AIBullisharXiv â CS AI · 4h ago3
ð§ Researchers propose BiKA, a new ultra-lightweight neural network accelerator inspired by Kolmogorov-Arnold Networks that uses binary thresholds instead of complex computations. The FPGA prototype demonstrates 27-51% reduction in hardware resource usage compared to existing binarized and quantized neural network accelerators while maintaining competitive accuracy.
AIBullisharXiv â CS AI · 4h ago4
ð§ Researchers introduce ReDON, a new recurrent diffractive optical neural processor that overcomes limitations of traditional optical neural networks through reconfigurable self-modulated nonlinearity. The architecture demonstrates up to 20% improved accuracy on image recognition tasks while maintaining energy efficiency, establishing a new paradigm for non-von Neumann analog processors.
AIBullisharXiv â CS AI · 4h ago3
ð§ Researchers developed UPath, a universal AI-powered pathfinding algorithm that improves A* search performance by up to 2.2x across diverse grid environments. The deep learning model generalizes across different map types without retraining, achieving near-optimal solutions within 3% of optimal cost on unseen tasks.
AIBullisharXiv â CS AI · 4h ago3
ð§ Researchers propose FedNSAM, a new federated learning algorithm that improves global model performance by addressing the inconsistency between local and global flatness in distributed training environments. The algorithm uses global Nesterov momentum to harmonize local and global optimization, showing superior performance compared to existing FedSAM approaches.
AIBullisharXiv â CS AI · 4h ago2
ð§ Researchers developed SHINE, a Sequential Hierarchical Integration Network for analyzing brain signals (EEG/MEG) to detect speech from neural activity. The system achieved high F1-macro scores of 0.9155-0.9184 in the LibriBrain Competition 2025 by reconstructing speech-silence patterns from magnetoencephalography signals.
AIBullisharXiv â CS AI · 4h ago5
ð§ Researchers have developed a new method to extract interpretable causal mechanisms from neural networks using structured pruning as a search technique. The approach reframes network pruning as finding approximate causal abstractions, yielding closed-form criteria for simplifying networks while maintaining their causal structure under interventions.
AINeutralarXiv â CS AI · 4h ago4
ð§ Researchers introduce Memory Caching (MC), a technique that enhances recurrent neural networks by allowing their memory capacity to grow with sequence length, bridging the gap between fixed-memory RNNs and growing-memory Transformers. The approach offers four variants and shows competitive performance with Transformers on language modeling and long-context tasks while maintaining better computational efficiency.
AIBullisharXiv â CS AI · 4h ago5
ð§ Researchers investigate in-context learning (ICL) in world models, identifying two core mechanisms - environment recognition and environment learning - that enable AI systems to adapt to new configurations. The study provides theoretical error bounds and empirical evidence showing that diverse environments and long context windows are crucial for developing self-adapting world models.
AIBullisharXiv â CS AI · 4h ago6
ð§ Researchers from arXiv demonstrate that activation function design is crucial for maintaining neural network plasticity in continual learning scenarios. They introduce two new activation functions (Smooth-Leaky and Randomized Smooth-Leaky) that help prevent models from losing their ability to adapt to new tasks over time.
$LINK
AIBullisharXiv â CS AI · 4h ago3
ð§ Researchers propose QKAN-LSTM, a quantum-inspired neural network that integrates quantum variational activation functions into LSTM architecture for sequential modeling. The model achieves superior predictive accuracy with 79% fewer parameters than classical LSTMs while remaining executable on classical hardware.
AIBullisharXiv â CS AI · 4h ago5
ð§ Researchers propose Generalized Primal Averaging (GPA), a new optimization method that improves training speed for large language models by 8-10% over standard AdamW while using less memory. GPA unifies and enhances existing averaging-based optimizers like DiLoCo by enabling smooth iterate averaging at every step without complex two-loop structures.
AIBullisharXiv â CS AI · 4h ago6
ð§ SceneTok introduces a novel 3D scene tokenizer that compresses view sets into permutation-invariant tokens, achieving 1-3 orders of magnitude better compression than existing methods while maintaining state-of-the-art reconstruction quality. The system enables efficient 3D scene generation in 5 seconds using a lightweight decoder that can render novel viewpoints.
AINeutralarXiv â CS AI · 4h ago6
ð§ Researchers reveal that Test-Time Training (TTT) with KV binding, previously understood as online meta-learning for memorization, can actually be reformulated as a learned linear attention operator. This new perspective explains previously puzzling behaviors and enables architectural simplifications and efficiency improvements.
