paper-with-me

Papers

Anchored Alignment: Preventing Positional Collapse in Multimodal Recommender Systems

2026-03-13 · Yonghun Jeong, David Yoon Suk Kang, Yeon-Chang Lee arxiv

Multimodal recommender systems (MMRS) leverage images, text, and interaction signals to enrich item representations. However, recent alignment based MMRSs that enforce a unified embedding space often blur modality specific structures and exacerbate ID dominance. Therefore, we propose AnchorRec, a multimodal recommendation framework that performs indirect, anchor based alignment in a lightweight projection domain. By decoupling alignment from representation learning, AnchorRec preserves each modality's native structure while maintaining cross modal consistency and avoiding positional collapse. Experiments on four Amazon datasets show that AnchorRec achieves competitive top N recommendation accuracy, while qualitative analyses demonstrate improved multimodal expressiveness and coherence. The codebase of AnchorRec is available at https://github.com/hun9008/AnchorRec.

📄 PDF Abstract BibTeX arXiv:2603.12726

Code (0)

등록된 구현이 없습니다.

Tasks

Multimodal RecommendationRepresentation Learning

Similar Papers 제목 키워드 기반

ANO: A Principled Approach to Robust Policy Optimization

2026-05-04 · Yiheng Zhang, Yiming Wang, Kaiyan Zhao, Zhenglin Wan 외 arxiv

Proximal Policy Optimization (PPO) dominates reinforcement learning and LLM alignment but relies on a "hard clipping" mechanism that discards valuable gradients. Conversely, unconstrained methods like SPO expose the opti…

Reinforcement Learning

CodeBind: Decoupled Representation Learning for Multimodal Alignment with Unified Compositional Codebook

2026-05-18 · Zeyu Chen, Jie Li, Kai Han arxiv

Multimodal representation alignment is pivotal for large language models and robotics. Traditional methods are often hindered by cross-modal information discrepancies and data scarcity, leading to suboptimal alignment sp…

Representation Learning

Human-JEPA: A Human-Centric Vision Model that Perceives and Anticipates

2026-08-21 · Hui Wei, Licai Sun, Guoying Zhao arxiv

Machines that understand humans should perceive the present and anticipate the future. Existing human-centric vision model are pretrained on human images, set the state of the art in static dense perception, so motion an…

Person Re-Identification

What CLIP Knows but Cannot Say: Recovering Negation from Frozen Intermediate Features

2026-07-25 · Chen-Yi Lu, Yueh-Shao Chen, Somali Chaterji arxiv

Contrastive vision-language models such as CLIP map semantically opposite phrases (e.g., "a dog" vs. "not a dog") to nearly identical embeddings, rendering them insensitive to negation. We attribute this failure to a phe…

Text-to-Image Generation

Cohort-Anchored Foundation Models for Electronic Health Records: From Risk Scores to Auditable Peer Cohorts

2026-06-20 · Kaiping Zheng arxiv

Foundation models have achieved remarkable performance across medical question answering, imaging, and electronic health record (EHR) tasks, yet reliable clinical deployment remains challenging due to limited interpretab…

Representation LearningQuestion Answering