AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Image is All You Need: Towards Efficient and Effective Large Language Model-Based Recommender Systems

Kibum Kim, Sein Kim, HongSeok Kang, Jiwan Kim, Heewoong Noh, Yeonjun In, Kanghoon Yoon, Jinoh Oh, Julian McAuley, Chanyoung Park

ICLR 2026 · Large language models › Language, safety and interpretability · approach: LLM unlearning and benchmarks

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 RISA alignment module to image-only features (ablation)I-LLMRec · Amazon SportHit@5: 0.3953 -> 0.4316Improved
add RISA alignment module to image-only features (ablation)I-LLMRec · Amazon ArtHit@5: 0.5040 -> 0.5564Improved
add CF feature to image in RERI (ablation)I-LLMRec · Amazon SportHit@5: 0.4316 -> 0.4491Improved
add text feature to image and CF in RERI (ablation)I-LLMRec · Amazon SportHit@5: 0.4491 -> 0.4570Improved
add text feature to image and CF in RERI (ablation)I-LLMRec · Amazon ArtHit@5: 0.5795 -> 0.5883Improved
add item descriptions to image tokens (I-LLMRec+D)I-LLMRec · Amazon SportHit@5: 0.4570 -> 0.4554No clear effect
represent items by images instead of summarized descriptions (I-LLMRec vs TRSR)TRSR · Amazon SportHit@5: 0.4302 -> 0.4570Improved
use I-LLMRec image-based alignment instead of UniMP multimodal LLMUniMP · Amazon PhoneHit@5: 0.4427 -> 0.5156Improved
fine-tune LLM backbone with LoRA instead of freezingI-LLMRec · Amazon SportHit@5: 0.4570 -> 0.4633Improved
replace long descriptions with a single image token per itemTRSR · inference time on long historiesinference time: 47 minutes -> 20 minutes including feature extractionImproved
use I-LLMRec in a visually weak domain instead of description-based TRSRTRSR · GoodbooksHit@5: 0.5100 -> 0.4870Hurt
use I-LLMRec instead of TALLRec on visual-centric dataTALLRec · Amazon ClothingHit@5: 0.4388 -> 0.5469Improved

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