mlsanityData to 14 Oct 2026

Improving Multimodal Reasoning via Worst Dimension Optimization

arXiv 2606.07801 ↗First posted 5 Jun 2026cs.AIcited by 0

On the map: LLM reasoning → Multimodal reasoning

Abstract (arXiv)

Multimodal reasoning requires a path that retains integrity over a wide range of constraints, from visual grounding to logic consistency. However, the current Process Reward Models focus on heuristically defined rewards that equally weigh these factors, which may lead to the concealment of individual dimension failures by the dominating factors, without guaranteeing the validity of the reasoning process in general.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 20 of its 51 references that are in the map. First posted on arXiv 5 Jun 2026.

Builds on

20 of 51 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Training Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons Learned27 Sep
  2. 2025VisualPRM: An Effective Process Reward Model for Multimodal Reasoning13 Mar
  3. 2025Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models9 Mar
  4. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling6 Dec
  5. 2024Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization15 Nov

Other references · 15

  1. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  2. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  3. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  4. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,079
  5. 2024Improve Mathematical Reasoning in Language Models by Automated Process Supervisioncited by 441
  6. 2025rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinkingcited by 313
  7. 2025R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimizationcited by 301
  8. 2024InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Outputcited by 195
  9. 2024Ovis: Structural Embedding Alignment for Multimodal Large Language Modelcited by 169
  10. 2024Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTScited by 54
  11. 20243DSceneEditor: Controllable 3D Scene Editing with Gaussian Splattingcited by 22
  12. 2026RAM: Recover Any 3D Human Motion in-the-Wildcited by 12
3 more
  1. 2024Graph Canvas for Controllable 3D Scene Generationcited by 11
  2. 2025Learning an Efficient Optimizer via Hybrid-Policy Sub-Trajectory Balancecited by 5
  3. 2026PSGS: Text-driven Panorama Sliding Scene Generation via Gaussian Splattingcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Disentangling Perception and Reasoning in Multimodal LLMs via Reward Design
  2. 2025What MLLMs Learn about When they Learn about Multimodal Reasoning
  3. 2025GM-PRM: A Generative Multimodal Process Reward Model for Multimodal Mathematical Reasoning
  4. 2025Unlocking Multimodal Mathematical Reasoning via Process Reward Model
  5. 2025Self-Rewarded Multimodal Coherent Reasoning Across Diverse Visual Domains
  6. 2025Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)
  7. 2026Beyond Final Answers: CRYSTAL Benchmark for Transparent Multimodal Reasoning Evaluation
  8. 2026Reinforcing Multimodal Reasoning via Token-Level Perception-Grounded Advantage Estimation