#contrastive learning

topiccontrastive learning

32 papers · 1 filter

cs.CV2026

Contrastive-Augmented Flow Matching for Style-Content Disentanglement

Yusong Li, Pingchuan Ma, Ming Gui +2

The paper proposes Contrastive Augmented Flow Matching (CAtFM), a method that adds contrastive regularization to invertible flow matching to learn disentangled content and style re…

cs.CL2026

DIVE: Embedding Compression via Self-Limiting Gradient Updates

Dongfang Zhao

The paper introduces DIVE, a residual compression adapter that reduces the dimensionality of language‑model embeddings using a self‑limiting hinge loss, geometry distillation, and…

cs.CV2026

Together, Then Apart: Balancing Alignment and Distinctiveness for Multimodal Survival Analysis

Wenjing Liu, Qin Ren, Wen Zhang +2

The paper introduces TTA, a framework that first aligns shared patterns across histopathology images and genomic data and then preserves modality‑specific information to improve ca…

cs.LG2026

CatRetriever: Contrastive Representation Learning for Slab-to-Bulk Retrieval in Generative Catalyst Discovery

Jungho Oh, Woosung Kim, Dong Hyeon Mok +2

The paper introduces CatRetriever, a contrastive representation learning model that maps catalyst slab structures to their corresponding bulk crystals, enabling accurate retrieval…

cs.CV2026

The Devil Is in the Leakage: A Disentangled Dual-Purification Framework for High-Fidelity Hairstyle Transfer

Jijie Li, Jiankuo Zhao, Xiangyu Zhu +1

The paper introduces a Dual‑Purification Framework that reduces identity and geometric leakage in diffusion‑based hairstyle transfer, enabling high‑fidelity, identity‑preserving po…

cs.CV2026

SISA-Rec: A Semantically Integrated Sequential Recommender with Contrastive Alignment

Soohan Abbasi, Shahid Munir Shah, Rafia Shaikh +1

The paper introduces SISA-Rec, a transformer-based sequential recommender that combines item ID embeddings with BERT-derived text embeddings via gated fusion and contrastive alignm…