ARXIV:2603.25743 · GENERATIVE VIDEO · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

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

RefAlign: Representation Alignment for Reference-to-Video Generation

Lei Wang · YuXin Song · Ge Wu · Haocheng Feng · Hang Zhou · Jingdong Wang · +2 at arXiv

A framework to improve identity consistency and reduce artifacts in reference-to-video generation by explicitly aligning visual features.

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

Opportunity summary

Pain A framework to improve identity consistency and reduce artifacts in reference-to-video generation by explicitly aligning visual features.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

A framework to improve identity consistency and reduce artifacts in reference-to-video generation by explicitly aligning visual features. In practice, existing R2V methods typically introduce additional high-level semantic or cross-modal features alongside the VAE latent…

METHOD

Full abstract

Reference-to-video (R2V) generation is a controllable video synthesis paradigm that constrains the generation process using both text prompts and reference images, enabling applications such as personalized advertising and virtual try-on. In practice, existing R2V methods typically introduce additional high-level semantic or cross-modal features alongside the VAE latent representation of the reference image and jointly feed them into the diffusion Transformer (DiT). These auxiliary representations provide semantic guidance and act as implicit alignment signals, which can partially alleviate pixel-level information leakage in the VAE latent space. However, they may still struggle to address copy--paste artifacts and multi-subject confusion caused by modality mismatch across heterogeneous encoder features. In this paper, we propose RefAlign, a representation alignment framework that explicitly aligns DiT reference-branch features to the semantic space of a visual foundation model (VFM). The core of RefAlign is a reference alignment loss that pulls the reference features and VFM features of the same subject closer to improve identity consistency, while pushing apart the corresponding features of different subjects to enhance semantic discriminability. This simple yet effective strategy is applied only during training, incurring no inference-time overhead, and achieves a better balance between text controllability and reference fidelity. Extensive experiments on the OpenS2V-Eval benchmark demonstrate that RefAlign outperforms current state-of-the-art methods in TotalScore, validating the effectiveness of explicit reference alignment for R2V tasks.

RESULT

ScienceToStartup currently rates this 7.0/10 on the public viability pass. The core of RefAlign is a reference alignment loss that pulls the reference features and VFM features of the same subject closer to improve…

WHY NOW

Generative Video moved forward this cycle; last verified April 2026. Public score 7.0/10. Production flags indicate code availability.

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

Opportunity summary

Score7.0

PainA framework to improve identity consistency and reduce artifacts in reference-to-video generation by explicitly aligning visual features.

Evidence0 refs | 0 sources | 17% coverage

Blockerno shell-level blocker reported

Analysis summary

A framework to improve identity consistency and reduce artifacts in reference-to-video generation by explicitly aligning visual features.

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

ARXIV:2603.25743 · GENERATIVE VIDEO · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

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

RefAlign: Representation Alignment for Reference-to-Video Generation

Lei Wang · YuXin Song · Ge Wu · Haocheng Feng · Hang Zhou · Jingdong Wang · +2 at arXiv

A framework to improve identity consistency and reduce artifacts in reference-to-video generation by explicitly aligning visual features.

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

Opportunity summary

Pain A framework to improve identity consistency and reduce artifacts in reference-to-video generation by explicitly aligning visual features.

Evidence 0 refs | 0 sources | 17% 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 April 2026. Public score 7.0/10. Production flags indicate code availability.

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

Opportunity summary

Score7.0

PainA framework to improve identity consistency and reduce artifacts in reference-to-video generation by explicitly aligning visual features.

Evidence0 refs | 0 sources | 17% coverage

Blockerno shell-level blocker reported

Analysis summary

A framework to improve identity consistency and reduce artifacts in reference-to-video generation by explicitly aligning visual features.

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

Paper Pack

10.48550/arXiv.2603.25743

RefAlign: Representation Alignment for Reference-to-Video Generation

A framework to improve identity consistency and reduce artifacts in reference-to-video generation by explicitly aligning visual features.

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 fallback51 indexednot indexed

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

Viability

7.0

Time to MVP

MVP estimate missing

Commercial

code

Export

Preparing verified analysis

lens / founder

PROBLEM

METHOD

RESULT

WHY NOW

Generative Video moved forward this cycle; last verified April 2026. Public score 7.0/10. Production flags indicate code availability.

Claim map

Abstract-backed public claims while anchored extraction refreshes.

