AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

X-Fusion: Introducing New Modality to Frozen Large Language Models

Sicheng Mo, Thao Nguyen, Xun Huang, Siddharth Srinivasan Iyer, Yijun Li, Yuchen Liu, Abhishek Tandon, Eli Shechtman, Krishna Kumar Singh, Yong Jae Lee, Bolei Zhou, Yuheng Li

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Unified any-modality language models · 10 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
use Dual Tower (frozen text tower plus trainable vision tower) instead of fine-tuning a single tower (ablation)X-Fusion · COCO text-to-imageFID: 19.10 -> 14.20Improved
keep language weights frozen with a separate vision tower (ablation)X-Fusion · MMLU 5-shotaccuracy: 25.0 -> 32.2Improved
use Dual Tower instead of Gated Tower (ablation)X-Fusion · COCO captioningBLIP-ITM: 14.5 -> 31.3Improved
use Dual Tower instead of Dual Projection (ablation)X-Fusion · COCO text-to-imageFID: 20.22 -> 14.20Improved
use clean images (no noise) in image-to-text samples (ablation)X-Fusion · COCO generation and understandingFID and BLIPImproved
increase image understanding (I2T) data share (ablation)X-Fusion · COCO text-to-imageFIDImproved
add text-to-image generation data to help understanding (ablation)X-Fusion · COCO captioningBLIP-ITMNo clear effect
add CLIP feature alignment loss (ablation)X-Fusion 1B and 3B · COCO generation and understandingFID and BLIPImproved
add CLIP feature alignment loss (ablation)X-Fusion 8B · COCO generation and understanding at 100k iterationsFID and BLIPHurt
add X-Fuse layer fusing features from both towers (ablation)X-Fusion · COCO generation and understandingFID and BLIPImproved
initialize vision tower from pretrained DiTX-Fusion 8B · image generationqualitativeImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.

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