iGEN
Visit IGEN World Explore IGEN Expo
EXPLORE UPGRADE PLANS
BREAKING
Moody's Assigns First-Time Baa2 Rating to RBL Bank, One Notch Above India's Sovereign Sebi Bars Zee's Subhash Chandra, Punit Goenka From Market for One Year Zepto Defers IPO by Two to Three Quarters After Tepid Investor Response Tim Cook: India Among Apple's Best Global Markets as June Quarter Records Revenue Domestic funds reach record 21% stake in Indian companies as FPI ownership drops to 17% Cybercriminals widen net as assessees rush to meet I-T return filing deadline Bloomberg Delays India's Sovereign Bond Index Inclusion as Market Reforms Need Further Testing Gold loans jump 93.8% y-o-y, fuel bank credit growth in Q1FY27 Snapchat joins YouTube, LinkedIn and Substack in fight against 'AI slop' Amazon speeds last-mile delivery, expands robotics fleet past 1 million Moody's Assigns First-Time Baa2 Rating to RBL Bank, One Notch Above India's Sovereign Sebi Bars Zee's Subhash Chandra, Punit Goenka From Market for One Year Zepto Defers IPO by Two to Three Quarters After Tepid Investor Response Tim Cook: India Among Apple's Best Global Markets as June Quarter Records Revenue Domestic funds reach record 21% stake in Indian companies as FPI ownership drops to 17% Cybercriminals widen net as assessees rush to meet I-T return filing deadline Bloomberg Delays India's Sovereign Bond Index Inclusion as Market Reforms Need Further Testing Gold loans jump 93.8% y-o-y, fuel bank credit growth in Q1FY27 Snapchat joins YouTube, LinkedIn and Substack in fight against 'AI slop' Amazon speeds last-mile delivery, expands robotics fleet past 1 million
Home ›› Topics ›› representation learning

Topic

representation learning

13 stories
New Framework GeoVR Learns 3D Spatial Intelligence from 2D Videos for Multimodal LLMs Technology
Artificial Intelligence #artificial intelligence#multimodal

New Framework GeoVR Learns 3D Spatial Intelligence from 2D Videos for Multimodal LLMs

Multimodal Large Language Models (MLLMs) traditionally lack intrinsic 3D awareness. Researchers present GeoVR, a framework that learns geometric representations from 2D video sequences, restructuring the semantic latent space to unlock spatial intelligence. GeoVR uses four complementary geometric targets from pre-trained 3D foundation models, achieving state-of-the-art performance on spatial reasoning benchmarks.

Jul 8, 2026 1 source
REST-GAN: A Deep Generative Model for Resting-State EEG Synthesis and Transferable Representation Learning Technology
Artificial Intelligence #deep learning#generative model

REST-GAN: A Deep Generative Model for Resting-State EEG Synthesis and Transferable Representation Learning

Researchers introduce REST-GAN, a generative adversarial network for resting-state EEG that both synthesizes realistic neural signals and learns transferable representations. The model achieves high precision and recall in band-power features and shows competitive performance in demographic classification tasks, requiring substantially less training data and computational resources than existing methods.

Jun 21, 2026 1 source
Boundary Embedding Shaping with Adaptive Contrastive Learning Boosts GNN Classification by 3.3% Technology
Artificial Intelligence #artificial intelligence#graph neural networks

Boundary Embedding Shaping with Adaptive Contrastive Learning Boosts GNN Classification by 3.3%

Graph neural networks suffer from structural entanglement, especially near class boundaries. A new plug-in module called Boundary Embedding Shaping (BES) uses adaptive contrastive learning to selectively suppress spurious correlations, boosting GCN node classification by an average of 3.3% (up to 5% on WikiCS) and improving link prediction accuracy.

Jun 20, 2026 1 source
Concept Flow Models Anchor AI Reasoning with Hierarchical Bottlenecks to Reduce Information Leakage Technology
Artificial Intelligence #concept flow#concept-based reasoning

Concept Flow Models Anchor AI Reasoning with Hierarchical Bottlenecks to Reduce Information Leakage

Researchers Wang and Paschke propose Concept Flow Models (CFMs) that replace the flat bottleneck in Concept Bottleneck Models (CBMs) with a hierarchical, concept-driven decision tree. CFMs mitigate information leakage by reducing effective concept usage, matching predictive performance of flat CBMs while providing stepwise decision flows for transparent and auditable model reasoning.

Jun 20, 2026 1 source
FOUNDv2: Unified Quantized Tokenizers Transform User Representation Learning Technology
Artificial Intelligence #machine learning#user representation

FOUNDv2: Unified Quantized Tokenizers Transform User Representation Learning

FOUNDv2, a novel user representation framework, uses quantized tokenizers to transform heterogeneous data into discrete tokens, achieving superior performance and reduced storage costs. The model outperforms task-specific baselines and has been deployed at scale on Alipay, demonstrating practical efficiency.

