Neural Networks

Researchers have developed DiffSlack, a differentiable projection layer that enforces nonlinear inequality constraints in neural networks by reformulating them as equalities with learnable slack variables. Tested on vehi…

Researchers have developed a framework for unpaired RGB-thermal novel view synthesis that uses a 3D feed-forward transformer to independently estimate camera poses for each modality, then aligns them with the Procrustes …

Researchers have demonstrated that formal concept lattices, derived from Formal Concept Analysis, can serve as principled semantic scaffolds to guide neural network learning by organizing concepts hierarchically from gen…

Researchers have developed LightVesselNet, a neural network with only 75,000 parameters that performs retinal blood vessel segmentation competitively with much larger models. The ultra-lightweight architecture, which use…

Researchers have developed DFPL, a framework for incomplete image-tabular classification that addresses the missing-modality problem through fine-grained prototype learning. The method introduces Shared-Specific Prototyp…

Researchers developed a sensor-guided adaptive contrastive learning framework that uses privileged LiDAR data during training to teach visual encoders to focus on navigation-relevant geometry rather than scene-specific a…

Researchers developed and evaluated deep learning models for automated age-related macular degeneration (AMD) staging using OCT and OCT angiography data from 271 participants. A biomarker-based model achieved the highest…

Researchers have developed NIV (Neural Axis Variations), a method that automatically converts a static font into a fully functional variable font by predicting per-point displacements along desired design axes. Trained o…

Researchers have developed a deep learning algorithm that restores three-dimensional capillary anatomy from a single optical coherence tomographic angiography (OCTA) volume, addressing imaging artifacts that hinder relia…

Researchers have demonstrated that human preference scores for text-to-image content can be accurately predicted before generation begins, using minimal computational overhead. The study found that predicting these score…

A developer has introduced A11, an architecture designed to prevent AI model degradation by enforcing strict handling of gaps between wisdom (S2) and knowledge (S3). Rather than smoothing contradictions, A11 records thes…

Researchers have introduced On-Policy Representation Distillation (OPRD), a method that aligns student and teacher model representations across selected layers during training, bypassing the language model head to elimin…

Yun Cheng and Chao Zhang published a PM2.5 forecasting model in Scientific Reports on June 5, 2026, that combines variational mode decomposition with deep learning. The approach decomposes PM2.5 time series into frequenc…

A new analysis of dictionary learning, which Sparse Autoencoders (SAEs) approximate, identifies necessary optimality conditions that explain why SAEs exhibit puzzling behaviors like feature-splitting and feature-absorpti…

A developer porting PyTorch LLM code to JAX using Flax encountered difficulties when attempting to store model checkpoints with Safetensors, as the library's Flax API expects flat dictionaries but Flax's `nnx.State.to_pu…

Researchers have developed a machine-learning method that detects genetic epilepsy signals in seizure-free baseline EEG recordings, according to a study published in the Journal of Neural Engineering. The 'bag-of-waves' …

Flourish, a New York-based neuroscience startup, raised $500 million at a $2.5 billion valuation from investors including Jeff Bezos, Lux Capital, and GV. The company is developing Cortex AI, a brain-inspired system desi…

A developer completed a baseline implementation for the Kaggle Orbit Wars competition, achieving an initial score of around 1030 before the score dipped slightly. The developer also used AWS for the first time to extract…

Hemminger and colleagues introduced CIPHER, a neural-network framework that jointly optimizes gene pooling into measurement channels and downstream cell embedding for aggregated spatial transcriptomics experiments. The f…

Researchers have improved Activation Oracles (AOs)—fine-tuned LLMs that answer natural language questions about a target model's internal activations—by training on on-policy rollouts, using a higher-quality conversation…