Crystalis: Progressive Nucleation and Semantic Annealing for Coordinated Multi-View Visualization Generation

• URL: http://arxiv.org/abs/2607.24766v1
• Date: Sun, 07 Jun 2026 09:38:44 GMT
• Title: Crystalis: Progressive Nucleation and Semantic Annealing for Coordinated Multi-View Visualization Generation
• Abstract summary: Large language models (LLMs) can generate individual charts, but coordinated multi-view visualizations (CMVs) are out of reach.<n>We present Crystalis, a framework built on query-centric CMV modeling that decomposes a CMV into structured queries.<n>On a 12-task benchmark across five frontier LLMs, Crystalis achieves up to 75% end-to-end success.
• Score: 27.412375108328174
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) can generate individual charts, but coordinated multi-view visualizations (CMVs), where views share data flows and cross-view interactions, remain out of reach. Tight field-level coupling among data transformations, visual encodings, and interaction coordinations causes errors in one component to silently invalidate others. Rather than pursuing end-to-end analytical quality, which depends on model capability, domain knowledge, and user expertise, we target a foundational question: can LLMs reliably produce structurally correct CMVs, and what abstractions make this possible? We present Crystalis, a framework built on query-centric CMV modeling that decomposes a CMV into structured queries over a dependency graph spanning three component types (Data, Visualization, Interaction) and three abstraction levels (requirement, specification, executable object). Two complementary mechanisms operate over this structure: progressive nucleation crystallizes each query vertically from requirement to object along the dependency order, while semantic annealing enforces horizontal consistency across queries at each level through layered logical checks. On a 12-task benchmark across five frontier LLMs, Crystalis achieves up to 75% end-to-end success, substantially outperforming an agentic coding baseline (8.3% E2E with the same foundation model), and a user study with 12 practitioners confirms the usability of the decomposition and iterative refinement workflow.

