Read original ↗
paperarXivTrust 82 · PrimaryPublished 1mo agoLive · 28d ago

When Physical Preferences Meet Semantic Constraints: Physical and Semantic Direct Preference Optimization for Text-to-Video Generation

Text-to-video (T2V) generation models have achieved strong visual realism, but improving physical plausibility can come at the cost of semantic consistency with the input text. This tension arises because physical preference is typically determined by comparing dynamics between two videos, without accounting for whether either video faithfully depicts the scene specified by the prompt, making physical-semantic conflict a systematic tendency under this supervision paradigm. We formulate this challenge as a constrained preference optimization problem and propose Physical and Semantic Direct Pref

Lineage graph

Paper → model → repo connections mined from source citations (Tier-1 exact match).

Why these links exist

Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.

  • FuzzyOverlapping authors or contributors · 62%modular/modular

    Shared author/contributor keys: liu

  • FuzzyOverlapping authors or contributors · 62%sgl-project/sglang

    Shared author/contributor keys: luo

  • FuzzySimilar title/name (fuzzy) · 59%microsoft/semantic-kernel

    Fuzzy title match (0.73): “When Physical Preferences Meet Semantic Constraints: Physica” ≈ “microsoft/semantic-kernel”

  • FuzzySimilar title/name (fuzzy) · 59%Developer-Y/cs-video-courses

    Fuzzy title match (0.73): “When Physical Preferences Meet Semantic Constraints: Physica” ≈ “Developer-Y/cs-video-courses”

  • LinkedLinked via arxiv author · 85%Siwei Meng

    When Physical Preferences Meet Semantic Constraints: Physical and Semantic Direct Preference Optimization for Text-to-Vi

  • LinkedLinked via arxiv author · 85%Yawei Luo

    When Physical Preferences Meet Semantic Constraints: Physical and Semantic Direct Preference Optimization for Text-to-Vi

  • LinkedLinked via arxiv author · 85%Shu Zhang

    When Physical Preferences Meet Semantic Constraints: Physical and Semantic Direct Preference Optimization for Text-to-Vi

  • LinkedLinked via arxiv author · 85%Huaping Liu

    When Physical Preferences Meet Semantic Constraints: Physical and Semantic Direct Preference Optimization for Text-to-Vi

Implements (incoming)

authored (incoming)

Related across the graph

Topics