Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers Paper • 2506.23918 • Published 5 days ago • 27 • 2
Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers Paper • 2506.23918 • Published 5 days ago • 27
OpenThinkIMG Collection OpenThinkIMG is an end-to-end open-source framework that empowers LVLMs to think with images. • 6 items • Updated 1 day ago • 3
Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers Paper • 2506.23918 • Published 5 days ago • 27 • 2
Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models Paper • 2506.05176 • Published 30 days ago • 62
Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning Paper • 2506.04207 • Published about 1 month ago • 46
Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning Paper • 2506.04207 • Published about 1 month ago • 46
MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning Paper • 2505.10557 • Published May 15 • 47
SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond Paper • 2505.19641 • Published May 26 • 66
The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models Paper • 2505.22617 • Published May 28 • 123
ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows Paper • 2505.19897 • Published May 26 • 102
AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting Paper • 2505.18822 • Published May 24 • 14
AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting Paper • 2505.18822 • Published May 24 • 14
OpenThinkIMG Collection OpenThinkIMG is an end-to-end open-source framework that empowers LVLMs to think with images. • 6 items • Updated 1 day ago • 3
OpenThinkIMG Collection OpenThinkIMG is an end-to-end open-source framework that empowers LVLMs to think with images. • 6 items • Updated 1 day ago • 3
Learn to Reason Efficiently with Adaptive Length-based Reward Shaping Paper • 2505.15612 • Published May 21 • 33