cs papers | Gist.Science

Experimental Realization of a Zero-RAM, Battery-Free 3.0mm Reversible Computing Platform Circumventing Landauer's Limit for Sustainable Global Climate Mitigation

This paper claims to present a revolutionary, battery-free 3.0 mm reversible computing platform that circumvents Landauer's limit and eliminates the need for physical RAM and traditional networking by utilizing adiabatic charge recovery and quantum resonance, thereby purportedly achieving near-zero power consumption, instant AI model synthesis, and total immunity to environmental and security threats.

Min Ho Jung2026-08-18

💻 computer science

Feature-Optimized Hybrid AI Models for Explainable and Generalizable Epilepsy Prediction

This paper evaluates hybrid AI frameworks that integrate optimized feature selection and explainable AI techniques to develop robust, interpretable, and generalizable models for predicting epileptic seizures using multimodal biomedical data.

Shruti Tilwant, Prof .Dr. Nandkumar Kulkarni2026-08-18

💻 computer science

Predicting Pathogen Emergence Using a Spatiotemporal Graph Neural Network and Explainable AI Approach

This study proposes a framework integrating Spatiotemporal Graph Neural Networks with Explainable AI to accurately forecast pathogen emergence risks using a human epidemic database, achieving superior performance over baseline models while quantifying uncertainty and identifying key drivers to enable proactive public health interventions.

Oreofe Jolaolu, Okoh J.C2026-08-18

💻 computer science

Signed Layer-Level Evidence in Transformer Predictions, and a Diagnostic for When It Applies

This paper introduces Language Evidence Flow (LEF) to decompose Transformer predictions into signed per-layer evidence and proposes ScopeGate, a permutation-based diagnostic tool that reveals the model- and task-specific limitations of existing error detectors, demonstrating that no single metric universally predicts model failure.

Jeffery Opoku, David Banahene2026-08-18

💻 computer science

A Quantum-Inspired Ensemble Learning Framework for Multi-Class Respiratory Disease Diagnosis

This paper introduces Quantum-Cognitive Fusion (Q-CogFusion), a novel quantum-inspired ensemble learning framework that integrates feature entanglement, geometry-aware class balancing, and attention-based aggregation to achieve high-accuracy, interpretable multi-class diagnosis of respiratory diseases on imbalanced clinical data.

Francis Ofoma Eze, Wang QingXian, Chidi Daniel Chukwu, Attah Festa Kosisochukwu, David Ocho Audu, Eze Franklin ThankGod (…)2026-08-18

💻 computer science

Buddhist, Yogic, and Vedic Contemplative Principles in AI Model Prompting: A Pilot Study

This pilot study demonstrates that prompting large language models with contemplative principles from Buddhist, Vedic, and Yogic traditions significantly enhances their safety, ethical alignment, and cooperative quality compared to non-contemplative baselines, offering a low-cost, tradition-agnostic intervention that requires no model retraining.

Steve Haberlin, Satyam Tiwari, Shiva Jahani2026-08-18

💻 computer science

Benchmarking Real-Time Database Synchronisation Architectures: REST Polling, WebSocket Push, and CockroachDB CDC

This paper presents a controlled benchmark comparing REST polling, WebSocket push, and CockroachDB CDC architectures for real-time database synchronization, revealing that while WebSocket push offers the lowest median latency and REST polling provides predictable bounded delays, CDC delivers competitive medians but suffers from significant tail latency due to batching and specific protocol incompatibilities.

Kunal Dhanda2026-08-18

💻 computer science

An Empirical Comparison of Positional Encoding Methods in a Small Character-Level Transformer

This study empirically compares four positional encoding methods in a small character-level Transformer trained on Shakespeare-style text, finding that Rotary Positional Embeddings (RoPE) consistently outperform learned embeddings, sinusoidal encoding, and ALiBi in validation loss and text generation quality, though the results are specific to the experimental setting.

Chaitanya Patil2026-08-18

💻 computer science

J-space Forecasts Model Collapse, but Only Anchoring the Function Prevents It

While recursive training on synthetic data causes model collapse that manifests as a global drift in the J-space representation subspace, the study finds that stabilizing this geometry is ineffective, whereas anchoring the model's input-output function to a pre-collapse state using a small number of real sequences successfully prevents nearly all damage.

ChaeWoo Son2026-08-18

💻 computer science

Resource-Constrained Overlay–Underlay Mode Selection in LTE-V2X Networks Using Double Deep Q-Learning

This paper proposes a Double Deep Q-Network (DDQN) framework with a switching-control mechanism to adaptively select overlay–underlay transmission modes across six radial cell layers in resource-constrained LTE-V2X networks, achieving significant improvements in throughput and reliability while stabilizing mode changes compared to existing empirical and greedy baselines.

Jabir Ahmad Jahin Bhuiyan, Mohammad Tawhid Kawser2026-08-18

← Previous Next →