| DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effective for LMMs | Jun 6, 2024 | Language ModellingLarge Language Model | —Unverified | 0 | 0 |
| EE-MLLM: A Data-Efficient and Compute-Efficient Multimodal Large Language Model | Aug 21, 2024 | Computational EfficiencyLanguage Modeling | —Unverified | 0 | 0 |
| Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy | Nov 23, 2024 | Instruction FollowingMME | —Unverified | 0 | 0 |
| EvoMoE: Expert Evolution in Mixture of Experts for Multimodal Large Language Models | May 28, 2025 | Mixture-of-ExpertsMME | —Unverified | 0 | 0 |
| Exploring Sparse Spatial Relation in Graph Inference for Text-Based VQA | Oct 13, 2023 | Graph LearningObject | —Unverified | 0 | 0 |
| FlexAttention for Efficient High-Resolution Vision-Language Models | Jul 29, 2024 | TextVQA | —Unverified | 0 | 0 |
| Graph Relation Transformer: Incorporating pairwise object features into the Transformer architecture | Nov 11, 2021 | Graph AttentionQuestion Answering | —Unverified | 0 | 0 |
| HyViLM: Enhancing Fine-Grained Recognition with a Hybrid Encoder for Vision-Language Models | Dec 11, 2024 | TextVQA | —Unverified | 0 | 0 |
| Locate Then Generate: Bridging Vision and Language with Bounding Box for Scene-Text VQA | Apr 4, 2023 | Answer GenerationLanguage Modelling | —Unverified | 0 | 0 |
| Making the V in Text-VQA Matter | Aug 1, 2023 | Optical Character Recognition (OCR)TextVQA | —Unverified | 0 | 0 |
