A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
A decade-long review of evolving architectures and long-horizon planning in multi-agent conversational AI, synthesizing progress and open challenges.
Simon Vandenhende, Stamatios Georgoulis, Wouter Van Gansbeke, et al.
A comprehensive survey of multi-task learning for dense prediction tasks, covering architectures, optimization methods, and experimental evaluation across benchmarks.
Giorgio Roffo
This tutorial explores advanced LLM techniques including RAG, PAL, ReAct, LangChain, fine-tuning strategies, and transformer architectures to address limitations like temporal cutoffs and mathematical inaccuracies.
Benjamin Belay
This paper demonstrates that generated text can carry detectable evidence of causally relevant internal states, even when the answer is unchanged, in controlled feed-forward and transformer architectures.
Zixuan Ke, Fangkai Jiao, Yifei Ming, et al.
A survey categorizing LLM reasoning methods along regimes (inference-time vs training) and architectures (standalone vs agentic), analyzing input/output-level techniques and trends.
Yin Dai, Yifan Gao, Fayu Liu
TransMed combines CNN and transformer architectures for multi-modal medical image classification, achieving significant accuracy improvements on parotid gland and knee injury datasets.
Li Deng
This tutorial survey provides a comprehensive overview of deep learning architectures, algorithms, and applications, categorizing them into generative, discriminative, and hybrid classes.
Yijia Xiao, Wanjia Zhao, Junkai Zhang, et al.
This paper provides the first comprehensive overview of Protein LLMs, covering architectures, training datasets, evaluation metrics, and applications, with a structured taxonomy from over 100 articles.
L'eo Grinsztajn, Klemens Floge, Oscar Key, et al.
Tabpfn-2.5 advances tabular foundation models with new techniques including retrieval, fine-tuning, and novel architectures, aiming to define the future of tabular data systems.
Unknown
This paper reviews geometric deep learning architectures that incorporate symmetry for molecular representation learning, highlighting their promise in molecular modelling applications.
Unknown
This paper presents a unified geometric deep learning framework that generalizes CNNs and other architectures to non-Euclidean domains such as graphs and manifolds.
Unknown
Continuous graph neural networks (CGNN) generalize existing graph neural networks by framing them as dynamical systems, enabling deeper architectures and improved performance.