Neural Networks

Researchers have demonstrated that large language models can serve as selective surrogates for GPU kernel performance evaluation, accurately forecasting kernel runtime without requiring repeated compilation and execution…

Researchers have developed Pixel Cube, a diffusion-based method for relighting dynamic portrait videos that achieves photorealism and temporal consistency. The system uses a hybrid dataset of real-captured and rendered v…

Researchers have developed CL-DMDF, a dynamic multimodal data fusion model that uses contrastive learning to address challenges with missing or uncertain modality inputs in real-world applications. The model introduces a…

Researchers have developed a Marchenko-Pastur (MP) random-matrix approach for pruning deep neural networks that requires minimal post-pruning fine-tuning. The method provides deterministic data-path certificates for accu…

Researchers introduced Geometry-Aware Tabular Diffusion (GATD), a method that improves tabular data synthesis by feeding pairwise angles and lengths from column value differences into diffusion denoisers as inputs and au…

Researchers have developed TopoMamSurv, a Graph Mamba survival analysis framework that uses topology-aware ordering to address computational bottlenecks in Whole Slide Image analysis. The framework integrates a bidirecti…

Researchers have developed a lightweight custom convolutional neural network to improve the security of EEG-based brain-computer interfaces against adversarial attacks. The proposed model outperformed existing EEG-specif…

A new study proves the Spectral Alignment Decomposition, which explains why the curvature exponent $\alpha$ — governing how Hessian eigenvalues scale with gradient singular values — varies across neural network layers, w…

Researchers found that transformer-based language models perform better when deeper attention layers learn context-free value vectors that preserve original token information, rather than relying on the residual stream f…

Researchers have developed AURA-Mem, a memory system for robot policies that maintains a constant 4,224-byte inference state regardless of episode length, compared to a KV-cache that grows 6,061 times larger over 100,000…

Researchers have developed a collaborative inference method for occlusion-robust object detection on edge devices with less than 1 MB SRAM, combining an MCUNet backbone, YOLOv2 detection head, and TensorFlow Lite quantiz…

Researchers introduced Mixture of Pathway Experts (MoPE), a knowledge-distillation framework that uses RNA-derived pathway information during training to improve computational pathology models that only analyze whole-sli…

Researchers from multiple institutions evaluated machine learning and deep learning models for satellite-derived bathymetry using Sentinel-2 imagery, finding that preserving spatial continuity during training was the mos…

Researchers have developed RelGT-AC, a relational graph transformer designed to predict missing column values in relational databases, functioning as an intelligent form-filling assistant. The model introduces a column m…

Researchers have developed WISE-HAR, an ensemble deep learning framework that uses WiFi signals to recognize human activities including walking and arm-waving with 94.87% accuracy. The framework, tested on the Wallhack1.…

A study evaluating encoder-only Transformer and LSTM frameworks for streamflow prediction in ungauged basins found that the LSTM outperformed the Transformer across both upstream-only and combined configurations. Incorpo…

Deep neural networks have enabled generative modeling of biomolecules, with models like AlphaFold3 and Chai-2 now capable of predicting and designing drug-like molecules and antibodies. However, researchers at Ligo found…

A study published in *Neuroscience* found that when young girls observe their parents discussing their relationship, their brain activity synchronizes with their mothers'. Researchers led by Yihui Wang at Shanghai Normal…

Anthropic's 2025 research paper "On the Biology of a Large Language Model" demonstrates that LLMs engage in genuine multi-step reasoning through human-interpretable concepts, contradicting the long-held belief that neura…

Dr. Hon Weng Chong, CEO of Cortical Labs, announced that biological neurons are 5,000 times more stable and sample-efficient than traditional GPU-based AI systems. Chong also raised ethical concerns about creating consci…