From the 1 of 11 linked papers with an AI index.
11 papers
Scene Graph Thinking: Reinforcing Structured Visual Reasoning for Multimodal Large Language Models
Zhiwei Yang, Yuanchen Wu, Nan Zhang +3
The paper proposes Scene Graph Thinking (SaGe), a method that equips multimodal large language models with explicit scene‑graph representations to enable fine‑grained, structured v…
Predictive Regularization Against Visual Representation Degradation in Multimodal Large Language Models
Enguang Wang, Qiang Wang, Yuanchen Wu +5
While Multimodal Large Language Models (MLLMs) excel at vision-language tasks, the cost of their language-driven training on internal visual foundational competence remains unclear…
D2Pruner: Debiased Importance and Structural Diversity for MLLM Token Pruning
Evelyn Zhang, Fufu Yu, Aoqi Wu +5
Processing long visual token sequences poses a significant computational burden on Multimodal Large Language Models (MLLMs). While token pruning offers a path to acceleration, we f…
Towards Rationale-Answer Alignment of LVLMs via Self-Rationale Calibration
Yuanchen Wu, Ke Yan, Shouhong Ding +2
Large Vision-Language Models (LVLMs) have manifested strong visual question answering capability. However, they still struggle with aligning the rationale and the generated answer,…
VISA: Group-wise Visual Token Selection and Aggregation via Graph Summarization for Efficient MLLMs Inference
Pengfei Jiang, Hanjun Li, Linglan Zhao +4
In this study, we introduce a novel method called group-wise \textbf{VI}sual token \textbf{S}election and \textbf{A}ggregation (VISA) to address the issue of inefficient inference…
Fuse Before Transfer: Knowledge Fusion for Heterogeneous Distillation
Guopeng Li, Qiang Wang, Ke Yan +3
Most knowledge distillation (KD) methodologies predominantly focus on teacher-student pairs with similar architectures, such as both being convolutional neural networks (CNNs). How…