Image de couverture de livre

Empowering Small VLMs to Think with Dynamic Memorization and Exploration

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liu, Jiazhen, Deng, Yuchuan, Chen, Long
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Segmentation as A Plug-and-Play Capability for Frozen Multimodal LLMs
par: Liu, Jiazhen, et autres
Publié: (2025)

Better, Stronger, Faster: Tackling the Trilemma in MLLM-based Segmentation with Simultaneous Textual Mask Prediction
par: Liu, Jiazhen, et autres
Publié: (2025)

Fundus-R1: Training a Fundus-Reading MLLM with Knowledge-Aware Reasoning on Public Data
par: Deng, Yuchuan, et autres
Publié: (2026)

How to Take a Memorable Picture? Empowering Users with Actionable Feedback
par: Laiti, Francesco, et autres
Publié: (2026)

CLGRPO: Reasoning Ability Enhancement for Small VLMs
par: Wang, Fanyi, et autres
Publié: (2025)

Listener-Rewarded Thinking in VLMs for Image Preferences
par: Gambashidze, Alexander, et autres
Publié: (2025)

DDX-TRACE: A Benchmark for Medical Diagnostic Trajectories in VLMs
par: Pan, Jiazhen, et autres
Publié: (2026)

Think Twice to See More: Iterative Visual Reasoning in Medical VLMs
par: Chen, Kaitao, et autres
Publié: (2025)

Towards Memorization-Free Diffusion Models
par: Chen, Chen, et autres
Publié: (2024)

Investigating Memorization in Video Diffusion Models
par: Chen, Chen, et autres
Publié: (2024)

Exploration of VLMs for Driver Monitoring Systems Applications
par: Cañas, Paola Natalia, et autres
Publié: (2025)

PuzzleCraft: Exploration-Aware Curriculum Learning for Puzzle-Based RLVR in VLMs
par: Jeddi, Ahmadreza, et autres
Publié: (2025)

Detecting, Explaining, and Mitigating Memorization in Diffusion Models
par: Wen, Yuxin, et autres
Publié: (2024)

VLMs have Tunnel Vision: Evaluating Nonlocal Visual Reasoning in Leading VLMs
par: Berman, Shmuel, et autres
Publié: (2025)

Integration of Object Detection and Small VLMs for Construction Safety Hazard Identification
par: Adil, Muhammad, et autres
Publié: (2026)

Thinking with Gaze: Sequential Eye-Tracking as Visual Reasoning Supervision for Medical VLMs
par: Li, Yiwei, et autres
Publié: (2026)

MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning
par: Pan, Jiazhen, et autres
Publié: (2025)

DAPL: Integration of Positive and Negative Descriptions in Text-Based Person Search
par: Deng, Yuchuan, et autres
Publié: (2024)

From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Models
par: Zhu, Wenxin, et autres
Publié: (2025)

Enhancing Privacy-Utility Trade-offs to Mitigate Memorization in Diffusion Models
par: Chen, Chen, et autres
Publié: (2025)

Exploring Local Memorization in Diffusion Models via Bright Ending Attention
par: Chen, Chen, et autres
Publié: (2024)

SemVink: Advancing VLMs' Semantic Understanding of Optical Illusions via Visual Global Thinking
par: Li, Sifan, et autres
Publié: (2025)

Unconsciously Forget: Mitigating Memorization; Without Knowing What is being Memorized
par: Jin, Er, et autres
Publié: (2025)

Modeling Visual Memorability Assessment with Autoencoders Reveals Characteristics of Memorable Images
par: Bagheri, Elham, et autres
Publié: (2024)

Learn to Memorize and to Forget: A Continual Learning Perspective of Dynamic SLAM
par: Li, Baicheng, et autres
Publié: (2024)

Memorizing SAM: 3D Medical Segment Anything Model with Memorizing Transformer
par: Shao, Xinyuan, et autres
Publié: (2024)

World2VLM: Distilling World Model Imagination into VLMs for Dynamic Spatial Reasoning
par: Zhang, Wanyue, et autres
Publié: (2026)

A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs
par: Zhao, Wangbo, et autres
Publié: (2024)

Adaptive Chain-of-Focus Reasoning via Dynamic Visual Search and Zooming for Efficient VLMs
par: Zhang, Xintong, et autres
Publié: (2025)

Start Small, Think Big: Curriculum-based Relative Policy Optimization for Visual Grounding
par: Yan, Qingyang, et autres
Publié: (2025)

Empowering Dynamic Urban Navigation with Stereo and Mid-Level Vision
par: Zhou, Wentao, et autres
Publié: (2025)

How Diffusion Models Memorize
par: Kim, Juyeop, et autres
Publié: (2025)

Global-Local Tree Search in VLMs for 3D Indoor Scene Generation
par: Deng, Wei, et autres
Publié: (2025)

Efficient Large-Deformation Medical Image Registration via Recurrent Dynamic Correlation
par: Li, Tianran, et autres
Publié: (2025)

AdaThinkDrive: Adaptive Thinking via Reinforcement Learning for Autonomous Driving
par: Luo, Yuechen, et autres
Publié: (2025)

XSPA: Crafting Imperceptible X-Shaped Sparse Adversarial Perturbations for Transferable Attacks on VLMs
par: Hu, Chengyin, et autres
Publié: (2026)

Are VLMs Ready for Lane Topology Awareness in Autonomous Driving?
par: Chen, Xin, et autres
Publié: (2025)

Filtering Memorization from Parameter-Space in Diffusion Models
par: Zhe, Yu, et autres
Publié: (2026)

Deep Pre-Alignment for VLMs
par: Yu, Tianyu, et autres
Publié: (2026)

Redistribute Ensemble Training for Mitigating Memorization in Diffusion Models
par: Guan, Xiaoliu, et autres
Publié: (2025)