diffusion models

MODELING FAKE NEWS PROPAGATION ON SOCIAL MEDIA USING EPIDEMIOLOGICAL MODELS

This study models the spread of fake news on social media using three epidemiological models: SIR (Susceptible– Infected–Recovered), SEIR (Susceptible–Exposed–Infected–Recovered), and an adapted SEIZ (Susceptible–Exposed– Infected–Skeptic) model. Three real-world case studies (Charlie Hebdo, an earthquake event, and an...

MODELING FAKE NEWS PROPAGATION ON SOCIAL MEDIA USING EPIDEMIOLOGICAL MODELS

This study models the spread of fake news on social media using three epidemiological models: SIR (Susceptible– Infected–Recovered), SEIR (Susceptible–Exposed–Infected–Recovered), and an adapted SEIZ (Susceptible–Exposed– Infected–Skeptic) model. Three real-world case studies (Charlie Hebdo, an earthquake event, and an...

RoBCtrl: Attacking GNN-Based Social Bot Detectors via Reinforced Manipulation of Bots Control Interaction

Social networks have become a crucial source of real-time information for individuals. The influence of social bots within these platforms has garnered considerable attention from researchers, leading to the development of numerous detection technologies. However, the vulnerability and robustness of these detection met...

CADSA: Content-Aware Dynamic Sparse Attention for Lightweight and Energy-Efficient Edge AI with Sub-Quadratic Complexity

CADSA is a content-aware dynamic sparse attention framework that lowers the quadratic complexity of self-attention to sub-quadratic for lightweight edge AI deployment, and fine-tuning strategy with gradient masking decreases the training memory overhead by 60%, allowing for practical on-device fine-tuning.

Distribution-Aware Diffusion-LLM for Robust Ultra-Long-Term Time Series Forecasting

Topological String-Gradient Theory (TSGT): Autonomous LLM Stress-Test and Critical Reconstruction

Topological String-Gradient Theory (TSGT): Autonomous LLM Stress-Test and Critical Reconstruction Author’s Context: Let’s be completely transparent about what this manuscript actually represents. While earlier drafts of TSGT were hand-iterated and driven by my own intuitive theoretical concepts, this release is the res...

Augment or Replace? Uneven Labour Market Consequences of AI Expansion Across Asia-Pacific Economies

The rapid diffusion of artificial intelligence (AI) has intensified debates regarding its implications for employment and the future of work. While some scholars argue that AI complements human labour by enhancing productivity and creating new employment opportunities, others contend that it displaces workers through a...

Code and figures for "Theoretical Rayleigh-wave velocity responses to seasonal hydrosphere-induced stresses: Competing stress pathways and nonunique depth interpretation"

Reproducibility package for the manuscript “Theoretical Rayleigh-wave velocity responses to seasonal hydrosphere-induced stresses: Competing stress pathways and nonunique depth interpretation.” This archive contains the source code, processed model inputs, numerical outputs, source tables, and figure-related files used...

Generate, Evaluate, Improve: Agentic Multimodal Content Personalization with Synthetic Evaluation and Closed-Loop Learning for E-Commerce

E-commerce personalization has largely optimized which item to recommend while leaving how the item is presented - image, copy, video, and narrative framing - comparatively static. This paper presents an end-to-end agentic system for multimodal advertising creative personalization. The system maps a customer-product pa...

Interference-Cancellation Vorticity Amplification and Merger Cascades: A Two-Matter Analytical Construction Program for Navier--Stokes Blowup Candidates

We develop a two-matter analytical construction program for Navier--Stokes blowup candidates, built on a single organizing principle: \emph{interference cancellation carrying the right amounts necessarily produces blowup}. The principle is formalized as an axiom with an anti-weakening clause, and its realizations are g...

Interference-Cancellation Vorticity Amplification and Merger Cascades: A Two-Matter Analytical Construction Program for Navier--Stokes Blowup Candidates

We develop a two-matter analytical construction program for Navier--Stokes blowup candidates, built on a single organizing principle: \emph{interference cancellation carrying the right amounts necessarily produces blowup}. The principle is formalized as an axiom with an anti-weakening clause, and its realizations are g...

Reconfiguring Creative Labour: Generative AI, Work Practice, and the Ethics of Distributed Agency

The diffusion of generative artificial intelligence (GenAI) across the creative industries has sharpened debates about automation, productivity, authorship, and the future of work. Attention has so far gravitated towards two poles: macro-level questions about job displacement, and technical questions about model perfor...