A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
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.
Unknown
vdr Embeddings improve visual document retrieval via synthetic data training and Matryoshka Representation Learning.
Saba Sturua, Isabelle Mohr, Mohammad Kalim Akram, et al.
Jina Embeddings v3 is a 570M parameter multilingual embedding model supporting 8192-token contexts, task-specific LoRA adapters, and flexible dimension reduction via Matryoshka learning.
Unknown
A framework for customizing LLM embeddings to enable significant dimensionality reduction without performance loss.
Unknown
E5-V adapts Multimodal LLMs for universal multimodal embeddings using prompts and single-modality text training, achieving strong performance without fine-tuning or costly multimodal data.
Unknown
ColPali uses PaliGemma to generate contextualized embeddings from document page images for efficient visually rich retrieval via late interaction.
Unknown
A suite of bilingual text embedding models supporting up to 8192 tokens, trained via modified BERT pre-training and multi-task contrastive learning.