5 papers
Trend strength predicts when generative foundation models win: a power-controlled benchmark, a mechanism, and an actionable selection rule
Ahmed Cherif
Pretrained generative foundation models cast forecasting as conditional generation from a learned predictive distribution and forecast unseen series zero-shot. We establish three r…
AgentMemBench: A Systematic Benchmark for Evaluating Long-Term Memory Management Strategies in Conversational AI Agents
Ahmed Cherif
Long-term memory remains a critical bottleneck for conversational AI agents, whose finite context windows cannot support coherent recall across thousands of turns. We present Agent…
BFORE: Butterfly-Firefly Optimized Retinex Enhancement for Low-Light Image Quality Improvement
Ahmed Cherif
Low-light images suffer from poor visibility, noise, and color distortion. Existing Retinex-based enhancement methods rely on manually tuned parameters that do not generalize acros…
HalluScan: A Systematic Benchmark for Detecting and Mitigating Hallucinations in Instruction-Following LLMs
Ahmed Cherif
Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks, yet they remain susceptible to hallucinations -- generating…
MSMixer: Learned Multi-Scale Temporal Mixing with Complementary Linear Shortcut for Long-Term Time Series Forecasting
Ahmed Cherif
Long-term time series forecasting requires models that simultaneously capture rapid oscillations, medium-range periodicities, and slowly evolving macro-trends from a fixed look-bac…