CoME-VL fuses contrastive and self-supervised vision encoders via entropy-guided multi-layer aggregation and RoPE cross-attention to improve vision-language model performance on benchmarks.
arXiv preprint arXiv:2602.06965 (2026)
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 4roles
background 2polarities
background 2representative citing papers
MicroWorld constructs a multimodal attributed property graph from scientific image-caption data and augments MLLM prompts via retrieval to raise Qwen3-VL-8B performance by 37.5% on MicroVQA and 6% on MicroBench.
CogAlign uses hierarchical supervised fine-tuning on clinical cognition data plus counterfactual RL to align MLLMs with expert diagnostic pathways and enforce causal lesion grounding for GI endoscopy diagnosis.
citing papers explorer
-
CoME-VL: Scaling Complementary Multi-Encoder Vision-Language Learning
CoME-VL fuses contrastive and self-supervised vision encoders via entropy-guided multi-layer aggregation and RoPE cross-attention to improve vision-language model performance on benchmarks.
-
MicroWorld: Empowering Multimodal Large Language Models to Bridge the Microscopic Domain Gap with Multimodal Attribute Graph
MicroWorld constructs a multimodal attributed property graph from scientific image-caption data and augments MLLM prompts via retrieval to raise Qwen3-VL-8B performance by 37.5% on MicroVQA and 6% on MicroBench.
-
Clinical Cognition Alignment for Gastrointestinal Diagnosis with Multimodal LLMs
CogAlign uses hierarchical supervised fine-tuning on clinical cognition data plus counterfactual RL to align MLLMs with expert diagnostic pathways and enforce causal lesion grounding for GI endoscopy diagnosis.
- RadAgent: A tool-using AI agent for stepwise interpretation of chest computed tomography