MIRAGE: A Micro-Interaction Relational Architecture for Grounded Exploration in Multi-Figure Artworks

• URL: http://arxiv.org/abs/2604.23788v1
• Date: Sun, 26 Apr 2026 16:25:30 GMT
• Title: MIRAGE: A Micro-Interaction Relational Architecture for Grounded Exploration in Multi-Figure Artworks
• Abstract summary: We present MIRAGE, an evidence-centric framework designed to scaffold the exploration of "micro-interactions" in multi-figure artworks.<n>Results show that MIRAGE significantly improves identity consistency, reduces relational hallucinations, and increases the coverage of subtle interactions.
• Score: 9.397297838455238
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Appreciating multi-figure paintings requires understanding how characters relate through subtle cues like gaze alignment, gesture, and spatial arrangement. We present MIRAGE, an evidence-centric framework designed to scaffold the exploration of these "micro-interactions" in multi-figure artworks. While such cues are essential for deep narrative appreciation, they are often distributed across complex scenes and difficult for viewers to systematically identify. Existing vision-language models (VLMs) frequently fail to provide reliable assistance, offering ungrounded interpretations that lack traceable visual evidence. MIRAGE addresses this by constructing a structured intermediate representation capturing identities, pose cues, and gaze hypotheses. However, the challenge extends beyond extracting these cues to coordinating them during interpretation. Without an explicit mechanism to organize and reconcile relational evidence, models often collapse multiple interaction hypotheses into a single unstable or weakly grounded narrative, even when low-level signals are available. This representation allows users to verify how high-level interpretations are anchored in low-level visual facts. By separating spatial grounding from narrative generation, MIRAGE enables users to inspect and reason about figure-to-figure relationships through a verifiable evidence layer. We evaluate MIRAGE against painting-only VLM baselines using a blind assessment protocol. Results show that MIRAGE significantly improves identity consistency, reduces relational hallucinations, and increases the coverage of subtle interactions. These findings suggest that structured grounding can serve as a critical interaction control layer, providing the necessary scaffolding for a more reliable, transparent, and human-led understanding of complex visual narratives.

