| MG2-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generation | ✓ Link | 97.85 | | | | | | | | | MG2-RAG (Qwen3.5-27B) | 2026-09-08 |
| Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs | ✓ Link | 97.5 | | | | | | | | | Phi-4-Multimodal | 2025-02-24 |
| Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training | ✓ Link | 94.88 | 97.47 | 90.44 | 93.18 | 96.97 | 93.75 | 94.49 | 95.3 | 94.13 | MC-CoT F-Large | 2023-11-23 |
| Honeybee: Locality-enhanced Projector for Multimodal LLM | ✓ Link | 94.39 | 95.20 | 96.29 | 91.18 | 94.48 | 93.75 | 93.17 | 95.04 | 93.21 | Honeybee | 2023-12-11 |
| | 92.53 | | | | | | | | | LLaVA (+ GPT-4) | |
| Multimodal Chain-of-Thought Reasoning in Language Models | ✓ Link | 91.68 | 95.91 | 82.00 | 90.82 | 95.26 | 88.80 | 92.89 | 92.44 | 90.31 | Multimodal CoT | 2023-02-02 |
| Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone | ✓ Link | 91.3 | | | | | | | | | Phi-3.5-Vision | 2024-04-22 |
| UVU: Improving Multimodal Understanding via Vision-Language Unified Autoregressive Paradigm | | 91.3 | | | | | | | | | UVU 3B | 2026-06-03 |
| Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding | ✓ Link | 90.99 | 90.41 | 95.05 | 88.91 | 89.64 | 88.05 | 90.94 | 91.19 | 90.64 | Chat-UniVi-13B | 2023-11-14 |
| Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action | ✓ Link | 88.8 | | | | | | | | | Unified-IO 2 XL | 2023-12-28 |
| LLaMA-Excitor: General Instruction Tuning via Indirect Feature Interaction | | 88.39 | | | | | | | | | LLaMA-Excitor@336px + LoRA | 2024-04-01 |
| Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering | ✓ Link | 75.17 | 75.44 | 70.87 | 78.09 | 74.68 | 67.43 | 79.93 | 78.23 | 69.68 | GPT-3 - CoT (QCM→ALE , 2-shot) | 2022-09-20 |
| Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering | ✓ Link | 74.61 | 76.60 | 65.92 | 77.55 | 75.51 | 66.09 | 79.58 | 78.49 | 67.63 | GPT-3 - CoT(QCM→AE, 2-shot) | 2022-09-20 |
| Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering | ✓ Link | 74.11 | 71.00 | 76.04 | 78.91 | 66.42 | 66.53 | 81.81 | 77.06 | 68.82 | UnifiedQA-BASE - CoT (QCM→ALE) | 2022-09-20 |
| Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering | ✓ Link | 73.97 | 74.64 | 69.74 | 76.00 | 74.44 | 67.28 | 77.42 | 76.80 | 68.89 | GPT-3 (QCM→A, 2-shot) | 2022-09-20 |
| Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization | ✓ Link | 70.0 | | | | | | | | | Video-LaVIT | 2024-02-05 |