MIRL uses mutual information to guide trajectory selection and provide separate rewards for visual perception in RLVR for VLMs, achieving 70.22% average accuracy with 25% fewer full trajectories.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
VLMs primarily reason in textual space with limited reliance on visual evidence, shown by consistent performance drops when images are added to text in a controlled aligned benchmark.
CharTool equips MLLMs with cropping and code tools plus agentic RL on DuoChart data to raise chart-reasoning accuracy by up to 9.78 percent on benchmarks.
CADFT improves supervised fine-tuning of large language models by dynamically down-weighting training samples whose low model-likelihood indicates high gradient variance, yielding better stability and generalization.
citing papers explorer
-
MIRL: Mutual Information-Guided Reinforcement Learning for Vision-Language Models
MIRL uses mutual information to guide trajectory selection and provide separate rewards for visual perception in RLVR for VLMs, achieving 70.22% average accuracy with 25% fewer full trajectories.
-
Do Vision-Language Models Truly Perform Vision Reasoning? A Rigorous Study of the Modality Gap
VLMs primarily reason in textual space with limited reliance on visual evidence, shown by consistent performance drops when images are added to text in a controlled aligned benchmark.
-
CharTool: Tool-Integrated Visual Reasoning for Chart Understanding
CharTool equips MLLMs with cropping and code tools plus agentic RL on DuoChart data to raise chart-reasoning accuracy by up to 9.78 percent on benchmarks.
-
Compatibility-Aware Dynamic Fine-Tuning for Large Language Models
CADFT improves supervised fine-tuning of large language models by dynamically down-weighting training samples whose low model-likelihood indicates high gradient variance, yielding better stability and generalization.