Pith. sign in

REVIEW 8 cited by

TinyChart: Efficient Chart Understanding with Visual Token Merging and Program-of-Thoughts Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.16635 v1 pith:ZJW2OYZW submitted 2024-04-25 cs.CV

TinyChart: Efficient Chart Understanding with Visual Token Merging and Program-of-Thoughts Learning

classification cs.CV
keywords chartunderstandingtinychartvisionefficientlearningmllmmodel
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Charts are important for presenting and explaining complex data relationships. Recently, multimodal large language models (MLLMs) have shown remarkable capabilities in various chart understanding tasks. However, the sheer size of these models in terms of parameters and computational requirements limits their use in resource-constrained environments. In this paper, we present TinyChart, an efficient MLLM for chart understanding with only 3B parameters. TinyChart overcomes two key challenges in efficient chart understanding: (1) reduce the burden of learning numerical computations through a Program-of-Thoughts (PoT) learning strategy, which trains the model to generate Python programs for numerical calculations, and (2) reduce lengthy vision feature sequences produced by the vision transformer for high-resolution images through a Vision Token Merging module, which gradually merges most similar vision tokens. Extensive experiments demonstrate that our 3B TinyChart achieves SOTA performance on a variety of chart understanding benchmarks including ChartQA, Chart-to-Text, Chart-to-Table, OpenCQA, and ChartX. It outperforms several chart understanding MLLM with up to 13B parameters such as ChartLlama and ChartAst, and close-sourced general-purpose MLLM GPT-4V on ChartQA. It also demonstrates its superior efficiency with higher throughput during inference due to a smaller model scale and more efficient vision encoding. Our code and model are available at https://github.com/X-PLUG/mPLUG-DocOwl/tree/main/TinyChart.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Infinity-Parser2 Technical Report

    cs.AI 2026-07 accept novelty 6.0

    A controllable DOM synthesis flywheel plus verifiable multi-task RL yields Infinity-Parser2, with Pro at 87.6% olmOCR-Bench and 74.3% ParseBench and Flash at 3.68× prior throughput.

  2. Making Multimodal LLMs Reliable Chart Data Extractors: A Benchmark and Training Framework

    cs.HC 2026-06 unverdicted novelty 6.0

    Introduces a benchmark for MLLM-based chart data extraction from unlabeled images and a human-centered training framework that reaches SOTA numerical accuracy with a 7B model.

  3. Chart-FR1: Visual Focus-Driven Fine-Grained Reasoning on Dense Charts

    cs.CV 2026-05 unverdicted novelty 6.0

    Chart-FR1 uses Focus-CoT for linking reasoning to visual cues and Focus-GRPO reinforcement learning with efficiency rewards to outperform prior MLLMs on dense chart reasoning tasks.

  4. Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing

    cs.CV 2026-03 conditional novelty 6.0

    PaddleOCR-VL uses a Valid Region Focus Module to select key visual tokens and a 0.9B model for guided recognition, delivering SOTA document parsing with far fewer tokens and parameters.

  5. ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch

    cs.CV 2026-01 conditional novelty 6.0

    ChartVerse uses Rollout Posterior Entropy and truth-anchored inverse QA synthesis to produce 640K high-quality chart reasoning samples, training an 8B model that surpasses its 30B teacher.

  6. CycleChart: A Unified Consistency-Based Learning Framework for Bidirectional Chart Understanding and Generation

    cs.CL 2025-12 unverdicted novelty 6.0

    CycleChart is a consistency-based framework that organizes chart generation, schema parsing, data parsing, and QA around single data instances to enforce bidirectional semantic alignment and improve cross-task generalization.

  7. Infinity-Parser2 Technical Report

    cs.AI 2026-07 unverdicted novelty 5.0

    Infinity-Parser2 pairs a 5M synthetic bilingual document corpus with multi-task RL to claim SOTA document parsing on olmOCR-Bench and ParseBench.

  8. PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training

    cs.CV 2026-06 unverdicted novelty 3.0

    PaddleOCR-VL-1.6 improves on PaddleOCR-VL-1.5 via region-aware data optimization and progressive post-training to reach 96.33% on OmniDocBench v1.6.