AI Paper Atlas

Research map / Large language models / Instruction and fine-tuning

LANA: A Language-Capable Navigator for Instruction Following and Generation

Xiaohan Wang, Wenguan Wang, Jiayi Shao, Yi Yang

CVPR 2023 · Large language models › Instruction and fine-tuning · approach: Fine-tuning for reasoning data · 35 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Jointly pretrain and fine-tune on instruction following and generation rather than using single-task agents (ablation)LANA · R2R val unseenSR: 65.7 -> 67.9Improved
Jointly pretrain and fine-tune on instruction following and generation rather than using single-task agents (ablation)LANA · R2R val unseenSPICE: 0.223 -> 0.226Improved
Add pretraining to joint-task fine-tuning (ablation)LANA · R2R val unseenSR: 53.1 -> 67.9Improved
Add pretraining to joint-task fine-tuning (ablation)LANA · R2R val unseenSPICE: 0.182 -> 0.226Improved
Add instruction generation to instruction-following training (ablation)LANA · R2R val unseenSR: 61.3 -> 65.7Improved
Add instruction following to instruction-generation training (ablation)LANA · R2R val unseenSPICE: 0.215 -> 0.223Improved
Add both temporal self-attention and visual cross-attention to the route encoder (ablation)LANA · R2R val unseenSR: 65.6 -> 67.9; 64.8 -> 67.9Improved
Add both temporal self-attention and visual cross-attention to the route encoder (ablation)LANA · R2R val unseenSPICE: 0.202 -> 0.226; 0.222 -> 0.226Improved
Use LANA mt instead of LANA st (ablation)LANA · R2R val unseenSPICE: 0.223 -> 0.226Improved
Use LANA mt instead of LANA st (ablation)LANA · R4R val unseenSPICE: 0.259 -> 0.262Improved
Train on DUET-augmented data instead of the original training dataLANA · REVERIE val unseenSR: 34.00 -> 48.31Improved
Train on DUET-augmented data instead of the original training dataLANA · REVERIE test unseenSR: 33.50 -> 51.72Mixed

Later papers that compared with this method

1 later accepted paper reports Lana as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy