When Identities Collapse: A Stress-Test Benchmark for Multi-Subject Personalization

• URL: http://arxiv.org/abs/2603.26078v1
• Date: Fri, 27 Mar 2026 05:12:22 GMT
• Title: When Identities Collapse: A Stress-Test Benchmark for Multi-Subject Personalization
• Abstract summary: We introduce the Subject Collapse Rate (SCR), a novel evaluation metric grounded in DINOv2's structural priors.<n>Our evaluation reveals a precipitous drop in identity fidelity as scene complexity grows, with SCR approaching 100% at 10 subjects.
• Score: 3.245046496701612
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Subject-driven text-to-image diffusion models have achieved remarkable success in preserving single identities, yet their ability to compose multiple interacting subjects remains largely unexplored and highly challenging. Existing evaluation protocols typically rely on global CLIP metrics, which are insensitive to local identity collapse and fail to capture the severity of multi-subject entanglement. In this paper, we identify a pervasive "Illusion of Scalability" in current models: while they excel at synthesizing 2-4 subjects in simple layouts, they suffer from catastrophic identity collapse when scaled to 6-10 subjects or tasked with complex physical interactions. To systematically expose this failure mode, we construct a rigorous stress-test benchmark comprising 75 prompts distributed across varying subject counts and interaction difficulties (Neutral, Occlusion, Interaction). Furthermore, we demonstrate that standard CLIP-based metrics are fundamentally flawed for this task, as they often assign high scores to semantically correct but identity-collapsed images (e.g., generating generic clones). To address this, we introduce the Subject Collapse Rate (SCR), a novel evaluation metric grounded in DINOv2's structural priors, which strictly penalizes local attention leakage and homogenization. Our extensive evaluation of state-of-the-art models (MOSAIC, XVerse, PSR) reveals a precipitous drop in identity fidelity as scene complexity grows, with SCR approaching 100% at 10 subjects. We trace this collapse to the semantic shortcuts inherent in global attention routing, underscoring the urgent need for explicit physical disentanglement in future generative architectures.

