Imagen de Portada

Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ma, Yan, Chern, Steffi, Shen, Xuyang, Zhong, Yiran, Liu, Pengfei
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Computation and Language Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

One RL to See Them All: Visual Triple Unified Reinforcement Learning
por: Ma, Yan, et al.
Publicado: (2025)

Thinking with Generated Images
por: Chern, Ethan, et al.
Publicado: (2025)

Can Large Language Models be Trusted for Evaluation? Scalable Meta-Evaluation of LLMs as Evaluators via Agent Debate
por: Chern, Steffi, et al.
Publicado: (2024)

ANOLE: An Open, Autoregressive, Native Large Multimodal Models for Interleaved Image-Text Generation
por: Chern, Ethan, et al.
Publicado: (2024)

Rethinking Multilingual Vision-Language Translation: Dataset, Evaluation, and Adaptation
por: Wang, Xintong, et al.
Publicado: (2025)

You Only Scan Once: Efficient Multi-dimension Sequential Modeling with LightNet
por: Qin, Zhen, et al.
Publicado: (2024)

Evaluating Fairness in Large Vision-Language Models Across Diverse Demographic Attributes and Prompts
por: Wu, Xuyang, et al.
Publicado: (2024)

Rethinking Visual Dependency in Long-Context Reasoning for Large Vision-Language Models
por: Zhou, Yucheng, et al.
Publicado: (2024)

VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models
por: Zhang, Ce, et al.
Publicado: (2025)

MarsRetrieval: Benchmarking Vision-Language Models for Planetary-Scale Geospatial Retrieval on Mars
por: Wang, Shuoyuan, et al.
Publicado: (2026)

Enhancing Large Vision Language Models with Self-Training on Image Comprehension
por: Deng, Yihe, et al.
Publicado: (2024)

LiveTalk: Real-Time Multimodal Interactive Video Diffusion via Improved On-Policy Distillation
por: Chern, Ethan, et al.
Publicado: (2025)

Judging the Judges: Can Large Vision-Language Models Fairly Evaluate Chart Comprehension and Reasoning?
por: Laskar, Md Tahmid Rahman, et al.
Publicado: (2025)

OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles
por: Deng, Yihe, et al.
Publicado: (2025)

Guiding Medical Vision-Language Models with Explicit Visual Prompts: Framework Design and Comprehensive Exploration of Prompt Variations
por: Zhu, Kangyu, et al.
Publicado: (2025)

EffiVLM-BENCH: A Comprehensive Benchmark for Evaluating Training-Free Acceleration in Large Vision-Language Models
por: Wang, Zekun, et al.
Publicado: (2025)

Evaluating Vision-Language Models as Evaluators in Path Planning
por: Aghzal, Mohamed, et al.
Publicado: (2024)

Halu-J: Critique-Based Hallucination Judge
por: Wang, Binjie, et al.
Publicado: (2024)

NPHardEval4V: Dynamic Evaluation of Large Vision-Language Models with Effects of Vision
por: Li, Xiang, et al.
Publicado: (2024)

AutoPresent: Designing Structured Visuals from Scratch
por: Ge, Jiaxin, et al.
Publicado: (2025)

Rethinking Comprehensive Benchmark for Chart Understanding: A Perspective from Scientific Literature
por: Shen, Lingdong, et al.
Publicado: (2024)

Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models
por: Ding, Yi, et al.
Publicado: (2025)

NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples
por: Li, Baiqi, et al.
Publicado: (2024)

AlignMMBench: Evaluating Chinese Multimodal Alignment in Large Vision-Language Models
por: Wu, Yuhang, et al.
Publicado: (2024)

A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language Models
por: Jing, Liqiang, et al.
Publicado: (2025)

Evaluating Vision-Language Models for Emotion Recognition
por: Bhattacharyya, Sree, et al.
Publicado: (2025)

Evaluation of Cultural Competence of Vision-Language Models
por: Yadav, Srishti, et al.
Publicado: (2025)

VEGA: Learning Interleaved Image-Text Comprehension in Vision-Language Large Models
por: Zhou, Chenyu, et al.
Publicado: (2024)

Scaling RL to Long Videos
por: Chen, Yukang, et al.
Publicado: (2025)

HPE-CogVLM: Advancing Vision Language Models with a Head Pose Grounding Task
por: Tian, Yu, et al.
Publicado: (2024)

SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis
por: Wu, Zijian, et al.
Publicado: (2025)

ScratchEval: Are GPT-4o Smarter than My Child? Evaluating Large Multimodal Models with Visual Programming Challenges
por: Fu, Rao, et al.
Publicado: (2024)

S-GRPO: Unified Post-Training for Large Vision-Language Models
por: Yan, Yuming, et al.
Publicado: (2026)

What Does Vision Tool-Use Reinforcement Learning Really Learn? Disentangling Tool-Induced and Intrinsic Effects for Crop-and-Zoom
por: Ma, Yan, et al.
Publicado: (2026)

Anatomical Structure-Guided Medical Vision-Language Pre-training
por: Li, Qingqiu, et al.
Publicado: (2024)

Can Vision-Language Models Evaluate Handwritten Math?
por: Nath, Oikantik, et al.
Publicado: (2025)

Instruction-Following Evaluation of Large Vision-Language Models
por: Shiono, Daiki, et al.
Publicado: (2025)

FlightGPT: Towards Generalizable and Interpretable UAV Vision-and-Language Navigation with Vision-Language Models
por: Cai, Hengxing, et al.
Publicado: (2025)

From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens
por: Sheta, Hala, et al.
Publicado: (2025)

Visual In-Context Learning for Large Vision-Language Models
por: Zhou, Yucheng, et al.
Publicado: (2024)