works on

From the 1 of 11 linked papers with an AI index.

collaborators

11 papers

cs.CV2026

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…

cs.CV2026

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…

cs.CV2025

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…

cs.CV2025

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,…

cs.CV2025

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…

cs.CV2025

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…