ScienceRLM (ScienceRLM)

akariasai

authored a paper 2 months ago

OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs

Paper • 2411.14199 • Published Nov 21, 2024 • 30

jacquelinehe

authored a paper 2 months ago

OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs

Paper • 2411.14199 • Published Nov 21, 2024 • 30

akariasai

authored a paper 3 months ago

Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages

Paper • 2410.16153 • Published Oct 21, 2024 • 44

rulins

authored a paper 6 months ago

Scaling Retrieval-Based Language Models with a Trillion-Token Datastore

Paper • 2407.12854 • Published Jul 9, 2024 • 30

akariasai

authored a paper 6 months ago

Scaling Retrieval-Based Language Models with a Trillion-Token Datastore

Paper • 2407.12854 • Published Jul 9, 2024 • 30

rulins

authored a paper 11 months ago

Language models scale reliably with over-training and on downstream tasks

Paper • 2403.08540 • Published Mar 13, 2024 • 15

akariasai

authored 4 papers 11 months ago

Fine-grained Hallucination Detection and Editing for Language Models

Paper • 2401.06855 • Published Jan 12, 2024 • 4

When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories

Paper • 2212.10511 • Published Dec 20, 2022 • 1

Task-aware Retrieval with Instructions

Paper • 2211.09260 • Published Nov 16, 2022

XOR QA: Cross-lingual Open-Retrieval Question Answering

Paper • 2010.11856 • Published Oct 22, 2020

rulins

authored a paper 11 months ago

Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning

Paper • 2402.11690 • Published Feb 18, 2024 • 9

akariasai

authored a paper over 1 year ago

Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection

Paper • 2310.11511 • Published Oct 17, 2023 • 76

rulins

authored a paper over 1 year ago

VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use

Paper • 2308.06595 • Published Aug 12, 2023 • 6

ScienceRLM

AI & ML interests

ScienceRLM's activity

OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs

OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs

Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages

Scaling Retrieval-Based Language Models with a Trillion-Token Datastore

Scaling Retrieval-Based Language Models with a Trillion-Token Datastore

Language models scale reliably with over-training and on downstream tasks

Fine-grained Hallucination Detection and Editing for Language Models

When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories

Task-aware Retrieval with Instructions

XOR QA: Cross-lingual Open-Retrieval Question Answering

Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning

Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection

VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use

AI & ML interests

Team members 3

ScienceRLM's activity