All Articles
17710 articles total
Memoirs of Extraordinary Popular Delusions and the Madness of Crowds
A discussion regarding the book 'Memoirs of Extraordinary Popular Delusions and the Madness of Crowds'.
Distilling a Modular Reservoir Through a Genomic Bottleneck
Researchers use hypernetworks to learn a compressed generative process for modular reservoir computing, improving performance on temporal tasks.
Evolutional Math: Cross-Validated Island-Model Genetic Programming for Interpretable Symbolic Regression on Small, Wide Datasets
Evolutional Math is an open-source genetic programming system for interpretable symbolic regression on small, wide datasets.
A Query-Driven Communication-Efficient Digital Twins Design for Autonomous Driving
A new query-driven digital twin architecture for autonomous driving that reduces communication overhead and planning position error.
RoboGaze: Evaluating Robot World Models via Structured Vision-Language Analysis
RoboGaze is a multi-agent VLM framework designed to provide structured, interpretable evaluation for robot-manipulation videos.
Data Provenance for Image Auto-Regressive Generation
A post-hoc framework for the robust detection of provenance signals in images generated by autoregressive models.
Schema-First Retrieval: Embedding Catalogs for Natural Language Analytics
Schema-First Retrieval improves text-to-SQL systems by embedding catalog metadata to better select relevant tables and columns.
Automated Quality Assessment of Geospatial Vector Data: A GeoAI Approach using Spatial Representation Learning
Topo4Vec is an automated GeoAI framework for scalable vector data quality assessment using spatial representation learning.
Few-class Fidelity: Evaluating Explanations of Real-conditions CNN classifiers with Optimized Perturbations
A proposed variation of Fidelity-based XAI metrics to evaluate the faithfulness of eXplainable AI solutions for low-class CNN classifiers.
RADIANT-PET: Reasoning-Augmented PET/CT Lesion Segmentation with Large Language Models and Reinforcement Learning
RADIANT-PET is a reasoning-augmented framework combining voxel-level segmentation with LLM adjudication for PET/CT lesion segmentation.
Zluda 6 release (run unmodified CUDA applications on non-Nvidia GPUs)
Zluda 6 has been released, allowing unmodified CUDA applications to run on non-Nvidia GPUs.
Who are the fire-tamers?
An exploration of 'fire-tamers', though the provided snippet contains no technical details.
AI agents need context everywhere they run, even where the cloud can't follow
Couchbase announced the AI Data Plane, an operational platform providing agent memory, context retrieval, and an MCP server for enterprise AI agents across cloud, on-prem, and edge.
Beyond the Reranker: Do RAG Retrieval Enhancements Help Once a Strong Reranker Is Present?
Researchers investigate whether RAG retrieval enhancements help when a strong reranker is present, finding that only query expansion and a new method called SSCC yield reliable gains on heterogeneous data.
Multimodal and Multiscale Spatial-Temporal Semantic Search and Recommendation with AI Foundation Models
A new framework using LLMs and VLMs, featuring CAMERA and ASTRA algorithms, is proposed for multimodal spatial-temporal semantic search in Geographic Information Retrieval.
Conversational Query Engine for Mixed-Modality Heterogeneous Enterprise Data Sources
COGNI is introduced as a conversational BI system for heterogeneous enterprise data, utilizing slide-adaptive chunking and a LoRA fine-tuned Qwen model for modality routing.
Model Merging to Evolution: Parameter Space Exploration for Expert Models
The MERGEvolve framework is proposed to improve expert model merging by combining it with an evolution strategy to explore parameter space beyond convex combinations.
When Does Overlap Help? OSU-Mem and a Cell-Conditional Analysis of Trajectory Memory for LLM Agents
The OSU-Mem system analyzes trajectory memory for LLM agents, demonstrating that overlapping semantic units improve retrieval when evidence steps share tool calls or entities.
Memory-Augmented LSTM Autoencoder for Unsupervised Activity Recognition with IMU Sensor Fusion
A memory-augmented LSTM autoencoder is proposed for unsupervised activity recognition using IMU sensor fusion, achieving high accuracy in real-world activity transitions.
LEDGER: Scaling Agentic Document Editing with Dependency-aware Graph Retrieval
LEDGER is introduced to scale agentic document editing by using dependency-aware graph retrieval to maintain consistency and reduce token usage in long structured documents.