Jun 17, 2026 1 source
Representation Autoencoders v2 Achieves 10x Faster Convergence and State-of-the-Art Image Generation Technology
Artificial Intelligence #machine learning#autoencoders

Representation Autoencoders v2 Achieves 10x Faster Convergence and State-of-the-Art Image Generation

A team of researchers has introduced RAEv2, an improved version of Representation Autoencoders (RAE), which achieves state-of-the-art image generation results with over 10x faster convergence. The work reveals that RAE and representation alignment (REPA) are complementary, and that REPA can provide guidance for classifier-free diffusion without a second weaker model.

Jun 17, 2026 1 source
Cascaded Sparse Autoencoders Enable Hierarchical Visual Concept Learning in Multimodal LLMs Technology
Artificial Intelligence #cascaded sparse autoencoders#multimodal llms

Cascaded Sparse Autoencoders Enable Hierarchical Visual Concept Learning in Multimodal LLMs

Researchers introduce cascaded sparse autoencoders (CSAEs) that learn hierarchical visual concepts in multimodal large language models. By training a second-level SAE on the decoder weights of the first, CSAEs achieve 'concepts of concepts' without nesting or stacking bottlenecks. Experiments on Qwen3-VL, Gemma-3, and LLaVA show improved interpretability and effective group-level steering.

Jun 16, 2026 1 source
Autonomous End-to-End SOH Prediction Service Uses Temporal-Contrastive Learning to Cut Error by Half Technology
Artificial Intelligence #battery#soh

Autonomous End-to-End SOH Prediction Service Uses Temporal-Contrastive Learning to Cut Error by Half

A new plug-and-play service architecture called TC-SOH uses temporal-contrastive representation learning to predict lithium-ion battery state of health directly from raw operational data, eliminating manual feature engineering. Across four public datasets, it reduces mean absolute percentage error by 1.91 times and root mean squared error by 2.13 times compared to physics-informed and data-driven baselines. The approach also improves model transparency through a suite of representation diagnostics, including visualization and sensitivity analysis.

Jun 16, 2026 1 source
Sensor-Conditioned Representation Learning Uses Scene-Relevant Observation Quotients to Improve Latent Geometry Technology
Artificial Intelligence #sensor-conditioned#representation learning

Sensor-Conditioned Representation Learning Uses Scene-Relevant Observation Quotients to Improve Latent Geometry

Researchers propose a sensor-conditioned representation learning framework using scene-relevant observation quotients. Their OQ-TSAE method, tested on synthetic and real-radar data, improves representation-correctness diagnostics over reconstruction, metric-learning, and contrastive baselines.

Jun 16, 2026 2 sources
RECTOR Framework Sets New State-of-the-Art in EEG Emotion Recognition and sEEG Classification Technology
Artificial Intelligence #rector#masked modeling

RECTOR Framework Sets New State-of-the-Art in EEG Emotion Recognition and sEEG Classification

Researchers propose RECTOR, a self-supervised framework for representation learning from EEG/sEEG data, achieving state-of-the-art performance in emotion recognition and task-engagement classification. The model demonstrates strong robustness to missing channels and cross-montage generalization, promising for large-scale pre-training on heterogeneous neural data.

Jun 16, 2026 1 source
EyeMVP AI Model Enhances Retinal Screening by Learning OCT Insights from Fundus Photos Technology
Artificial Intelligence #artificial intelligence#computer vision

EyeMVP AI Model Enhances Retinal Screening by Learning OCT Insights from Fundus Photos

Researchers developed EyeMVP, a cross-modal retinal foundation model that enriches color fundus photography (CFP) with depth-resolved information from optical coherence tomography (OCT). Pretrained on 674,893 paired images from 112,642 patients across eight Chinese hospitals, EyeMVP outperforms leading models on 16 downstream tasks including macular edema detection (AUROC 0.948 vs 0.852) and myopic macular schisis (0.825).

Jun 16, 2026 1 source
New Rational Sparse Autoencoder Improves AI Interpretability with Trainable Activation Function Technology
Artificial Intelligence #machine learning#autoencoder

New Rational Sparse Autoencoder Improves AI Interpretability with Trainable Activation Function

Researchers introduce the Rational Sparse Autoencoder (RSAE), which replaces fixed encoder nonlinearities with a trainable rational function. Across three language models and three baseline activation families, RSAE strictly improves reconstruction and downstream-behaviour metrics while preserving feature-level interpretability, adding only a few scalar parameters per autoencoder.

Jun 16, 2026 1 source
Subject-Specific Encoders Improve Cross-Subject EEG Decoding, Study Finds Technology
Artificial Intelligence #eeg#brain-computer interface

Subject-Specific Encoders Improve Cross-Subject EEG Decoding, Study Finds

A new study on arXiv.org proposes replacing shared EEG encoders with subject-specific encoders to handle inter-subject distribution shifts. The hybrid model, tested on four motor-imagery datasets, internalises Euclidean Alignment and increases class distinctiveness, though head selection for unseen subjects remains a bottleneck.

Jun 16, 2026 1 source