Pith. sign in

REVIEW 13 cited by

Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models

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 2406.17294 v3 pith:4ZE6XDJZ submitted 2024-06-25 cs.CL

Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models

classification cs.CL
keywords mathematicalmultimodalreasoningmath-llavacapabilitiesdatasetspairsdataset
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Large language models (LLMs) have demonstrated impressive reasoning capabilities, particularly in textual mathematical problem-solving. However, existing open-source image instruction fine-tuning datasets, containing limited question-answer pairs per image, do not fully exploit visual information to enhance the multimodal mathematical reasoning capabilities of Multimodal LLMs (MLLMs). To bridge this gap, we address the lack of high-quality, diverse multimodal mathematical datasets by collecting 40K high-quality images with question-answer pairs from 24 existing datasets and synthesizing 320K new pairs, creating the MathV360K dataset, which enhances both the breadth and depth of multimodal mathematical questions. We introduce Math-LLaVA, a LLaVA-1.5-based model fine-tuned with MathV360K. This novel approach significantly improves the multimodal mathematical reasoning capabilities of LLaVA-1.5, achieving a 19-point increase and comparable performance to GPT-4V on MathVista's minitest split, and yielding leading performance on Math-V and MathVerse. Furthermore, Math-LLaVA demonstrates enhanced generalizability, showing substantial improvements on the MMMU benchmark. Our research highlights the importance of dataset diversity and synthesis in advancing MLLMs' mathematical reasoning abilities. The code and data are available at: \url{https://github.com/HZQ950419/Math-LLaVA}.

discussion (0)

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

Forward citations

Cited by 13 Pith papers

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

  1. ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection

    cs.CL 2024-10 unverdicted novelty 8.0

    ErrorRadar is a new benchmark of 2,500 multimodal K-12 math problems for MLLM error step identification and categorization, where GPT-4o trails human experts by ~10%.

  2. Weather-R1: Logically Consistent Reinforcement Fine-Tuning for Multimodal Reasoning in Meteorology

    cs.CV 2026-01 conditional novelty 7.0

    Weather-R1 is a multimodal reasoning model for meteorology that uses logical consistency rewards during reinforcement fine-tuning to cut self-contradictory outputs and raises benchmark accuracy by 9.8 points over baselines.

  3. BVS: Bayesian Visual Search with Multimodal Large Language Model for Fine-grained Perception

    cs.CV 2026-07 conditional novelty 6.0

    BVS combines early-stop attention rollout priors with a scale-aware non-stationary kernel and GP-UCB to locate tiny objects in UHR images more accurately and with fewer MLLM queries than prior visual-search methods.

  4. TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RL

    cs.AI 2026-06 unverdicted novelty 6.0

    TRON supplies 520 rule-verifiable online visual reasoning environments across five ability buckets that generate unlimited training instances for RL post-training, yielding consistent gains on ten external multimodal ...

  5. SIF: Semantically In-Distribution Fingerprints for Large Vision-Language Models

    cs.CV 2026-04 unverdicted novelty 6.0

    SIF creates semantically in-distribution fingerprints for LVLMs by distilling text watermarks into visual inputs and optimizing for robustness against detection and modification.

  6. InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

    cs.CV 2025-04 conditional novelty 6.0

    InternVL3-78B sets a new open-source SOTA of 72.2 on MMMU via native joint multimodal pre-training, V2PE, MPO, and test-time scaling while remaining competitive with proprietary models.

  7. OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles

    cs.CV 2025-03 conditional novelty 6.0

    Iterative SFT-RL cycles enable a 7B LVLM to develop sophisticated visual chain-of-thought reasoning and improve performance on math and general reasoning benchmarks.

  8. MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems

    cs.CV 2025-03 unverdicted novelty 6.0

    MathFlow decouples perception and inference stages in MLLMs for visual math, with a dedicated perception model delivering gains on the FlowVerse benchmark when paired with existing reasoners.

  9. MathVis-Fine: Aligning Visual Supervision with Necessity via Progressive Dependency-Guided Training for Multimodal Mathematical Reasoning

    cs.AI 2026-06 unverdicted novelty 5.0

    MathVis-Fine proposes a dataset with fine-grained visual annotations and dependency ratings plus a progressive two-stage training paradigm to align visual supervision with sample-specific necessity in multimodal mathe...

  10. From Shortcuts to Reasoning: Robust Post-Training of Theory of Mind with Reinforcement Learning

    cs.LG 2026-06 unverdicted novelty 5.0

    Thinking-RFT improves Theory of Mind accuracy by 6% over SFT on shortcut-free datasets, with 10% gains on higher-order reasoning and better generalization to new domains.

  11. DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

    cs.CV 2024-12 accept novelty 5.0

    DeepSeek-VL2 is a series of MoE vision-language models using dynamic tiling and latent attention that reach competitive or state-of-the-art results on VQA, OCR, document understanding and grounding with 1.0B to 4.5B a...

  12. The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes

    cs.CL 2026-06 unverdicted novelty 4.0

    A literature survey that introduces a taxonomy for LLM reasoning paradigms, analyzes methodological trends, and synthesizes failure modes from over 300 papers.

  13. Vision-EKIPL: External Knowledge-Infused Policy Learning for Visual Reasoning

    cs.CV 2025-06 unverdicted novelty 4.0

    Vision-EKIPL injects high-quality actions from external models into RL training to expand exploration and raise the reasoning ceiling of MLLMs, reporting up to 5% gains on the Reason-RFT-CoT benchmark.