AIBullisharXiv â CS AI · 4h ago5
ð§ Researchers introduced SemVideo, a breakthrough AI framework that can reconstruct videos from brain activity using fMRI scans. The system uses hierarchical semantic guidance to overcome previous limitations in visual consistency and temporal coherence, achieving state-of-the-art results in brain-to-video reconstruction.
$RNDR
AINeutralarXiv â CS AI · 4h ago1
ð§ Researchers introduce Hierarchical Concept Embedding Models (HiCEMs), a new approach to make deep neural networks more interpretable by modeling relationships between concepts in hierarchical structures. The method includes Concept Splitting to automatically discover fine-grained sub-concepts without additional annotations, reducing the burden of manual labeling while improving model accuracy and interpretability.
AINeutralarXiv â CS AI · 4h ago0
ð§ Researchers propose Mixed Guidance Graph Optimization (MGGO) to improve multi-agent pathfinding systems by optimizing both edge directions and weights in guidance graphs. The paper introduces two MGGO methods, including one using Quality Diversity algorithms with neural networks, to provide stricter guidance for agent movement in lifelong scenarios.
AINeutralarXiv â CS AI · 4h ago0
ð§ Researchers propose SegReg, a latent-space regularization framework for medical image segmentation that improves model generalization and continual learning capabilities. The method operates on U-Net feature maps and demonstrates consistent improvements across prostate, cardiac, and hippocampus segmentation tasks without adding extra parameters.
AINeutralarXiv â CS AI · 4h ago0
ð§ Researchers propose Flowette, a new AI framework for generating graphs with recurring structural patterns using continuous flow matching and graph neural networks. The model introduces 'graphettes' as probabilistic priors to better capture domain-specific structures like molecular patterns, showing improvements in synthetic and small-molecule generation tasks.
AINeutralarXiv â CS AI · 4h ago1
ð§ Researchers analyzed training trajectories in small transformer models, finding that parameter updates organize into a dominant drift direction with transverse dynamics. The study reveals that different optimizers (AdamW vs SGD) create substantially different trajectory geometries, with AdamW developing multi-dimensional structures while SGD produces more linear evolution.
AINeutralarXiv â CS AI · 4h ago0
ð§ Researchers developed a dual-branch neural network for micro-expression recognition that combines residual and Inception networks with parallel attention mechanisms. The method achieved 74.67% accuracy on the CASME II dataset, significantly outperforming existing approaches like LBP-TOP by over 11%.
AINeutralarXiv â CS AI · 4h ago0
ð§ Researchers propose the Intrinsic Lorentz Neural Network (ILNN), a fully intrinsic hyperbolic architecture that performs all computations within the Lorentz model for better handling of hierarchical data structures. The network introduces novel components including point-to-hyperplane layers and GyroLBN batch normalization, achieving state-of-the-art performance on CIFAR and genomic benchmarks while outperforming Euclidean baselines.
AINeutralarXiv â CS AI · 4h ago0
ð§ Researchers developed a new approach to minimize cost functions in shallow ReLU neural networks through explicit construction rather than gradient descent. The study provides mathematical upper bounds for cost minimization and characterizes the geometric structure of network minimizers in classification tasks.
AINeutralarXiv â CS AI · 4h ago0
ð§ Researchers propose a dispatcher/executor principle for multi-task Reinforcement Learning that partitions controllers into task-understanding and device-specific components connected by a regularized communication channel. This structural approach aims to improve generalization and data efficiency as an alternative to simply scaling large neural networks with vast datasets.
AIBullisharXiv â CS AI · 4h ago0
ð§ Researchers propose a quaternion-valued supervised learning Hopfield neural network (QSHNN) that leverages quaternions' geometric advantages for representing rotations and postures. The model introduces periodic projection-based learning rules to maintain quaternionic consistency while achieving high accuracy and fast convergence, with potential applications in robotics and control systems.
AINeutralarXiv â CS AI · 4h ago1
ð§ Researchers have developed MEDIC, a neural network framework for Data Quality Monitoring (DQM) in particle physics experiments that uses machine learning to automatically detect detector anomalies and identify malfunctioning components. The simulation-driven approach using modified Delphes detector simulation represents an initial step toward comprehensive ML-based DQM systems for future particle detectors.
