A new arXiv preprint (2608.23809v1) investigates whether multilingual LLMs use shared or language-specific features for mathematical reasoning, introducing the Geometry-Invariant Sparse Autoencoder (G…
A new dual-encoder transformer model, RetrievalFormer, can score new items from features alone, keeping a shared search-and-recommendation index open to cold items without retraining, according to an …
Researchers propose the Structure-Guided Spatiotemporal Attention Graph Neural Network (SGSAN) for traffic flow prediction, achieving state-of-the-art accuracy while providing built-in interpretabilit…
Researchers introduced CMCNet, a model that aligns ultrasound image embeddings with textual TI-RADS representations for fine-grained thyroid classification, achieving superior performance over InfoNCE…
Researchers propose GeoUniPR, a geometry-consistent unified framework for cross-modal place recognition that projects LiDAR point clouds into camera perspective to create depth image views, achieving …
A team from ZeroR achieved 2nd place on hate speech detection (F1: 0.797) and 4th place on sentiment analysis (F1: 0.518) in the CHiPSAL 2026 shared task on multimodal hate speech and sentiment detect…
Noise Contrastive Estimation (NCE) and InfoNCE are machine learning methods for estimating statistical distributions by distinguishing real data from noise, with applications in language modeling, spe…
Researchers have developed a brain-to-image system that decodes visual stimuli from EEG signals, achieving a mean Top-1 retrieval accuracy of 86.30% and a CLIP score of 0.903 for image reconstruction.…