Related papers

• MNIST-PRO: MNIST is Back as a Partially Observable World for AI Agents [74.83535434786145]
  MNIST-PRO is a benchmark that isolates agentic perception by converting MNIST digit recognition into a sequential, glimpse-based search task with lookback constraints.<n>We evaluate ten multimodal models across four memory representations, including raw visual history, textual states, structured metric grid maps, and a consolidated visual canvas.
  arXiv  Detail & Related papers  (2026-08-31T16:05:39Z)
• Do Large Language Models Play Six Degrees of Separation? Measuring Topological Compression in Long-Context Manifolds [1.8190501646350212]
  This work mathematically formalizes how transformers execute abstract reasoning and provides a novel, strictly geometric signature for evaluating factual reliability.<n>We show that factually grounded generations maintain structural integrity with their source context, whereas hallucinations induce severe topological collapse.
  arXiv  Detail & Related papers  (2026-08-18T16:05:25Z)
• Unleashing Multimodal Large Language Models for Training-free HOI Detection in the Wild [49.77540427384148]
  We present AgentHOI, a training-free, agentic framework that transfers the generalist multimodal reasoning capabilities of foundation models to HOI detection in the wild.<n>To address the challenges of incomplete interaction discovery and ambiguous localization in complex scenes, we introduce two key mechanisms.<n>AgentHOI achieves superior performance over state-of-the-art supervised and weakly supervised methods in real-world settings.
  arXiv  Detail & Related papers  (2026-07-15T14:30:20Z)
• Faithful Grounded Visual Reasoning via Learned Proxy-Tokens [1.5749416770494706]
  Grounded Visual Reasoning (GVR) approaches attempt to improve interpretability by explicitly couple textual rationales with visual grounding information.<n>This mechanism lacks a learnable semantic link to the visual features, often resulting in a semantic-spatial gap.<n>We introduce Composer, a MLLM that leverages a novel visual grounding mechanism based on learned proxy-tokens.
  arXiv  Detail & Related papers  (2026-06-22T13:54:48Z)
• Diagnosing Visual Ignorance in Vision-Language Models [29.2851901986069]
  Vision-Language Models (VLMs) frequently rely on language priors, producing confident answers that are weakly grounded in visual evidence.<n>In this work, we study language-prior reliance from both mechanistic and behavioral perspectives.<n>We find that language-prior reliance is a systematic routing failure affecting both model internals and benchmark validity.
  arXiv  Detail & Related papers  (2026-06-05T04:16:01Z)
• Using Machine Mental Imagery for Representing Common Ground in Situated Dialogue [3.1039961644960186]
  Situated dialogue requires speakers to maintain a reliable representation of shared context.<n>Current conversational agents often struggle with this requirement.<n>We introduce an active visual scaffolding framework that incrementally converts dialogue state into a persistent visual history.
  arXiv  Detail & Related papers  (2026-04-22T23:15:42Z)
• SpatialImaginer: Towards Adaptive Visual Imagination for Spatial Reasoning [67.67774742200626]
  spatial intelligence, which refers to the ability to reason about geometric and physical structure from visual observations, is a core challenge for large language models.<n>We propose a unified multimodal generation framework that integrates textual reasoning with visual imagination.<n>Our framework adopts a divide-and-conquer strategy, using text chain-of-thought for high-level semantic planning and the visual imagination for geometry-sensitive state transformation and consistency preservation.
  arXiv  Detail & Related papers  (2026-04-19T11:21:59Z)
• MISID: A Multimodal Multi-turn Dataset for Complex Intent Recognition in Strategic Deception Games [7.184720967960135]
  We introduce MISID, a comprehensive benchmark for intent recognition in multi-turn interactions.<n>Sourced from high-stakes social strategy games, MISID features a fine-grained, two-tier multi-dimensional annotation scheme tailored for long-context discourse analysis and evidence-based causal tracking.<n>Our systematic evaluation of state-of-the-art Multimodal Large Language Models (MLLMs) on MISID reveals critical deficiencies in complex scenarios, including text-prior visual hallucination, impaired cross-modal synergy, and limited capacity in chaining causal cues.
  arXiv  Detail & Related papers  (2026-04-14T13:07:54Z)
• SceneAlign: Aligning Multimodal Reasoning to Scene Graphs in Complex Visual Scenes [69.03114625064282]
  Multimodal large language models often struggle with faithful reasoning in complex visual scenes.<n>Existing preference-based approaches fail to address this challenge as they allow models to exploit language priors to bypass visual grounding.<n>We propose SceneAlign, a framework that leverages scene graphs as structured visual information to perform controllable structural interventions.
  arXiv  Detail & Related papers  (2026-01-09T07:40:39Z)
• Uncovering Grounding IDs: How External Cues Shape Multi-Modal Binding [8.918147502104603]
  We propose the concept of Grounding IDs, latent identifiers induced by external cues that bind objects to their designated partitions across modalities.<n>We show that Grounding IDs strengthen attention between related components, which in turn improves cross-modal grounding and reduces hallucinations.
  arXiv  Detail & Related papers  (2025-09-28T21:15:07Z)
• Explaining multimodal LLMs via intra-modal token interactions [55.27436637894534]
  Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse vision-language tasks, yet their internal decision-making mechanisms remain insufficiently understood.<n>We propose enhancing interpretability by leveraging intra-modal interaction.
  arXiv  Detail & Related papers  (2025-09-26T14:39:13Z)
• Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas [69.56484419619919]
  We study the spatial reasoning challenge from the lens of mechanistic interpretability.<n>We observe that successful spatial reasoning correlates strongly with the model's ability to align its attention with actual object locations.<n>Motivated by these findings, we propose ADAPTVIS to sharpen the attention on highly relevant regions when confident.
  arXiv  Detail & Related papers  (2025-03-03T17:57:03Z)
• INTRA: Interaction Relationship-aware Weakly Supervised Affordance Grounding [10.787807888885888]
  We propose INTeraction Relationship-aware weakly supervised Affordance grounding (INTRA) Unlike prior arts, INTRA recasts this problem as representation learning to identify unique features of interactions through contrastive learning with exocentric images only. Our method outperformed prior arts on diverse datasets such as AGD20K, IIT-AFF, CAD and UMD.
  arXiv  Detail & Related papers  (2024-09-10T04:31:51Z)

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.