A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Cecilia Ka Yuk Chan, Katherine K. W. Lee
Survey study comparing Gen Z students and Gen X/Y teachers on generative AI adoption in higher education, revealing a generation gap in optimism versus concern.
Rafael Gómez‐Bombarelli, Jennifer N. Wei, David Duvenaud, et al.
A deep neural network converts discrete molecular representations to and from a continuous latent space, enabling gradient-based optimization and generation of novel chemical structures.
Nicholas Ekow Thomford, Dimakatso Alice Senthebane, Arielle Rowe, et al.
This review discusses plant-based natural product drug discovery and how innovative technologies like AI, organ-on-chip, and microfluidics play a role in next-generation drug discovery.
Yingxia Shao, Hongzheng Li, Xizhi Gu, et al.
This survey systematically reviews distributed GNN training, categorizing optimization techniques into data partition, batch generation, execution model, and communication protocol to address communication, accuracy, and imbalance challenges.
Ruichen Zhang, Hongyang Du, Yinqiu Liu, et al.
Proposes an interactive AI framework with pluggable LLM and RAG modules for next-generation network management and optimization, demonstrating effective optimization problem design.
Boci Peng, Yun Zhu, Yongchao Liu, et al.
The first comprehensive survey of Graph Retrieval-Augmented Generation (GraphRAG), formalizing its workflow into graph-based indexing, graph-guided retrieval, and graph-enhanced generation.
Juyong Jiang, Fan Wang, Jiasi Shen, et al.
A systematic survey of LLMs for code generation, covering data curation, advances, evaluation, ethics, environmental impact, and applications, with comparative analysis on HumanEval, MBPP, and BigCodeBench.
Unknown
UniLat3D introduces geometry-appearance unified latents for single-stage 3D generation, evaluated against state-of-the-art models like Hunyuan3D2.1 and TRELLIS.
Unknown
Direct3D-S2 introduces spatial sparse attention for scalable 3D generation, enabling practical gigascale 3D synthesis at 1024^3 resolution.
Unknown
SSDNeRF unifies 3D generation and reconstruction by conjoining a triplane NeRF auto-decoder with a single-stage diffusion model.
Unknown
Tune-A-Video enables one-shot text-to-video generation by tuning a pretrained image diffusion model on a single video.
Liangchen Li, Jiajun He
Bidirectional consistency models extend consistency models to enable both forward and reverse sampling, improving image generation quality and flexibility.