Topic
embedding
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.
Token Factory: Efficiently Integrating Diverse Signals into Large Recommendation Models
Token Factory is a framework that converts diverse traditional signals into soft tokens for large recommendation models (LRMs), addressing challenges of long prompts, memory footprint, and computational overhead. The approach has been validated in a production-scale environment, promising enhanced performance and efficiency.
CLoVE: New Federated Learning Algorithm Clusters Loss Vectors for Personalization
Researchers propose CLoVE (Clustering of Loss Vector Embeddings), a novel clustered federated learning algorithm that groups clients based on loss patterns. It achieves high cluster recovery in few rounds and state-of-the-art accuracy across supervised and unsupervised tasks.
Akasha 2 Achieves 4x Faster Visual Synthesis with Hamiltonian-Inspired AI Architecture
Akasha 2 introduces Hamiltonian State Space Duality and Visual-Language Joint Embedding Predictive Architecture, achieving state-of-the-art video prediction with 4x faster synthesis than diffusion models and 3-18x speedup over transformers. The system enforces physical conservation laws for spatiotemporal coherence.
MMLongEmbed Benchmark Reveals Limitations in Long-Context Multimodal Embedding Models
MMLongEmbed is the first comprehensive benchmark for evaluating multimodal embedding models (MEMs) in long-context scenarios. It comprises four retrieval tasks covering text, document, and video modalities. The evaluation reveals that current MEMs rely heavily on superficial feature matching and struggle with deep semantic and structural dependencies, with performance degrading systematically based on context length and key information placement.