Pith. sign in

REVIEW 15 cited by

MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale

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 2412.05237 v2 pith:C5JEH547 submitted 2024-12-06 cs.CL cs.CV

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

Open-source multimodal large language models (MLLMs) have shown significant potential in a broad range of multimodal tasks. However, their reasoning capabilities remain constrained by existing instruction-tuning datasets, which were predominately repurposed from academic datasets such as VQA, AI2D, and ChartQA. These datasets target simplistic tasks, and only provide phrase-level answers without any intermediate rationales. To address these challenges, we introduce a scalable and cost-effective method to construct a large-scale multimodal instruction-tuning dataset with rich intermediate rationales designed to elicit CoT reasoning. Using only open models, we create a dataset containing 12M instruction-response pairs to cover diverse, reasoning-intensive tasks with detailed and faithful rationales. Experiments demonstrate that training MLLMs on this dataset significantly improves reasoning capabilities, achieving state-of-the-art performance on benchmarks such as MathVerse (+8.1%), MMMU-Pro (+7%), and MuirBench (+13.3%). Additionally, the model demonstrates notable improvements of up to 4% on non-reasoning-based benchmarks. Ablation studies further highlight the importance of key components, such as rewriting and self-filtering, in the dataset construction process.

Discussion (0). Sign in to comment.

Forward citations

Cited by 15 Pith papers

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

  1. ScaleLong: A Multi-Timescale Benchmark for Long Video Understanding

    cs.CV 2025-05 conditional novelty 7.0 of 10

    ScaleLong embeds four timescale question types into the same long videos, and evaluation of 23 MLLMs reveals a U-shaped accuracy curve across timescales.

  2. Point-RFT: Improving Multimodal Reasoning with Visually Grounded Reinforcement Finetuning

    cs.CV 2025-05 reject novelty 7.0 of 10

    Point-RFT uses point-grounded chain-of-thought with GRPO reinforcement to improve chart reasoning, reporting 90.04% on ChartQA, though internal tables and the OOD setup weaken the claim.

  3. Sparse-LaViDa: Sparse Multimodal Discrete Diffusion Language Models

    cs.CV 2025-12 conditional novelty 6.0 of 10

    Sparse-LaViDa speeds up masked diffusion LLMs by truncating masked tokens, using register tokens and a step-causal attention mask, reaching ~2-2.8x speedup over LaViDa-O with comparable generation quality.

  4. Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation

    cs.CV 2025-09 conditional novelty 6.0 of 10

    Lavida-O introduces an elastic mixture-of-transformers architecture that brings high-resolution text-to-image generation, object grounding, and image editing into a single masked diffusion model, using planning and se...

  5. The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs

    cs.CL 2025-07 conditional novelty 6.0 of 10

    Long-CoT SFT and RL trade off strengths in reasoning VLMs, and five combination strategies fail to produce additive gains.

  6. BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset

    cs.CL 2025-07 conditional novelty 6.0 of 10

    BMMR provides a 110k-question bilingual, multimodal, college-level dataset across 300 subjects where state-of-the-art models score at most about 50%.

  7. DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real World

    cs.CV 2025-06 conditional novelty 6.0 of 10

    DenseWorld-1M provides one million images with detailed object captions, pixel masks, and spatial relations by chaining SAM, APE, RAM++, and VLMs through a three-stage labeling pipeline.

  8. MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A two-stage training recipe that converts causal VLMs into bidirectional multimodal embedding models, achieving SOTA on MMEB.

  9. VL-GenRM: Enhancing Vision-Language Verification via Vision Experts and Iterative Training

    cs.CL 2025-06 conditional novelty 6.0 of 10

    A vision-expert-filtered, chain-of-thought-guided, iteratively fine-tuned reward model boosts a compact 7B model's ability to judge vision-language responses, especially detecting hallucinations.

  10. Multi-Step Visual Reasoning with Visual Tokens Scaling and Verification

    cs.CV 2025-06 conditional novelty 6.0 of 10

    An iterative, verifier-guided visual token scaling framework improves multi-step visual reasoning in both closed and open multimodal models on BLINK and related benchmarks.

  11. VReST: Enhancing Reasoning in Large Vision-Language Models through Tree Search and Self-Reward Mechanism

    cs.CV 2025-06 conditional novelty 5.0 of 10

    VReST combines Monte Carlo tree search with a self-reward signal inside a vision-language model to get higher accuracy than CoT, ToT, or voting baselines on MathVista, MathVision, and CharXiv, while spending several t...

  12. Multimodal Tabular Reasoning with Privileged Structured Information

    cs.LG 2025-06 conditional novelty 5.0 of 10

    An 8B multimodal LLM trained on 9k reasoning traces distilled from structured tables reaches state-of-the-art open-source accuracy on table-image question answering and fact verification.

  13. Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start

    cs.CL 2025-05 conditional novelty 5.0 of 10

    Using a two-stage SFT-plus-GRPO pipeline, the authors train 3B and 7B multimodal models that beat prior open-source models on four math reasoning benchmarks, while showing that reflective 'aha moment' text is not a re...

  14. A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models

    cs.CL 2025-09 conditional novelty 4.0 of 10

    A structured literature survey concluding that reasoning capabilities do not automatically make LLMs more trustworthy and can introduce new vulnerabilities in safety, robustness, and privacy.

  15. A Survey on Diffusion Language Models

    cs.CL 2025-08 unverdicted novelty 3.0 of 10

    A comprehensive survey of diffusion language models covering taxonomy, training and inference techniques, and comparisons with autoregressive models.

Pith tools