All Articles
16560 articles total
Federated Lightweight Fine-Tuning
FLITE is a new federated learning framework that drastically reduces communication bandwidth by using low-rank mapping networks to generate weights.
FSDBN: Foreground-Aware EEG--Visual Alignment via Dynamic Brain Networks
FSDBN is a framework for EEG-visual decoding that uses dynamic brain networks and foreground-aware alignment to improve brain-to-image retrieval.
AMD Ryzen 7 7700X3D Review: 3D V-Cache Gaming Performance for Less – HotHardware
A review of the AMD Ryzen 7 7700X3D processor, focusing on its 3D V-Cache gaming performance and value proposition.
Utility companies are promising to spare us from AI’s energy bill
Utility companies and data center developers in the US have signed a pledge to protect consumers from rising electricity bills caused by the AI boom.
Reliability Scales Inversely: Bigger Models Compound Mistakes Faster via a Hidden Auto-Regressive Risk Regime
Research indicating that larger language models compound mistakes faster due to an auto-regressive risk regime, where reliability degrades as scale increases.
The Information Shadow: Measuring Structural Limits on What Language Models Can Learn
Introduction of the 'information shadow' concept, defining structural limits on what language models can learn regardless of data scale or training time.
Gradient-Energy Guided Block-Wise Perturbations for Sharpness-Aware Minimization
Proposed GEAR-SAM, a Gradient-Energy Adaptive Radius SAM method to improve generalization and robustness in neural network training.
Agentic Calibration of Grey-Box Simulation Models: An LLM-Driven Alternative
An LLM-driven agentic calibration method for grey-box simulation models that outperforms classical Bayesian Optimization and Nelder-Mead methods.
Distribution-First Population Simulation: Collapse, Calibration, and Recall in Non-WEIRD LLM Persona Modeling
Study on LLM persona modeling showing that independent agents fail to reproduce population distributions and proposing a 'distribution-first' corrective.
Approximating SPR Distance Between Phylogenetic Trees with Graph Neural Networks
Using Graph Neural Networks to approximate the NP-hard SPR distance between phylogenetic trees for better epidemic dynamics understanding.
Binding Drift in Multi-Step Tool-Augmented Agents
Analysis of 'binding drift' in tool-augmented agents, showing how entities can shift during multi-step workflows and proposing a re-verifier fix.
Cost Accounting for Reactive Computational Graphs: Exhaustive Sweeps, Sequential Mutation, and the Backward-Locality Gap
A cost accounting analysis of reactive computational graphs for neural network interventions, validated using the NeuroDSL engine in Julia.
Codeberg: ToU extension to prohibit LLM-extrusions
Codeberg updates its Terms of Use to prohibit the use of its platform for LLM training data extraction (scraping).
Glow emerges from stealth at $1.2B valuation to challenge endpoint security in the AI era
Glow launches with a $1.2B valuation to provide endpoint security tailored for AI agents and developer tools in enterprise environments.
FedCC: A Low-Resource Federated Adaptation of Foundation Models for Robust Corpus Callosum localization in Fetal Ultrasound Images
FedCC is a federated learning framework using DINOv2 and LoRA for privacy-preserving corpus callosum localization in fetal ultrasound images.
Compressing What Matters: Neuron Importance Meets Data-Aware Low Rank Approximation for Language Model Compression
Researchers propose a new method for LLM compression combining neuron importance and data-aware low-rank approximation with dynamic rate allocation.
Edge-Efficient Transformer for End-to-End RF Spectrum Monitoring
E-SpecFormer is an edge-efficient Transformer for RF spectrum monitoring featuring a new Softmax-free attention mechanism called LiTAN.
Preference-Conditioned Multi-Objective Reinforcement Learning for Runtime-Tunable Transit Signal Priority
A preference-conditioned multi-objective RL controller is introduced for runtime-tunable transit signal priority to balance bus delay and traffic flow.
BearingNAS: Obtaining In-Sensor Intelligent Fault Diagnosis Systems for Bearings Using a Laptop
BearingNAS provides a hardware-aware NAS framework for deploying intelligent fault diagnosis systems directly onto low-resource sensor dies.
Towards Principled Continual Anomaly Detection: A Systematic Framework and Benchmark Scenarios
A systematic framework for reproducible benchmark scenario design is proposed for continual anomaly detection in tabular cybersecurity datasets.