A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Peng Cui, Xiao Wang, Jian Pei, et al.
A comprehensive survey categorizing network embedding methods into structure/property-preserving, side-information-based, and advanced information-preserving approaches, with evaluation and future directions.
Hongyun Cai, Vincent Wenchen Zheng, Kevin Chen–Chuan Chang
A comprehensive survey of graph embedding that formalizes the problem, proposes two taxonomies, summarizes applications, and suggests future research directions.
Unknown
This study presents a low-rank adaptation method for finetuning large language models, embedding a semantic-aware low-rank adaptation module into attention layers.
Adnan El Assadi, Niklas Muennighoff, Jinhyuk Lee
A controlled, cost-aware comparison of LLMs and embedding models across 37 tasks finds them effectively tied in quality, but LLMs cost up to 1,431x more, supporting a division of labor.
Dhruva Karkada, D. Korchinski, A. Nava, et al.
This paper proves that translation symmetries in language statistics explain the geometric structures (circles, manifolds) in LLM word embeddings, deriving manifold geometry analytically and showing robustness to perturbations.
Aldo Pareja, Giacomo Domeniconi, Jie Chen, et al.
EvolveGCN adapts GCN parameters over time using an RNN to handle dynamic graphs without relying on node embeddings.
Omer Levy, Yoav Goldberg, Ido Dagan
The paper shows that performance gains of word embeddings over count-based models are due to design choices and hyperparameters, not the algorithms, and these can be transferred to traditional models.
Haris Riaz, Hyungji Kim, Mihai Surdeanu
SiPE learns a lightweight syntactic prior from dependency parses during pretraining and injects it into positional embeddings, improving syntax and language understanding benchmarks.
Mukhtiar Ali, Harsh Dubey, Sugam Mishra, et al.
Introduces CLIP-CC-Bench, an evaluation suite for long-form video description using 90-second movie clips and expert-written paragraph references, with an ensemble of five LLM embeddings and coarse/fine-grained semantic matching to rank 17 video-lang
Unknown
This paper explores self-supervised learning methods to obtain general-purpose feature embeddings by capturing visual invariances across domains.
Unknown
This paper explores the theoretical capabilities of ideal foundation models and their embedding spaces, demonstrating their power and potential applications.
Orion Weller, Michael Boratko, Iftekhar Naim, et al.
This paper proves that single-vector embedding models have a fundamental dimension-dependent limit on the number of distinct top-k subsets they can represent, and shows this limitation arises even in simple realistic queries.