Strong 0Mixed 0Weak 4

Evidencepartial
A framework to improve identity consistency and reduce artifacts in reference-to-video generation by explicitly aligning visual features. In practice, existing R2V methods typically introduce additional high-level semantic or cross-modal features alongside the VAE latent representation of the reference image and jointly feed them into the diffusion Transformer (DiT).
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Reference-to-video (R2V) generation is a controllable video synthesis paradigm that constrains the generation process using both text prompts and reference images, enabling applications such as personalized advertising and virtual try-on. In practice, existing R2V methods typically introduce additional high-level semantic or cross-modal features alongside the VAE latent representation of the reference image and jointly feed them into the diffusion Transformer (DiT).
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. The core of RefAlign is a reference alignment loss that pulls the reference features and VFM features of the same subject closer to improve identity consistency, while pushing apart the corresponding features of different subjects to enhance semantic discriminability. Code availability is flagged in the production record; the public repository link still needs proof alignment.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Generative Video moved forward this cycle; last verified April 2026. Public score 7.0/10. Production flags indicate code availability.
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

Generative Video

Competitors

not indexed

Competitive landscape

A framework to improve identity consistency and reduce artifacts in reference-to-video generation by explicitly aligning visual features.

Segment

Generative Video

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 2603.25743 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(51)

VINO: A Unified Visual Generator with Interleaved OmniModal Context

2026Junyi Chen, Tong He et al.

Kling-Omni Technical Report

2025Jialu Chen, Yuanzheng Ci et al.

Scaling Zero-Shot Reference-to-Video Generation

2025Zijian Zhou, Shikun Liu et al.

HunyuanVideo 1.5 Technical Report

2025Tencent Hunyuan Team

ID-Crafter: VLM-Grounded Online RL for Compositional Multi-Subject Video Generation

2025Panwang Pan, Jingjing Zhao et al.

Kaleido: Open-Sourced Multi-Subject Reference Video Generation Model

2025Zhenxing Zhang, Jiayan Teng et al.

BindWeave: Subject-Consistent Video Generation via Cross-Modal Integration

2025Zhaoyang Li, Dongjun Qian et al.

Lynx: Towards High-Fidelity Personalized Video Generation

2025Shen Sang, Tiancheng Zhi et al.

DINOv3

2025Oriane Sim'eoni, Huy V. Vo et al.

Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation

2025Bowen Xue, Qixin Yan et al.

Representation Entanglement for Generation:Training Diffusion Transformers Is Much Easier Than You Think

2025Ge Wu, Shen Zhang et al.

Phantom-Data : Towards a General Subject-Consistent Video Generation Dataset

2025Zhuowei Chen, Bingchuan Li et al.

PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement

2025Teng Hu, Zhentao Yu et al.

VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models

2025Xiangdong Zhang, Jiaqi Liao et al.

OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation

2025Shenghai Yuan, Xianyi He et al.

Pursuing Temporal-Consistent Video Virtual Try-On via Dynamic Pose Interaction

2025Dong Li, Wenqi Zhong et al.

HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation

2025Teng Hu, Zhentao Yu et al.

Boosting Generative Image Modeling via Joint Image-Feature Synthesis

2025Theodoros Kouzelis, Efstathios Karypidis et al.

REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers

2025Xingjian Leng, Jaskirat Singh et al.

SwiftTry: Fast and Consistent Video Virtual Try-On with Diffusion Models

2025Hung Nguyen, Q. Nguyen et al.

Showing 20 of 51 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 WorkCVA: Context-aware Video-text Alignment for Video Temporal Grounding

7.0

Prior WorkRoboAlign-R1: Distilled Multimodal Reward Alignment for Robot Video World Models

7.0

Prior WorkAligning Few-Step Generative Models by Amortizing Sample-based Variational Inference

7.0

Prior WorkFrom Noise to Intent: Anchoring Generative VLA Policies with Residual Bridges

7.0

Prior WorkRefReward-SR: LR-Conditioned Reward Modeling for Preference-Aligned Super-Resolution

7.0

Extension

Builds On ThisTraining-Free Representation Guidance for Diffusion Models with a Representation Alignment Projector

6.0

Builds On ThisLet's Roll a BiFTA: Bi-refinement for Fine-grained Text-visual Alignment in Vision-Language Models

6.0

Builds On ThisAHPA: Adaptive Hierarchical Prior Alignment for Diffusion Transformers

3.0

Builds On ThisReferences Improve LLM Alignment in Non-Verifiable Domains

6.0

Commercially relevant

none indexed

Conflicting

Competing ApproachVIGOR: VIdeo Geometry-Oriented Reward for Temporal Generative Alignment

