AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

"SPHINX: A Mixer of Weights, Visual Embeddings and Image Scales for Multi-modal Large Language Models"

Ziyi Lin, Dongyang Liu, Renrui Zhang, Peng Gao, Longtian Qiu, Han Xiao, Han Qiu, Wenqi Shao, Keqin Chen, Jiaming Han, Siyuan Huang, Yichi Zhang and 3 more

ECCV 2024 · Vision-language and multimodal › Multimodal LLMs · approach: Instruction-tuned multimodal assistants · 36 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
add high-resolution sub-images (mixed scales, SPHINX-1k vs SPHINX) (ablation)SPHINX · POPEaccuracy: 80.7 -> 90.8Improved
add mixed scales with sub-images (ablation)SPHINX · TextVQAaccuracy: 51.6 -> 58.8Improved
add sub-images (mixed scales) for referring comprehension (ablation)SPHINX · RefCOCO+ valTop-1 accuracy@0.5: 82.77 -> 86.64Improved
keep low-resolution global view alongside sub-images (ablation)SPHINX-1k · RefCOCO valTop-1 accuracy@0.5: 71.72 -> 91.05Improved
mix all four visual encoders instead of Q-Former global features only (ablation)SPHINX · RefCOCO valTop-1 accuracy@0.5: 46.52 -> 89.14Improved
mix all visual encoders for VQA benchmarks (ablation)SPHINX · General and text-oriented VQAaccuracyMixed
jointly train with text-only RefinedWeb during pre-training (ablation)SPHINX · pre-training losstext generation lossImproved
mix scales at inference (SPHINX-1k vs SPHINX) cost (ablation)SPHINX · A100 inference, 200 tokenstime and memory: 5.2s -> 5.5s; 29GB -> 33GBHurt
go from SPHINX-1k to SPHINX-2k resolution (ablation)SPHINX · MMBenchaccuracy: 67.1 -> 65.9Mixed

Later papers that compared with this method

6 later accepted papers report SPHINX-Tiny as a baseline in their results tables; 6 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