Neural Networks

Researchers propose a new approach to near-sensor computing that performs lightweight Neural Architecture Search (NAS) directly on deployment devices to adapt tiny neural networks to real-time sensor data. Validated on t…

Researchers introduced block-sparse featurizers (BSFs) to capture visual concept manifolds in neural network representations, showing that concepts are low-dimensional geometric structures rather than isolated directions…

Researchers propose SEMIR, a framework that replaces the pixel lattice with a parameterized graph minor to preserve thin-structure connectivity in segmentation tasks. The method achieves full-resolution inference without…

Researchers propose G-SPIN, a graph-based framework that corrects phonetic errors in ASR outputs by combining a graph neural network for candidate generation with a masked language model and LLM for contextual re-ranking…

Researchers argue that neural network learning opacity stems from dynamical complexity, identifying sensitivity to weight initialization, feedback in gradient optimization, and sensitivity to training data as irreducible…

Researchers propose an empirical test for error correction in large language models, finding that residual-stream activations are robust to small perturbations and that feature-specific directions are privileged over gen…

Researchers introduced the Swarm-Inspired Emergent Synchronizer (SIES), a graph-dynamical framework that learns local interaction rules for collective behaviors across graphs, dynamics, and tasks. SIES achieved synchroni…

A new study on holographic memory for zero-shot compositional reasoning in knowledge graphs found that while Holographic Reduced Representations (HRR) and Fourier HRR (FHRR) perform competitively on single-hop queries, t…

Researchers propose DCQ-GNN, a spectral graph neural network using convex-concave quadratic filters to improve spectral selectivity without high-order polynomials. The model achieves top average rank on heterophilic grap…

Researchers introduced Pre-Warm, a zero-training-cost method for data-conditioned initialization of the first convolutional layer in CNNs. The technique clusters patches from a single training batch to initialize half of…

Researchers propose a novel neural network quantization method that learns quantization-aware linear paths in weight space to find low-loss subspaces, enabling direct quantization of the midpoint without performance degr…

A developer completed building an LSTM cell using PyTorch and Lightning AI, implementing the forward pass and optimizer. The LSTM unit processes stock price inputs over four days, updating long-term and short-term memory…

Shrijith Venkatramana, building git-lrc, explains how scaling laws discovered by OpenAI, Google, DeepMind, and Anthropic made large language models like ChatGPT, Claude, and Gemini possible. The 2020 OpenAI paper 'Scalin…

PyTorch, JAX, and compiler-level tools like Enzyme use three different representations for automatic differentiation—runtime tape, functional trace-and-transform, and source (IR) transformation—each with distinct trade-o…

Researchers propose EMRFormer, a spiking neural network architecture that applies spike-driven transformers to automatic modulation recognition, achieving state-of-the-art accuracy while reducing theoretical energy consu…

Researchers propose a frequency-guided feature representation learner for small object detection that shifts from spatial to spectral processing. The method, instantiated via lightweight plug-and-play modules, achieves c…

Researchers developed low-power analogue neural networks with trainable nonlinear connections, inspired by Kolmogorov-Arnold networks, achieving efficient continuous control tasks like robotic kinematics and photovoltaic…

Researchers argue that vanilla conditional diffusion models are fundamentally incapable of compositional generation when target distributions are out-of-distribution, as score estimation errors cause catastrophic perform…

Researchers propose Progressive Pixel-Neighborhood Deformable Cross-Attention (PNAFusion) for multispectral object detection, achieving state-of-the-art results on FLIR, M3FD, and DroneVehicle datasets while reducing GPU…

Researchers propose ModTGCN, a modularity-aware graph neural network for text classification that jointly optimizes cross-entropy and a modularity-based auxiliary objective to promote class-coherent document communities.…