AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models

Jianting Tang, Yubo Wang, Haoyu Cao, Linli Xu

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Instruction-tuned multimodal assistants · 1 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 directional alignment loss L_das (ablation)BASIC-7B (Vicuna-7B) · MMBench-ENscore: 64.3 -> 68.6Improved
add semantic distribution loss L_sds (ablation)BASIC-7B (Vicuna-7B) · MMBench-ENscore: 64.3 -> 68.0Improved
add both L_das and L_sds (ablation)BASIC-7B (Vicuna-7B) · ScienceQA-IMGscore: 66.8 -> 70.6Improved
add both L_das and L_sds over either alone (ablation)BASIC-7B (Vicuna-7B) · MM-Vetscore: 33.1 -> 33.8Improved
add both lossesBASIC-7B (Vicuna-7B) · TextVQAscore: 58.2 -> 58.0Hurt
add both losses (ablation)BASIC-7B (Vicuna-7B) · TextVQAscore: 57.7 -> 58.0Hurt
increasing layer weights instead of decreasing (layers 1-16) (ablation)BASIC-7B (Vicuna-7B) · MM-Vetscore: 27.8 -> 28.7Improved
increasing layer weights instead of constant (ablation)BASIC-7B (Vicuna-7B) · GQAscore: 55.6 -> 55.9Improved
importance-based supervision instead of equal supervision (ablation)BASIC-7B (Vicuna-7B) · MM-Vetscore: 27.6 -> 28.7Improved
importance-based supervision instead of equal supervision (ablation)BASIC-7B (Vicuna-7B) · VQAv2score: 73.0 -> 73.4Improved
use refined embeddings from deep layers (16-32) in supervision (ablation)BASIC-7B (Vicuna-7B) · benchmark averagescoreHurt
apply BASIC to Gemma-2BGemma-2B · MMBench-CNscore: 49.5 -> 51.2Improved

Later papers that compared with this method

1 later accepted paper reports BASIC 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