✨Thinking with Images via Self-Calling Agent

📝 Summary:
sCoT is a novel visual reasoning paradigm that reformulates interleaved multimodal CoT as a language-only CoT with self-calling subagents. It improves reasoning performance and efficiency by avoiding explicit multimodal interleaving and using group-relative policy optimization.

🔹 Publication Date: Published on Dec 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.08511
• PDF: https://arxiv.org/pdf/2512.08511
• Github: https://github.com/YWenxi/think-with-images-through-self-calling

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#VisualReasoning #MultimodalAI #LLMs #AIagents #AIResearch

✨Puzzle Curriculum GRPO for Vision-Centric Reasoning

📝 Summary:
Puzzle Curriculum GRPO PC-GRPO improves VLM visual reasoning without annotations. It uses self-supervised puzzle environments for verifiable rewards and a difficulty-aware curriculum to enhance consistency and accuracy.

🔹 Publication Date: Published on Dec 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.14944
• PDF: https://arxiv.org/pdf/2512.14944
• Project Page: https://pcgrpo.github.io/

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#VLM #VisualReasoning #SelfSupervisedLearning #ComputerVision #AI

✨Latent Implicit Visual Reasoning

📝 Summary:
Large Multimodal Models struggle with visual reasoning due to their text-centric nature and limitations of prior methods. This paper introduces a task-agnostic mechanism for LMMs to discover and use visual reasoning tokens without explicit supervision. The approach achieves state-of-the-art resul...

🔹 Publication Date: Published on Dec 24

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.21218
• PDF: https://arxiv.org/pdf/2512.21218

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#LMMs #VisualReasoning #AI #ComputerVision #DeepLearning

✨Forest Before Trees: Latent Superposition for Efficient Visual Reasoning

📝 Summary:
Laser introduces Dynamic Windowed Alignment Learning DWAL for visual reasoning. This method maintains global feature superposition, achieving state-of-the-art performance with significantly reduced computational costs and high efficiency.

🔹 Publication Date: Published on Jan 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.06803
• PDF: https://arxiv.org/pdf/2601.06803

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#VisualReasoning #MachineLearning #AIResearch #ComputerVision #EfficientAI

✨Thinking with Comics: Enhancing Multimodal Reasoning through Structured Visual Storytelling

📝 Summary:
Thinking with Comics emerges as an effective visual reasoning approach that bridges images and videos by leveraging comic structures for improved multimodal reasoning efficiency and performance. AI-ge...

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.02453
• PDF: https://arxiv.org/pdf/2602.02453
• Project Page: https://thinking-with-comics.github.io/
• Github: https://github.com/andongBlue/Think-with-Comics

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#AI #MultimodalAI #VisualReasoning #Comics #ComputerVision

✨Thinking with Drafting: Optical Decompression via Logical Reconstruction

📝 Summary:
Current AI struggles with precise visual reasoning. We propose Thinking with Drafting TwD, a DSL-based approach to decompress visual tokens into logical structures. This generates verifiable visual proofs, making visual generation a logical verifier for robust reasoning.

🔹 Publication Date: Published on Feb 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.11731
• PDF: https://arxiv.org/pdf/2602.11731

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#AI #VisualReasoning #ComputerVision #Logic #RobustAI

✨MetaphorStar: Image Metaphor Understanding and Reasoning with End-to-End Visual Reinforcement Learning

📝 Summary:
MetaphorStar is an end-to-end visual reinforcement learning framework that solves AIs challenge in understanding image metaphors. It uses a new dataset, RL method, and benchmark. MetaphorStar achieves state-of-the-art performance, outperforming many MLLMs and improving general visual reasoning.

🔹 Publication Date: Published on Feb 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.10575
• PDF: https://arxiv.org/pdf/2602.10575
• Project Page: https://metaphorstar.github.io/
• Github: https://github.com/MING-ZCH/MetaphorStar

🔹 Models citing this paper:
• https://huggingface.co/MING-ZCH/MetaphorStar-32B
• https://huggingface.co/MING-ZCH/MetaphorStar-3B
• https://huggingface.co/MING-ZCH/MetaphorStar-7B

✨ Datasets citing this paper:
• https://huggingface.co/datasets/MING-ZCH/TFQ-Bench-Lite
• https://huggingface.co/datasets/MING-ZCH/TFQ-Bench-Full
• https://huggingface.co/datasets/MING-ZCH/TFQ-Data-Full

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#AI #ReinforcementLearning #ComputerVision #ImageMetaphor #VisualReasoning

✨Lightweight Visual Reasoning for Socially-Aware Robots

📝 Summary:
A lightweight language-to-vision feedback module enhances VLMs for robotics. It reinterprets visual scenes under text context via a gated MLP, improving navigation, scene description, and human intention recognition with minimal parameters.

🔹 Publication Date: Published on Mar 4

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.03942
• PDF: https://arxiv.org/pdf/2603.03942
• Github: https://github.com/alessioGalatolo/VLM-Reasoning-for-Robotics

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#Robotics #VLMs #VisualReasoning #AI #HumanRobotInteraction

✨Vero: An Open RL Recipe for General Visual Reasoning

📝 Summary:
Vero is an open vision-language model family that achieves state-of-the-art visual reasoning performance through scaled reinforcement learning data across diverse tasks, demonstrating that broad data ...

🔹 Publication Date: Published on Apr 6

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.04917
• PDF: https://arxiv.org/pdf/2604.04917
• Project Page: https://vero-reasoning.github.io/

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#VisualReasoning #ReinforcementLearning #VisionLanguageModels #AIResearch #DeepLearning

✨Learning Adaptive Reasoning Paths for Efficient Visual Reasoning

📝 Summary:
Existing visual reasoning models often overthink, using redundant steps. AVR is an adaptive framework that dynamically chooses efficient reasoning formats. It reduces token usage by 50-90 percent while maintaining accuracy.

🔹 Publication Date: Published on Apr 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.14568
• PDF: https://arxiv.org/pdf/2604.14568
• Github: https://github.com/RunRiotComeOn/AVR

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#VisualReasoning #AI #MachineLearning #Efficiency #DeepLearning