7.0

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: 2603.25743
Route: /paper/refalign-representation-alignment-for-reference-to-video-generation
Active tab: read
Artifact: refalign-representation-alignment-for-reference-to-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/refalign-representation-alignment-for-reference-to-video-generation/paper-pack
REST build passport API/api/v1/paper/refalign-representation-alignment-for-reference-to-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": "194f9205-e988-4450-8544-af56d732cbd0",
  "arxiv_id": "2603.25743",
  "canonical_route": "/paper/refalign-representation-alignment-for-reference-to-video-generation",
  "active_tab": "synced from current hash by the drawer client",
  "selected_artifact": "refalign-representation-alignment-for-reference-to-video-generation",
  "endpoints": {
    "paper_pack": "/api/v1/paper/refalign-representation-alignment-for-reference-to-video-generation/paper-pack",
    "build_passport": "/api/v1/paper/refalign-representation-alignment-for-reference-to-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/refalign-representation-alignment-for-reference-to-video-generation

stale

Proof freshness: stale
Proof status: unverified
Display score: 7/10
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

RefAlign: Representation Alignment for Reference-to-Video Generation

Canonical ID refalign-representation-alignment-for-reference-to-video-generation | Route /paper/refalign-representation-alignment-for-reference-to-video-generation

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/paper/refalign-representation-alignment-for-reference-to-video-generation

MCP example

{
  "tool": "get_paper",
  "arguments": {
    "arxiv_id": "2603.25743"
  }
}

source_context

{
  "surface": "paper",
  "mode": "paper",
  "query": "RefAlign: Representation Alignment for Reference-to-Video Generation",
  "normalized_query": "2603.25743",
  "route": "/paper/refalign-representation-alignment-for-reference-to-video-generation",
  "paper_ref": "refalign-representation-alignment-for-reference-to-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

Watch and verify: RefAlign: Representation Alignment for Reference-to-Video Generation

/buildability/refalign-representation-alignment-for-reference-to-video-generation

Watchwatch

Subject: RefAlign: Representation Alignment for Reference-to-Video Generation

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/refalign-representation-alignment-for-reference-to-video-generation

