proof

Visual citation anchors from the paper document graph.

18 anchors

proof blockPage 368%

This equation captures one of the core mathematical components of the system. Let 𝑥∈[0, 1] be the fusion ratio and 𝑛∈[0, 𝑁] the

Page and bbox are available; crop image is pending.

proof blockPage 568%

This equation captures one of the core mathematical components of the system. ( 𝑇1, 𝑛< 𝜏PF, 𝑇𝑒, 𝑛≥𝜏PF b𝑇𝑒(𝑛) = and b𝑇(𝑛) = [b𝑇1(𝑛); . . . ; b𝑇𝐸(𝑛)]. Thus, in the coarse

Page and bbox are available; crop image is pending.

proof blockPage 568%

This equation captures one of the core mathematical components of the system. b𝑇𝑒(𝑛) = and b𝑇(𝑛) = [b𝑇1(𝑛); . . . ; b𝑇𝐸(𝑛)]. Thus, in the coarse layout diff

Page and bbox are available; crop image is pending.

JSON-LD twin

The application/ld+json payload rendered for agents.

{
  "@context": "https://schema.org",
  "@graph": [
    {
      "@type": "WebPage",
      "@id": "https://sciencetostartup.com/paper/tunerdit-training-free-progressive-steering-of-diffusion-transformer-for-multi-event-video-generation#webpage",
      "url": "https://sciencetostartup.com/paper/tunerdit-training-free-progressive-steering-of-diffusion-transformer-for-multi-event-video-generation",
      "name": "TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation",
      "description": "A training-free method to progressively steer diffusion transformers for multi-event video generation by partitioning events and fusing prompts.",
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      }
    },
    {
      "@type": "ScholarlyArticle",
      "@id": "https://sciencetostartup.com/paper/tunerdit-training-free-progressive-steering-of-diffusion-transformer-for-multi-event-video-generation#scholarlyArticle",
      "headline": "TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation",
      "description": "A training-free method to progressively steer diffusion transformers for multi-event video generation by partitioning events and fusing prompts.",
      "url": "https://sciencetostartup.com/paper/tunerdit-training-free-progressive-steering-of-diffusion-transformer-for-multi-event-video-generation",
      "sameAs": "https://arxiv.org/abs/2605.31590",
      "identifier": {
        "@type": "PropertyValue",
        "propertyID": "arXiv",
        "value": "2605.31590"
      },
      "isAccessibleForFree": true,
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      },
      "datePublished": "2026-05-29T17:56:09.000Z",
      "author": [
        {
          "@type": "Person",
          "name": "Ruotong Liao"
        },
        {
          "@type": "Person",
          "name": "Guowen Huang"
        },
        {
          "@type": "Person",
          "name": "Qing Cheng"
        },
        {
          "@type": "Person",
          "name": "Guangyao Zhai"
        },
        {
          "@type": "Person",
          "name": "Lei Zhang"
        },
        {
          "@type": "Person",
          "name": "Xun Xiao"
        },
        {
          "@type": "Person",
          "name": "Thomas Seidl"
        },
        {
          "@type": "Person",
          "name": "Daniel Cremers"
        },
        {
          "@type": "Person",
          "name": "Volker Tresp"
        }
      ],
      "citation": [
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "ea4f07ad73250afa7f52720f322479f91f7973b4"
          },
          "url": "https://www.semanticscholar.org/paper/ea4f07ad73250afa7f52720f322479f91f7973b4"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "a39de7a5d8e0bf414dacde4119da6e328138ba12"
          },
          "url": "https://www.semanticscholar.org/paper/a39de7a5d8e0bf414dacde4119da6e328138ba12"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "a8eeaa10c87f7ae7746ddd35eb20746c33d4b3fe"
          },
          "url": "https://www.semanticscholar.org/paper/a8eeaa10c87f7ae7746ddd35eb20746c33d4b3fe"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "ef29ae9f1b6c2c2ce56f7a09bc1a06a9156d3196"
          },
          "url": "https://www.semanticscholar.org/paper/ef29ae9f1b6c2c2ce56f7a09bc1a06a9156d3196"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "d6a5f0339ddf541482b39ab4e25d670191ef1903"
          },
          "url": "https://www.semanticscholar.org/paper/d6a5f0339ddf541482b39ab4e25d670191ef1903"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "6d4def9e60c21ccf6e7620f619cd621b50363c5b"
          },
          "url": "https://www.semanticscholar.org/paper/6d4def9e60c21ccf6e7620f619cd621b50363c5b"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "8877e9a5bf473404c35b758faa76905c202f0f36"
          },
          "url": "https://www.semanticscholar.org/paper/8877e9a5bf473404c35b758faa76905c202f0f36"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "ed68d3a973b55185a55e711b8039dd0425711402"
