Research from Renmin University: Caution Advised in Data Augmentation for Contrastive Learning

The latest research from Renmin University warns that caution is needed in data augmentation for contrastive learning. Strongly aligned positive samples may harm the generalization ability of contrastive learning. While stronger data augmentation can enhance downstream task performance, alignment performance decreases. The study reveals the mechanisms by which data augmentation affects contrastive learning and proposes seeking better data augmentation strategies from an information-theoretic and spectral perspective.

Tencent Releases New Patent on Training Large Language Models to Enhance Generalization and Accuracy

Recently, Tencent Technology (Shenzhen) Co., Ltd. published a patent regarding a training method and related equipment for large language models on the Tianyancha app. The patent is titled 'Training Method, Device, Computer Equipment, and Storage Medium for Large Language Models' and aims to enhance the learning capacity and accuracy of large language models through innovative training methods. In the training process of large language models, traditional methods often rely on a single text summary, which may lead to model overfitting and negatively impact the accuracy and diversity of generated content. However, Tencent's new...

Microsoft Launches LLM2CLIP: New AI Technology Supports Image Understanding with Language Models

In today's technology landscape, CLIP (Contrastive Language-Image Pre-training) is an important multimodal foundational model. It combines visual signals and text signals into a shared feature space using contrastive learning loss on a large-scale dataset of image-text pairs. As a retriever, CLIP supports various tasks such as zero-shot classification, detection, segmentation, and image-text retrieval. Meanwhile, as a feature extractor, it performs well in nearly all...

Small yet Beautiful! HKU's Latest Recommendation System EasyRec Insights User Voices through Text

EasyRec is a recommendation system based on language models, developed by a team from the University of Hong Kong. Its uniqueness lies in analyzing emotional and detailed user behavior stories through a text behavior alignment framework to predict user preferences without requiring large amounts of user data. The system combines contrastive learning and collaborative language models, enabling accurate predictions of preferences for new users and new products, particularly excelling in zero-shot recommendation scenarios. EasyRec's plug-and-play features make it easy to integrate into existing recommendation systems, enhancing performance. The paper showcases EasyRec's performance across multiple...

Xiaomi Large Model MiMo Public Testing Extended, Users Can Enjoy Free Experience Until 2026!

Xiaomi announced that the free public testing period of its self-developed large model MiMo-V2-Flash has been extended by 20 days, until January 20, 2026. The model has 309 billion parameters, with 15 billion activated parameters, and performs excellently in reasoning and code generation. This move aims to provide users with a longer experience period and demonstrate Xiaomi's continuous investment and confidence in the AI field.

Research from Renmin University: Caution Advised in Data Augmentation for Contrastive Learning

Related Recommendations

Tencent Releases New Patent on Training Large Language Models to Enhance Generalization and Accuracy

Microsoft Launches LLM2CLIP: New AI Technology Supports Image Understanding with Language Models

Small yet Beautiful! HKU's Latest Recommendation System EasyRec Insights User Voices through Text

Israeli AI company AI21Labs clarifies there is no transaction agreement with NVIDIA

Xiaomi Large Model MiMo Public Testing Extended, Users Can Enjoy Free Experience Until 2026!