Wanli Ouyang, Yu Qiao, Si Liu, Zhen Wang, Jing Shao, Zeren Chen, Ziqin Wang, Huayang Liu, Zhenfei Yin, Lu Sheng, Trainable Frozen, Lora Lora #
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Recent studies have demonstrated Large Language Models (LLMs) can extend their zero-shot generalization capabilities to multimodal learning through instruction tuning. As more modalities and downstream tasks are introduced, negative conflicts and interference may have a worse impact on performance. While this phenomenon has been overlooked in previous work, we propose a novel and extensible framework, called Octavius, for comprehensive studies and experimentation on multimodal learning with Multimodal Large Language Models (MLLMs). Specifically, we combine the well-known Mixture-of-Experts (MoE) and one of the representative PEFT techniques, i.e., LoRA, designing a novel LLM-based decoder, called LoRA-MoE, for multimodal learning. To the best of our knowledge, we are one of the pioneering efforts to introduce MoE into MLLMs to address this problem. The experimental results (about 20% improvement) have shown the effectiveness and versatility of our design in various 2D and 3D downstream tasks. Code and datasets are available at https://openlamm.github.io/tutorial/.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2311.02684")
get_code_for_paper("2311.02684")
have("2311.02684")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2311.02684.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2311.02684)
Connect an agent — have() is free.