Related papers

• MV-STRIDE: Enabling MLLMs to Master Multi-View Spatial Reasoning via Hierarchical Capability Modeling [22.069318507340423]
  We introduce MV-STRIDE, a hierarchical SpaTial Reasoning dataset with Interdependent and DE capabilitiEs.<n>Moving beyond flat data structures, MV-STRIDE explicitly models the dependency relationships between perception, scene understanding, and complex contextual reasoning.<n>We develop a systematic QA generation pipeline leveraging diverse 3D scene sources that enforces cross-view dependency constraints.
  arXiv  Detail & Related papers  (2026-09-07T09:14:13Z)
• UniCVR: From Alignment to Reranking for Unified Zero-Shot Composed Visual Retrieval [87.12447641908143]
  We propose UniCVR, the first unified zero-shot composed visual retrieval framework.<n>UniCVR jointly addresses all three tasks without any task-specific human-annotated data.<n>In Stage I, we train the MLLM as a compositional query embedder via contrastive learning on a curated dataset of approximately 3.5M samples.<n>In Stage II, we introduce an MLLM-guided dual-level reranking mechanism that applies adaptive budgeted subset scoring to a small number of top-ranked candidates.
  arXiv  Detail & Related papers  (2026-04-22T08:16:50Z)
• MM-CondChain: A Programmatically Verified Benchmark for Visually Grounded Deep Compositional Reasoning [37.02901476078596]
  We introduce MM-CondChain, a benchmark for visually grounded deep compositional reasoning.<n> MM-CondChain is organized as a multi-layer reasoning chain, where every layer contains a non-trivial compositional condition.<n>A Planner orchestrates layer-by-layer generation of compositional conditions, while a Verifiable Programmatic Intermediate Representation (VPIR) ensures each layer's condition is mechanically verifiable.
  arXiv  Detail & Related papers  (2026-03-12T17:59:56Z)
• DataFactory: Collaborative Multi-Agent Framework for Advanced Table Question Answering [18.66810094244931]
  Table Question Answering (TableQA) enables natural language interaction with structured data.<n>Existing large language model (LLM) approaches face critical limitations.<n>This paper introduces DataFactory, a multi-agent framework that addresses these limitations.
  arXiv  Detail & Related papers  (2026-03-10T03:44:52Z)
• Talk Freely, Execute Strictly: Schema-Gated Agentic AI for Flexible and Reproducible Scientific Workflows [0.0]
  Large language models (LLMs) can translate a researcher's plain-language goal into executable computation, yet scientific demand determinism, provenance, and governance.<n>We propose schema-gated orchestration as the resolving principle, so that nothing runs unless the complete action--including cross-step dependencies--validates against a machine-checkable specification.
  arXiv  Detail & Related papers  (2026-03-06T15:40:39Z)
• Exploring a Unified Vision-Centric Contrastive Alternatives on Multi-Modal Web Documents [99.62178668680578]
  We propose Vision-Centric Contrastive Learning (VC2L), a unified framework that models text, images, and their combinations using a single vision transformer.<n> VC2L operates entirely in pixel space by rendering all inputs, whether textual, visual, or combined, as images.<n>To capture complex cross-modal relationships in web documents, VC2L employs a snippet-level contrastive learning objective that aligns consecutive multimodal segments.
  arXiv  Detail & Related papers  (2025-10-21T14:59:29Z)
• CIR-CoT: Towards Interpretable Composed Image Retrieval via End-to-End Chain-of-Thought Reasoning [93.05917922306196]
  Composed Image Retrieval (CIR) aims to find a target image from a reference image and a modification text.<n>CIR-CoT is the first end-to-end retrieval-oriented MLLM designed to integrate explicit Chain-of-Thought (CoT) reasoning.
  arXiv  Detail & Related papers  (2025-10-09T09:41:45Z)
• Generalized Deep Multi-view Clustering via Causal Learning with Partially Aligned Cross-view Correspondence [72.41989962665285]
  Multi-view clustering (MVC) aims to explore the common clustering structure across multiple views.<n>However, real-world scenarios often present a challenge as only partial data is consistently aligned across different views.<n>We design a causal multi-view clustering network, termed CauMVC, to tackle this problem.
  arXiv  Detail & Related papers  (2025-09-19T14:31:40Z)
• KG-QAGen: A Knowledge-Graph-Based Framework for Systematic Question Generation and Long-Context LLM Evaluation [3.618621510356872]
  KG-QAGen is a framework that extracts QA pairs at multiple complexity levels.<n>We construct a dataset of 20,139 QA pairs and open-source a part of it.<n>We evaluate 13 proprietary and open-source LLMs and observe that even the best-performing models are struggling with set-based comparisons.
  arXiv  Detail & Related papers  (2025-05-18T16:46:39Z)
• CAISSON: Concept-Augmented Inference Suite of Self-Organizing Neural Networks [0.0]
  We present CAISSON, a novel hierarchical approach to Retrieval-Augmented Generation (RAG)<n>At its core, CAISSON leverages dual Self-Organizing Maps (SOMs) to create complementary organizational views of the document space.<n>To evaluate CAISSON, we develop SynFAQA, a framework for generating synthetic financial analyst notes and question-answer pairs.
  arXiv  Detail & Related papers  (2024-12-03T21:00:10Z)
• Contextualization Distillation from Large Language Model for Knowledge Graph Completion [51.126166442122546]
  We introduce the Contextualization Distillation strategy, a plug-in-and-play approach compatible with both discriminative and generative KGC frameworks. Our method begins by instructing large language models to transform compact, structural triplets into context-rich segments. Comprehensive evaluations across diverse datasets and KGC techniques highlight the efficacy and adaptability of our approach.
  arXiv  Detail & Related papers  (2024-01-28T08:56:49Z)
• Scalable Incomplete Multi-View Clustering with Structure Alignment [71.62781659121092]
  In this paper, we propose a novel incomplete anchor graph learning framework. We construct the view-specific anchor graph to capture the complementary information from different views. The time and space complexity of the proposed SIMVC-SA is proven to be linearly correlated with the number of samples.
  arXiv  Detail & Related papers  (2023-08-31T08:30:26Z)

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.