wolosonovich (Jason Wolosonovich)

upvoted a paper 6 days ago

HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems

Paper • 2411.02959 • Published 8 days ago • 57

upvoted a paper 27 days ago

Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free

Paper • 2410.10814 • Published 29 days ago • 48

upvoted a paper 28 days ago

StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization

Paper • 2410.08815 • Published Oct 11 • 41

upvoted a paper about 1 month ago

Large Language Models as Markov Chains

Paper • 2410.02724 • Published Oct 3 • 31

upvoted a paper about 2 months ago

Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts

Paper • 2409.16040 • Published Sep 24 • 13

upvoted a paper 2 months ago

OLMoE: Open Mixture-of-Experts Language Models

Paper • 2409.02060 • Published Sep 3 • 77

upvoted 2 articles 3 months ago

Article

dstack: Your LLM Launchpad - From Fine-Tuning to Serving, Simplified

By

•

Aug 22

• 12

Article

Welcome FalconMamba: The first strong attention-free 7B model

Aug 12

• 102

upvoted 2 papers 3 months ago

CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases

Paper • 2408.03910 • Published Aug 7 • 15

Improving Text Embeddings for Smaller Language Models Using Contrastive Fine-tuning

Paper • 2408.00690 • Published Aug 1 • 21

upvoted an article 4 months ago

Article

Docmatix - a huge dataset for Document Visual Question Answering

Jul 18

• 66

upvoted a paper 4 months ago

E5-V: Universal Embeddings with Multimodal Large Language Models

Paper • 2407.12580 • Published Jul 17 • 39

upvoted an article 4 months ago

Article

SmolLM - blazingly fast and remarkably powerful

Jul 16

• 260

upvoted 2 papers 4 months ago

SpreadsheetLLM: Encoding Spreadsheets for Large Language Models

Paper • 2407.09025 • Published Jul 12 • 128

Is It Really Long Context if All You Need Is Retrieval? Towards Genuinely Difficult Long Context NLP

Paper • 2407.00402 • Published Jun 29 • 22

upvoted 2 papers 5 months ago

GEB-1.3B: Open Lightweight Large Language Model

Paper • 2406.09900 • Published Jun 14 • 20

Block Transformer: Global-to-Local Language Modeling for Fast Inference

Paper • 2406.02657 • Published Jun 4 • 36

upvoted 2 papers 6 months ago

Towards Modular LLMs by Building and Reusing a Library of LoRAs

Paper • 2405.11157 • Published May 18 • 25

SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization

Paper • 2405.11582 • Published May 19 • 12

upvoted a paper 8 months ago

TnT-LLM: Text Mining at Scale with Large Language Models

Paper • 2403.12173 • Published Mar 18 • 19

Jason Wolosonovich

AI & ML interests

Organizations

wolosonovich's activity

HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems

Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free

StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization

Large Language Models as Markov Chains

Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts

OLMoE: Open Mixture-of-Experts Language Models

dstack: Your LLM Launchpad - From Fine-Tuning to Serving, Simplified

Welcome FalconMamba: The first strong attention-free 7B model

CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases

Improving Text Embeddings for Smaller Language Models Using Contrastive Fine-tuning

Docmatix - a huge dataset for Document Visual Question Answering

E5-V: Universal Embeddings with Multimodal Large Language Models

SmolLM - blazingly fast and remarkably powerful

SpreadsheetLLM: Encoding Spreadsheets for Large Language Models

Is It Really Long Context if All You Need Is Retrieval? Towards Genuinely Difficult Long Context NLP

GEB-1.3B: Open Lightweight Large Language Model

Block Transformer: Global-to-Local Language Modeling for Fast Inference

Towards Modular LLMs by Building and Reusing a Library of LoRAs

SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization

TnT-LLM: Text Mining at Scale with Large Language Models