Cover Image

Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shen, Yifan, Liu, Yuanzhe, Zhu, Jingyuan, Cao, Xu, Zhang, Xiaofeng, He, Yixiao, Ye, Wenming, Rehg, James Matthew, Lourentzou, Ismini
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

CoRe3D: Collaborative Reasoning as a Foundation for 3D Intelligence
by: Yu, Tianjiao, et al.
Published: (2025)

Commonsense for Zero-Shot Natural Language Video Localization
by: Holla, Meghana, et al.
Published: (2023)

Toward Cognitive Supersensing in Multimodal Large Language Model
by: Li, Boyi, et al.
Published: (2026)

EgoForge: Goal-Directed Egocentric World Simulator
by: Shen, Yifan, et al.
Published: (2026)

ELBA: Learning by Asking for Embodied Visual Navigation and Task Completion
by: Shen, Ying, et al.
Published: (2023)

Phantom: Physics-Infused Video Generation via Joint Modeling of Visual and Latent Physical Dynamics
by: Shen, Ying, et al.
Published: (2026)

RAVEL: Rare Concept Generation and Editing via Graph-driven Relational Guidance
by: Venkatesh, Kavana, et al.
Published: (2024)

3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding
by: Ogunleye, Makanjuola, et al.
Published: (2026)

Iterative Reasoning Preference Optimization
by: Pang, Richard Yuanzhe, et al.
Published: (2024)

Counterfactual Segmentation Reasoning: Diagnosing and Mitigating Pixel-Grounding Hallucination
by: Li, Xinzhuo, et al.
Published: (2025)

DreamPartGen: Semantically Grounded Part-Level 3D Generation via Collaborative Latent Denoising
by: Yu, Tianjiao, et al.
Published: (2026)

VLM-FO1: Bridging the Gap Between High-Level Reasoning and Fine-Grained Perception in VLMs
by: Liu, Peng, et al.
Published: (2025)

ASPO: Adaptive Sentence-Level Preference Optimization for Fine-Grained Multimodal Reasoning
by: Wang, Yeyuan, et al.
Published: (2025)

Through the Lens of Contrast: Self-Improving Visual Reasoning in VLMs
by: Pan, Zhiyu, et al.
Published: (2026)

PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation
by: Liu, Yuanzhe, et al.
Published: (2026)

Reasmory: 3D Reconstruction as Explicit Memory for VLMs Spatial Reasoning
by: He, Jixuan, et al.
Published: (2026)

Fine-Grained Self-Endorsement Improves Factuality and Reasoning
by: Wang, Ante, et al.
Published: (2024)

Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas
by: Chen, Shiqi, et al.
Published: (2025)

Part$^{2}$GS: Part-aware Modeling of Articulated Objects using 3D Gaussian Splatting
by: Yu, Tianjiao, et al.
Published: (2025)

CALICO: Part-Focused Semantic Co-Segmentation with Large Vision-Language Models
by: Nguyen, Kiet A., et al.
Published: (2024)

iVISPAR -- An Interactive Visual-Spatial Reasoning Benchmark for VLMs
by: Mayer, Julius, et al.
Published: (2025)

Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model
by: Zhu, Wenhong, et al.
Published: (2024)

Decompose, Look, and Reason: Reinforced Latent Reasoning for VLMs
by: Zhu, Mengdan, et al.
Published: (2026)

AVERE: Improving Audiovisual Emotion Reasoning with Preference Optimization
by: Chaubey, Ashutosh, et al.
Published: (2026)

Spatial Hierarchy and Temporal Attention Guided Cross Masking for Self-supervised Skeleton-based Action Recognition
by: Yin, Xinpeng, et al.
Published: (2024)

HandVQA: Diagnosing and Improving Fine-Grained Spatial Reasoning about Hands in Vision-Language Models
by: Sayem, MD Khalequzzaman Chowdhury, et al.
Published: (2026)

Improving Complex Reasoning with Dynamic Prompt Corruption: A soft prompt Optimization Approach
by: Fan, Sinan, et al.
Published: (2025)

Can VLMs Detect and Localize Fine-Grained AI-Edited Images?
by: Sun, Zhen, et al.
Published: (2025)

YFPO: A Preliminary Study of Yoked Feature Preference Optimization with Neuron-Guided Rewards for Mathematical Reasoning
by: Le, Yifan
Published: (2026)

LaTtE-Flow: Layerwise Timestep-Expert Flow-based Transformer
by: Shen, Ying, et al.
Published: (2025)

MetaSpatial: Reinforcing 3D Spatial Reasoning in VLMs for the Metaverse
by: Pan, Zhenyu, et al.
Published: (2025)

PRIMA: Multi-Image Vision-Language Models for Reasoning Segmentation
by: Wahed, Muntasir, et al.
Published: (2024)

Coarse-Grained Dynamics with Spatial Disorder and Non-Markovian Memory
by: Liu, Chuyi, et al.
Published: (2026)

Fine-grained Video Dubbing Duration Alignment with Segment Supervised Preference Optimization
by: Cui, Chaoqun, et al.
Published: (2025)

KV-Compress: Paged KV-Cache Compression with Variable Compression Rates per Attention Head
by: Rehg, Isaac
Published: (2024)

Improving Fine-grained Visual Understanding in VLMs through Text-Only Training
by: Choi, Dasol, et al.
Published: (2024)

DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models
by: Wu, Ziyi, et al.
Published: (2025)

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models
by: Li, Zhikai, et al.
Published: (2026)

Divide, Optimize, Merge: Fine-Grained LLM Agent Optimization at Scale
by: Liu, Jiale, et al.
Published: (2025)

Best of Both Worlds: Multimodal Reasoning and Generation via Unified Discrete Flow Matching
by: Susladkar, Onkar, et al.
Published: (2026)