Hugging Face Trending Papers July 14, 2026

Contrastive-Collapsed Loss for Flexible and Geometrically Optimal Embeddings and Faster Convergence

Read the original on Hugging Face Trending Papers →

In this work, we introduce CoCo, a loss function aimed at learning normalized and well-structured representations. The proposed loss encourages intra-class collapse and inter-class contrast while preserving sufficient flexibility for neural networks to approximate geometrically optimal embeddings with large angular separation between classes.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

arXiv Machine Learning

Jul 15

Contrastive-Collapsed Loss for Flexible and Geometrically Optimal Embeddings and Faster Convergence

arXiv:2607. 12916v1 Announce Type: new Abstract: In this work, we introduce CoCo, a loss function aimed at learning normalized and well-structured representations.

By Blanca Cano-Camarero, \'Angela Fern\'andez-Pascual, Jos\'e R. Dorronsoro

rag benchmarks

arXiv Machine Learning

Jul 23

IConE: Batch Independent Collapse Prevention for Self-Supervised Representation Learning

arXiv:2603. 15263v2 Announce Type: replace-cross Abstract: Self-supervised learning (SSL) has revolutionized representation learning, with Joint-Embedding Architectures (JEAs) emerging as an effective approach for capturing semantic features.

By Konstantinos Almpanakis, Anna Kreshuk

rag

arXiv AI

Jun 6

Predict and Reconstruct: Joint Objectives for Self-Supervised Language Representation Learning

arXiv:2606. 05173v1 Announce Type: cross Abstract: Masked language modelling (MLM) has been the dominant pre-training objective for text encoders since BERT, yet it encourages representations that are strongly anchored to surface-form token identity rather than deeper semantic structure.

By Aimen Boukhari

rag diffusion benchmarks

arXiv Computer Vision

Sep 22

GeoBalance: Geometry-Aware Monitoring and Reconstruction with Asymmetric Optimization for Balanced Multimodal Learning

arXiv:2609.23533v1 Announce Type: new Abstract: Multimodal classifiers can converge to modality-dominant solutions in which one modality dominates the joint prediction, suppressing the learning of ot...

By Zechang Xiong, Da Li, Rong Yin, Kexin Tang, Biao Yang, Pengyuan Li, Wenkang Kong, Yulan Hu, Shengyu Zhu, Hao Peng

multimodal benchmarks

arXiv Machine Learning

Jul 28

XGRVFL-MV: Residual-Coupled Graph-Embedded Multi-View Random Vector Functional Link Network with FleXi Guardian Loss

arXiv:2607. 23149v1 Announce Type: new Abstract: Random Vector Functional Link (RVFL) networks provide an efficient randomized learning framework for classification.

By Yogesh Kumar, Mudasir Ganaie

rag benchmarks

Hugging Face Trending Papers

Jul 20

PRiSM: Prototype Regularization for Few-Shot VLMs

Training-free few-shot adaptation methods have gained significant attention recently in the context of Vision-language Models (VLMs). Yet, current benchmarks rely on strong assumptions about the statistics of the adaptation data, e.

llms multimodal benchmarks safety

One email a morning, machine-written

Related stories

Contrastive-Collapsed Loss for Flexible and Geometrically Optimal Embeddings and Faster Convergence

IConE: Batch Independent Collapse Prevention for Self-Supervised Representation Learning

Predict and Reconstruct: Joint Objectives for Self-Supervised Language Representation Learning

GeoBalance: Geometry-Aware Monitoring and Reconstruction with Asymmetric Optimization for Balanced Multimodal Learning

XGRVFL-MV: Residual-Coupled Graph-Embedded Multi-View Random Vector Functional Link Network with FleXi Guardian Loss

PRiSM: Prototype Regularization for Few-Shot VLMs