Cover Image

Training Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons Learned

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ong, Brandon, Pala, Tej Deep, Toh, Vernon, Tjhi, William Chandra, Poria, Soujanya
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique
by: Pala, Tej Deep, et al.
Published: (2024)

Lessons from Training Grounded LLMs with Verifiable Rewards
by: Sim, Shang Hong, et al.
Published: (2025)

Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning
by: Sun, Qi, et al.
Published: (2024)

Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision
by: Pala, Tej Deep, et al.
Published: (2025)

DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling
by: Deep, Pala Tej, et al.
Published: (2024)

Not All Votes Count! Programs as Verifiers Improve Self-Consistency of Language Models for Math Reasoning
by: Toh, Vernon Y. H., et al.
Published: (2024)

Are Language Models Puzzle Prodigies? Algorithmic Puzzles Unveil Serious Challenges in Multimodal Reasoning
by: Ghosal, Deepanway, et al.
Published: (2024)

The Jumping Reasoning Curve? Tracking the Evolution of Reasoning Performance in GPT-[n] and o-[n] Models on Multimodal Puzzles
by: Toh, Vernon Y. H., et al.
Published: (2025)

PuzzleVQA: Diagnosing Multimodal Reasoning Challenges of Language Models with Abstract Visual Patterns
by: Chia, Yew Ken, et al.
Published: (2024)

Ruby Teaming: Improving Quality Diversity Search with Memory for Automated Red Teaming
by: Han, Vernon Toh Yan, et al.
Published: (2024)

PromptDistill: Query-based Selective Token Retention in Intermediate Layers for Efficient Large Language Model Inference
by: Jin, Weisheng, et al.
Published: (2025)

LLMs Can't Handle Peer Pressure: Crumbling under Multi-Agent Social Interactions
by: Song, Maojia, et al.
Published: (2025)

Towards Robust Instruction Tuning on Multimodal Large Language Models
by: Han, Wei, et al.
Published: (2024)

Inference Time Alignment with Reward-Guided Tree Search
by: Hung, Chia-Yu, et al.
Published: (2024)

Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model
by: Kang, Jaeyong, et al.
Published: (2023)

Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations
by: Hazra, Rima, et al.
Published: (2024)

Exact Flow Linear Attention: Exact Solution from Continuous-Time Dynamics
by: Lei, Jingdi, et al.
Published: (2025)

Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic
by: Bhardwaj, Rishabh, et al.
Published: (2024)

Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost
by: Xuan, Richmond Sin Jing, et al.
Published: (2026)

NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards
by: Hung, Chia-Yu, et al.
Published: (2025)

Toward Robust Multimodal Learning using Multimodal Foundational Models
by: Zhao, Xianbing, et al.
Published: (2024)

Stacked from One: Multi-Scale Self-Injection for Context Window Extension
by: Han, Wei, et al.
Published: (2026)

RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time
by: Wang, Haozhe, et al.
Published: (2026)

Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models
by: Hazra, Rima, et al.
Published: (2024)

PREMISE: Matching-based Prediction for Accurate Review Recommendation
by: Han, Wei, et al.
Published: (2025)

Can-Do! A Dataset and Neuro-Symbolic Grounded Framework for Embodied Planning with Large Multimodal Models
by: Chia, Yew Ken, et al.
Published: (2024)

MM-InstructEval: Zero-Shot Evaluation of (Multimodal) Large Language Models on Multimodal Reasoning Tasks
by: Yang, Xiaocui, et al.
Published: (2024)

From Mathematical Reasoning to Code: Generalization of Process Reward Models in Test-Time Scaling
by: Chen, Zhengyu, et al.
Published: (2025)

The Lessons of Developing Process Reward Models in Mathematical Reasoning
by: Zhang, Zhenru, et al.
Published: (2025)

Limits and Gains of Test-Time Scaling in Vision-Language Reasoning
by: Ahmadpour, Mohammadjavad, et al.
Published: (2025)

GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning
by: Zhao, Jian, et al.
Published: (2025)

PROEMO: Prompt-Driven Text-to-Speech Synthesis Based on Emotion and Intensity Control
by: Zhang, Shaozuo, et al.
Published: (2025)

Two are better than one: Context window extension with multi-grained self-injection
by: Han, Wei, et al.
Published: (2024)

Reasoning Paths Optimization: Learning to Reason and Explore From Diverse Paths
by: Chia, Yew Ken, et al.
Published: (2024)

Harnessing Large Language Models for Scientific Novelty Detection
by: Liu, Yan, et al.
Published: (2025)

Logical Reasoning with Outcome Reward Models for Test-Time Scaling
by: Thatikonda, Ramya Keerthy, et al.
Published: (2025)

VerityMath: Advancing Mathematical Reasoning by Self-Verification Through Unit Consistency
by: Han, Vernon Toh Yan, et al.
Published: (2023)

RFG: Test-Time Scaling for Diffusion Large Language Model Reasoning with Reward-Free Guidance
by: Chen, Tianlang, et al.
Published: (2025)

Self-Adaptive Sampling for Efficient Video Question-Answering on Image--Text Models
by: Han, Wei, et al.
Published: (2023)

Understanding the Capabilities and Limitations of Large Language Models for Cultural Commonsense
by: Shen, Siqi, et al.
Published: (2024)