Paper ref

refalign-representation-alignment-for-reference-to-video-generation

arXiv id

2603.25743

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

7f96228040891e10a2cb5272cc92f02cd30a7444b8e5c3eed46a91eccb819487

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/refalign-representation-alignment-for-reference-to-video-generation#webpage",
      "url": "https://sciencetostartup.com/paper/refalign-representation-alignment-for-reference-to-video-generation",
      "name": "RefAlign: Representation Alignment for Reference-to-Video Generation",
      "description": "A framework to improve identity consistency and reduce artifacts in reference-to-video generation by explicitly aligning visual features.",
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      }
    },
    {
      "@type": "ScholarlyArticle",
      "@id": "https://sciencetostartup.com/paper/refalign-representation-alignment-for-reference-to-video-generation#scholarlyArticle",
      "headline": "RefAlign: Representation Alignment for Reference-to-Video Generation",
      "description": "A framework to improve identity consistency and reduce artifacts in reference-to-video generation by explicitly aligning visual features.",
      "url": "https://sciencetostartup.com/paper/refalign-representation-alignment-for-reference-to-video-generation",
      "sameAs": "https://arxiv.org/abs/2603.25743",
      "identifier": {
        "@type": "PropertyValue",
        "propertyID": "arXiv",
        "value": "2603.25743"
      },
      "isAccessibleForFree": true,
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      },
      "datePublished": "2026-03-26T17:59:57.000Z",
      "author": [
        {
          "@type": "Person",
          "name": "Lei Wang"
        },
        {
          "@type": "Person",
          "name": "YuXin Song"
        },
        {
          "@type": "Person",
          "name": "Ge Wu"
        },
        {
          "@type": "Person",
          "name": "Haocheng Feng"
        },
        {
          "@type": "Person",
          "name": "Hang Zhou"
        },
        {
          "@type": "Person",
          "name": "Jingdong Wang"
        },
        {
          "@type": "Person",
          "name": "Yaxing Wang"
        },
        {
          "@type": "Person",
          "name": "jian Yang"
        }
      ],
      "citation": [
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "44e491575936fb1209b04143ac60fd34f10d26a6"
          },
          "url": "https://www.semanticscholar.org/paper/44e491575936fb1209b04143ac60fd34f10d26a6"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "cc19152efc6b3f5b6c6be088190f75b18ce4d37c"
          },
          "url": "https://www.semanticscholar.org/paper/cc19152efc6b3f5b6c6be088190f75b18ce4d37c"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "d2aa044edf9104d129b16ce138dfa703630242c9"
          },
          "url": "https://www.semanticscholar.org/paper/d2aa044edf9104d129b16ce138dfa703630242c9"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "590b86f2145337fef22fca2eb5e48e0073f37fad"
          },
          "url": "https://www.semanticscholar.org/paper/590b86f2145337fef22fca2eb5e48e0073f37fad"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "d64b13de45629fdeadadb9988270ade940b9f17f"
          },
          "url": "https://www.semanticscholar.org/paper/d64b13de45629fdeadadb9988270ade940b9f17f"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "de8f86912ac3ea6910a4d0cd2484939e0569308a"
          },
          "url": "https://www.semanticscholar.org/paper/de8f86912ac3ea6910a4d0cd2484939e0569308a"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "4b68bfb2ca6e160892c00219a8968592a0456c0e"
          },
          "url": "https://www.semanticscholar.org/paper/4b68bfb2ca6e160892c00219a8968592a0456c0e"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "bfc9bd8b867560a3a78598809fb2b32f40c30d5d"
          },
          "url": "https://www.semanticscholar.org/paper/bfc9bd8b867560a3a78598809fb2b32f40c30d5d"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "b49c1adc847c8e2cb9f1b97358366e4887e532ce"
          },
          "url": "https://www.semanticscholar.org/paper/b49c1adc847c8e2cb9f1b97358366e4887e532ce"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "c85ca3a98c9456e1bc224eaf584d800490ad8fd6"
          },
          "url": "https://www.semanticscholar.org/paper/c85ca3a98c9456e1bc224eaf584d800490ad8fd6"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "b243783f327ef9b44bc2bfe8e5fe36c4e459e055"
          },
          "url": "https://www.semanticscholar.org/paper/b243783f327ef9b44bc2bfe8e5fe36c4e459e055"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "c28d73ff26030b02fbdaa5b7ec8f225ad174836a"
          },
          "url": "https://www.semanticscholar.org/paper/c28d73ff26030b02fbdaa5b7ec8f225ad174836a"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "78bf03290fa82c1988f7f9ff7bdeac538edb0b5a"
          },
          "url": "https://www.semanticscholar.org/paper/78bf03290fa82c1988f7f9ff7bdeac538edb0b5a"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "eb2705902ab73312e59396244cb7c2c0f908aebd"
          },
          "url": "https://www.semanticscholar.org/paper/eb2705902ab73312e59396244cb7c2c0f908aebd"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "cafa4fea1abeca67383199d4e14d40308174e602"
          },
          "url": "https://www.semanticscholar.org/paper/cafa4fea1abeca67383199d4e14d40308174e602"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "ea95319efa7b024a15d6df9bb06d037ca077bffa"
          },
          "url": "https://www.semanticscholar.org/paper/ea95319efa7b024a15d6df9bb06d037ca077bffa"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "0df8b9e0c919274b38d79eb9ee580db6cece68d8"
          },
          "url": "https://www.semanticscholar.org/paper/0df8b9e0c919274b38d79eb9ee580db6cece68d8"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "63c2eb636abf2dd0454469b636ddb4a65cd2d2cb"
          },
          "url": "https://www.semanticscholar.org/paper/63c2eb636abf2dd0454469b636ddb4a65cd2d2cb"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "27a028c9ad4145d52d5e00619a7672ca0429aac2"
          },
          "url": "https://www.semanticscholar.org/paper/27a028c9ad4145d52d5e00619a7672ca0429aac2"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "65d8f6d85042f1be9a9b48e04b4f711da69b4255"
          },
          "url": "https://www.semanticscholar.org/paper/65d8f6d85042f1be9a9b48e04b4f711da69b4255"
        }
      ],
      "additionalProperty": [
        {
          "@type": "PropertyValue",
          "propertyID": "viabilityScore",
          "value": 7
        },
        {
          "@type": "PropertyValue",
          "propertyID": "researchDomain",
          "value": "Generative Video"
        },
        {
          "@type": "PropertyValue",
          "propertyID": "commercialReadiness",
          "value": "code"
        }
      ]
    },
    {
      "@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": "RefAlign: Representation Alignment for Reference-to-Video Ge",
          "item": "https://sciencetostartup.com/paper/refalign-representation-alignment-for-reference-to-video-generation"
        }
      ]
    }
  ]
}

RefAlign: Representation Alignment for Reference-to-Video Generation

RefAlign: Representation Alignment for Reference-to-Video Generation

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(51)

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(51)

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