TRACE-Bench: Decomposing and Diagnosing Multi-Reference Image Generation
Despite recent advances in unified multimodal models for multi-reference image generation, existing benchmarks remain organized around predefined task types (e.g., "subject composition"), which are ill-suited to this combinatorial setting and lead to fragmented coverage, uncontrolled complexity, and little diagnostic value. Recognizing that diverse multi-reference tasks share a common set of atomic operations, we adopt a capability-oriented perspective and formalize four operators: Anchor ($f$), Disentangle ($g$), Apply ($\oplus$), and Compose ($C$). Any multi-reference prompt can then be repr
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.
- FuzzySimilar title/name (fuzzy) · 59%Tongyi-MAI/Z-Image-Turbo →
“Fuzzy title match (0.73): “TRACE-Bench: Decomposing and Diagnosing Multi-Reference Imag” ≈ “Tongyi-MAI/Z-Image-Turbo””
- FuzzyOverlapping authors or contributors · 62%bytedance/deer-flow →
“Shared author/contributor keys: wang”
- FuzzyOverlapping authors or contributors · 62%ray-project/ray →
“Shared author/contributor keys: wang”
- LinkedLinked via arxiv author · 85%Haoran Wang →
“TRACE-Bench: Decomposing and Diagnosing Multi-Reference Image Generation”
- LinkedLinked via arxiv author · 85%Chaofan Ma →
“TRACE-Bench: Decomposing and Diagnosing Multi-Reference Image Generation”
- LinkedLinked via arxiv author · 85%Ran Yi →
“TRACE-Bench: Decomposing and Diagnosing Multi-Reference Image Generation”
- LinkedLinked via arxiv author · 85%Lizhuang Ma →
“TRACE-Bench: Decomposing and Diagnosing Multi-Reference Image Generation”