Related papers

• Inter-X++: A Comprehensive Benchmark for Multimodal Human-Human Interaction Analysis [55.78822230833247]
  We present Inter-X++, a comprehensive and large-scale benchmark designed to empower versatile HHI analysis.<n>Inter-X++ provides 11,388 high-fidelity interaction sequences and over 8.1M frames, featuring precise whole-body movements and detailed finger articulations.<n>We propose OpenHHI, a single and unified HHI representation and modeling framework that jointly optimize interaction reconstruction and semantic understanding.
  arXiv  Detail & Related papers  (2026-08-20T17:51:48Z)
• Beyond Static Dialogues: Benchmarking Realistic, Heterogeneous, and Evolving Long-Term Memory [54.947805187562274]
  We introduce realistic dialogues across diverse interaction scenarios that exhibit dynamic temporal evolution and long-term coherence.<n>The resulting benchmark encompasses challenging question-answer pairs spanning seven inquiry types.<n>We identify at least one of 27 critical memory characteristics that we identify as essential yet underexplored in current research.
  arXiv  Detail & Related papers  (2026-05-29T09:51:22Z)
• From Intent to Evidence: A Categorical Approach for Structural Evaluation of Deep Research Agents [25.080554451314683]
  Deep research agents (DRAs) have emerged as a promising paradigm for complex information synthesis.<n>We formalize DRA behavior through the lens of category theory, modeling deep research workflow as a composition of structure-preserving maps.<n>We introduce a novel mechanism-aware benchmark with 296 questions designed to stress-test agents along four interpretable axes.
  arXiv  Detail & Related papers  (2026-03-26T11:37:26Z)
• AnyCrowd: Instance-Isolated Identity-Pose Binding for Arbitrary Multi-Character Animation [55.94507360511886]
  We propose AnyCrowd, a Transformer-based video generation framework capable of scaling to an arbitrary number of characters.<n>Specifically, we first introduce an Instance-Isolated Latent Representation (IILR), which encodes character instances independently prior to DiT processing to prevent latent identity entanglement.<n>Building on this disentangled representation, we further propose Tri-Stage Decoupled Attention (TSDA) to bind identities to driving poses by decomposing self-attention into: (i) instance-aware foreground attention, (ii) background-centric interaction, and (iii) global-background coordination.
  arXiv  Detail & Related papers  (2026-03-16T15:25:04Z)
• OMG-Agent: Toward Robust Missing Modality Generation with Decoupled Coarse-to-Fine Agentic Workflows [9.617220633655716]
  We present textbfunderlineOmni-textbfunderlineModality textbfunderlineGeneration Agent (textbfOMG-Agent)
  arXiv  Detail & Related papers  (2026-02-04T02:25:40Z)
• Relative Classification Accuracy: A Calibrated Metric for Identity Consistency in Fine-Grained K-pop Face Generation [0.0]
  Denoising Diffusion Probabilistic Models (DDPMs) have achieved remarkable success in high-fidelity image generation.<n>Standard metrics like FID and Inception Score (IS) often fail to detect identity misalignment in such specialized contexts.<n>We investigate Class-Conditional DDPMs for K-pop idol face generation (32x32), a domain characterized by high inter-class similarity.
  arXiv  Detail & Related papers  (2026-01-22T00:58:59Z)
• From Feature Interaction to Feature Generation: A Generative Paradigm of CTR Prediction Models [81.43473418572567]
  Click-Through Rate (CTR) prediction is a core task in recommendation systems.<n>We propose a novel generative framework to address embedding dimensional collapse and information redundancy.<n>We show that SFG consistently mitigates embedding collapse and reduces information redundancy, while yielding substantial performance gains.
  arXiv  Detail & Related papers  (2025-12-16T03:17:18Z)
• Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights [41.385614383367205]
  Current models aim to transcend the limitations of single-modality representations by unifying understanding and generation.<n>Their reliance on static single-image generation in training and evaluation leads to overfitting to static pattern matching and semantic fusion.<n>We propose Envision-a causal event progression benchmark for chained text-to-multi-image generation.
  arXiv  Detail & Related papers  (2025-12-01T15:52:31Z)
• ShortcutBreaker: Low-Rank Noisy Bottleneck with Global Perturbation Attention for Multi-Class Unsupervised Anomaly Detection [59.89803740308262]
  ShortcutBreaker is a novel unified feature-reconstruction framework for MUAD tasks.<n>It features two key innovations to address the issue of shortcuts.<n>The proposed method achieves a remarkable image-level AUROC of 99.8%, 98.9%, 90.6%, and 87.8% on four datasets.
  arXiv  Detail & Related papers  (2025-10-21T06:51:30Z)
• Hierarchical Self-Supervised Representation Learning for Depression Detection from Speech [51.14752758616364]
  Speech-based depression detection (SDD) is a promising, non-invasive alternative to traditional clinical assessments.<n>We propose HAREN-CTC, a novel architecture that integrates multi-layer SSL features using cross-attention within a multitask learning framework.<n>The model achieves state-of-the-art macro F1-scores of 0.81 on DAIC-WOZ and 0.82 on MODMA, outperforming prior methods across both evaluation scenarios.
  arXiv  Detail & Related papers  (2025-10-05T09:32:12Z)
• MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement [13.100620283631557]
  We present MOSAIC, a representation-centric framework that rethinks multi-subject generation.<n>Our key insight is that multi-subject generation requires precise semantic alignment at the representation level.<n>We propose the semantic correspondence attention loss to enforce precise point-to-point semantic alignment.
  arXiv  Detail & Related papers  (2025-09-02T05:40:07Z)
• Decoupled Multi-task Learning with Cyclical Self-Regulation for Face Parsing [71.19528222206088]
  We propose a novel Decoupled Multi-task Learning with Cyclical Self-Regulation for face parsing. Specifically, DML-CSR designs a multi-task model which comprises face parsing, binary edge, and category edge detection. Our method achieves the new state-of-the-art performance on the Helen, CelebA-HQ, and LapaMask datasets.
  arXiv  Detail & Related papers  (2022-03-28T02:12:30Z)
• Intra-Camera Supervised Person Re-Identification [87.88852321309433]
  We propose a novel person re-identification paradigm based on an idea of independent per-camera identity annotation. This eliminates the most time-consuming and tedious inter-camera identity labelling process. We formulate a Multi-tAsk mulTi-labEl (MATE) deep learning method for Intra-Camera Supervised (ICS) person re-id.
  arXiv  Detail & Related papers  (2020-02-12T15:26:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.