4 papers
Hierarchical Chain-of-Thought: Enhancing LLM Reasoning Performance and Efficiency
Xingshuai Huang, Derek Li, Bahareh Nikpour +1
Chain-of-Thought (CoT) prompting has significantly improved the reasoning capabilities of large language models (LLMs). However, conventional CoT often relies on unstructured, flat…
Multitask-Informed Prior for In-Context Learning on Tabular Data: Application to Steel Property Prediction
Dimitrios Sinodinos, Bahareh Nikpour, Jack Yi Wei +5
Accurate prediction of mechanical properties of steel during hot rolling processes, such as Thin Slab Direct Rolling (TSDR), remains challenging due to complex interactions among c…
Memory-Augmented Transformers: A Systematic Review from Neuroscience Principles to Enhanced Model Architectures
Parsa Omidi, Xingshuai Huang, Axel Laborieux +3
Memory is fundamental to intelligence, enabling learning, reasoning, and adaptability across biological and artificial systems. While Transformer architectures excel at sequence mo…
Language-Guided Reinforcement Learning for Hard Attention in Few-Shot Learning
Bahareh Nikpour, Narges Armanfard
Attention mechanisms have demonstrated significant potential in enhancing learning models by identifying key portions of input data, particularly in scenarios with limited training…