          },
          "url": "https://www.semanticscholar.org/paper/ed68d3a973b55185a55e711b8039dd0425711402"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "140830e42ee59e253b345f1e0434757e1ae8bbdf"
          },
          "url": "https://www.semanticscholar.org/paper/140830e42ee59e253b345f1e0434757e1ae8bbdf"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "211e915b2e1e0753ddd581f10362fc82f28cc606"
          },
          "url": "https://www.semanticscholar.org/paper/211e915b2e1e0753ddd581f10362fc82f28cc606"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "3938ed7e4120c53950a8dd2fe1e43d11ee4e64dd"
          },
          "url": "https://www.semanticscholar.org/paper/3938ed7e4120c53950a8dd2fe1e43d11ee4e64dd"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "0984e3c9ccfcecd0f31f5b6b2332885588400138"
          },
          "url": "https://www.semanticscholar.org/paper/0984e3c9ccfcecd0f31f5b6b2332885588400138"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "ae588b682150047b5f8adc3d73fa09a9fdf17edb"
          },
          "url": "https://www.semanticscholar.org/paper/ae588b682150047b5f8adc3d73fa09a9fdf17edb"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "58d9eaa0868e971687c20d0588de3058b7780b51"
          },
          "url": "https://www.semanticscholar.org/paper/58d9eaa0868e971687c20d0588de3058b7780b51"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "7a0f9a591fbb8b224e385351256b61c7a54be8f9"
          },
          "url": "https://www.semanticscholar.org/paper/7a0f9a591fbb8b224e385351256b61c7a54be8f9"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "a7ad5a50dc5d651d9182471ec32470d4f1b645e8"
          },
          "url": "https://www.semanticscholar.org/paper/a7ad5a50dc5d651d9182471ec32470d4f1b645e8"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "10edb97e60935e3ed4ef4976d38356bff714fac3"
          },
          "url": "https://www.semanticscholar.org/paper/10edb97e60935e3ed4ef4976d38356bff714fac3"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "7b248d78573ccf0dca6aa2cec2743d3eccaa9d1a"
          },
          "url": "https://www.semanticscholar.org/paper/7b248d78573ccf0dca6aa2cec2743d3eccaa9d1a"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "f25aeb6e9bb6b52540d9b9f2cf7b4df1a59f85a9"
          },
          "url": "https://www.semanticscholar.org/paper/f25aeb6e9bb6b52540d9b9f2cf7b4df1a59f85a9"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "22ae025a4f0b644369d05a3e13c0021f868a8372"
          },
          "url": "https://www.semanticscholar.org/paper/22ae025a4f0b644369d05a3e13c0021f868a8372"
        }
      ],
      "codeRepository": "https://github.com/cvpr-org/author-kit",
      "additionalProperty": [
        {
          "@type": "PropertyValue",
          "propertyID": "viabilityScore",
          "value": 7
        },
        {
          "@type": "PropertyValue",
          "propertyID": "researchDomain",
          "value": "Generative Video"
        },
        {
          "@type": "PropertyValue",
          "propertyID": "commercialReadiness",
          "value": "code, repo url"
        }
      ]
    },
    {
      "@type": "SoftwareSourceCode",
      "@id": "https://sciencetostartup.com/paper/tunerdit-training-free-progressive-steering-of-diffusion-transformer-for-multi-event-video-generation#software",
      "name": "TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation - Source Code",
      "description": "A training-free method to progressively steer diffusion transformers for multi-event video generation by partitioning events and fusing prompts.",
      "codeRepository": "https://github.com/cvpr-org/author-kit",
      "url": "https://github.com/cvpr-org/author-kit"
    },
    {
      "@type": "BreadcrumbList",
      "itemListElement": [
        {
          "@type": "ListItem",
          "position": 1,
          "name": "Home",
          "item": "https://sciencetostartup.com"
        },
        {
          "@type": "ListItem",
          "position": 2,
          "name": "Generative Video",
          "item": "https://sciencetostartup.com/topics"
        },
        {
          "@type": "ListItem",
          "position": 3,
          "name": "TunerDiT: Training-free Progressive Steering of Diffusion Tr",
          "item": "https://sciencetostartup.com/paper/tunerdit-training-free-progressive-steering-of-diffusion-transformer-for-multi-event-video-generation"
        }
      ]
    }
  ]
}

TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation

TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(38)

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(38)

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