A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
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.
Iulian Vlad Serban, Alessandro Sordoni, Yoshua Bengio, et al.
Extends hierarchical recurrent encoder-decoder networks to open-domain dialogue, showing competitiveness with n-gram models and improvement via bootstrapping from QA pairs and pretrained embeddings.
Unknown
This paper proposes Structural LM, which extends BERT by incorporating 1D and 2D cell-level embeddings for structured text understanding.
Unknown
LAMBERT enhances RoBERTa with layout embeddings and relative bias for layout-aware document understanding without raw images.
Xinkun Huang, Jinyan Sang, Changrong Jin, et al.
Extends BERT with 2-D position and image embeddings for layout-aware document understanding.
Daniel Bolya, Po-Yao Huang, Peize Sun, et al.
Perception Encoder is a vision encoder trained via contrastive vision-language learning that achieves state-of-the-art results across diverse tasks by extracting strong general embeddings from intermediate layers.
Unknown
Leverages Gemini LLM to generate generalizable multilingual text and code embeddings via synthetic data and filtering.