Simon Lupart

slupart

https://simonlupart.github.io/

AI & ML interests

My research mainly focuses on IR and conversational AI, working on distribution shifts, adversarial training, Large Language Models (LLMs) and Retrieval Augmented Generation (RAG).

Recent Activity

liked a dataset about 12 hours ago

slupart/chatr1-convqa-all

updated a collection about 14 hours ago

ChatR1

updated a dataset about 14 hours ago

slupart/chatr1-convqa-all

View all activity

Organizations

upvoted a paper 3 days ago

ChatR1: Reinforcement Learning for Conversational Reasoning and Retrieval Augmented Question Answering

Paper • 2510.13312 • Published Oct 15, 2025 • 1

upvoted a paper 6 days ago

Revisiting Text Ranking in Deep Research

Paper • 2602.21456 • Published Feb 25 • 7

upvoted a changelog 7 days ago

Hugging Face Changelog

Agent Traces on the Hub

8 days ago

• 98

upvoted a collection 13 days ago

Gemma 4

Collection

Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B. • 28 items • Updated 4 days ago • 139

upvoted an article 20 days ago

Article

Training and Finetuning Sparse Embedding Models with Sentence Transformers v5

Jul 1, 2025

•

137

upvoted a paper 22 days ago

On the Challenges and Opportunities of Learned Sparse Retrieval for Code

Paper • 2603.22008 • Published 23 days ago • 2

upvoted a collection 23 days ago

Splade-Code

Collection

Learned Sparse Retrieval Models for Code • 3 items • Updated 23 days ago • 4

upvoted an article about 2 months ago

Article

PISCO-OSCAR: embeddings for efficient Retrieval-Augmented Generation

Jun 18, 2025

•

upvoted 2 collections 8 months ago

QReCC

Collection

QReCC (Question Rewriting in Conversational Context) for passage retrieval and QA • 2 items • Updated Aug 25, 2025 • 1

gpt-oss

Collection

Open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. • 2 items • Updated Aug 7, 2025 • 430

upvoted a collection 11 months ago

Amharic Text Embedding Models

Collection

Text Embedding and ColBERT models based on Amharic RoBERTa and BERT for Amharic passage retrieval • 10 items • Updated Jun 11, 2025 • 6

upvoted a paper 11 months ago

Phi-4-reasoning Technical Report

Paper • 2504.21318 • Published Apr 30, 2025 • 55

upvoted a collection 11 months ago

DDRO-Generative-Document-Retrieval

Collection

Step-3 DDRO optimized checkpoints (final policy) + accompanying datasets/artifacts (docIDs, pseudo-queries, testsets) to reproduce the paper. • 8 items • Updated Dec 16, 2025 • 1

upvoted a paper 12 months ago

DiSCo Meets LLMs: A Unified Approach for Sparse Retrieval and Contextual Distillation in Conversational Search

Paper • 2410.14609 • Published Oct 18, 2024 • 1

upvoted 2 collections 12 months ago

SPLADE Conversational

Collection

Collection of the SIGIR 2025 full paper: DiSCo: LLM Knowledge Distillation for Efficient Sparse Retrieval in Conversational Search • 14 items • Updated about 14 hours ago • 3

SPLADE

Collection

Our SPLADE models • 4 items • Updated Jun 28, 2024 • 7

upvoted a paper over 1 year ago

DyVo: Dynamic Vocabularies for Learned Sparse Retrieval with Entities

Paper • 2410.07722 • Published Oct 10, 2024 • 15

Simon Lupart

AI & ML interests

Recent Activity

Organizations

slupart's activity

Agent Traces on the Hub

Training and Finetuning Sparse Embedding Models with Sentence Transformers v5

PISCO-OSCAR: embeddings for efficient Retrieval-Augmented Generation