Ankush Chander's picture

19 37

Ankush Chander

Ankush-Chander

·

AI & ML interests

NLP on scientific literature, Personalised summarisation, neural NLP

Organizations

Ankush-Chander's activity

upvoted an article about 2 months ago

Article

Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval

Mar 22

• 36

upvoted a paper 3 months ago

Graph Neural Prompting with Large Language Models

Paper • 2309.15427 • Published Sep 27, 2023 • 1

upvoted 2 collections 3 months ago

Large Language models and Knowledge graphs

9 items • Updated Mar 4 • 2

Matryoshka Embedding Models

https://huggingface.co/blog/matryoshka • 12 items • Updated 9 days ago • 10

upvoted 2 papers 3 months ago

Efficient Estimation of Word Representations in Vector Space

Paper • 1301.3781 • Published Jan 16, 2013 • 6

Unifying Large Language Models and Knowledge Graphs: A Roadmap

Paper • 2306.08302 • Published Jun 14, 2023 • 4

upvoted 3 collections 3 months ago

graph_embeddings

11 items • Updated Mar 23 • 2

Research Lessons

understanding important lessons from machine learning research • 2 items • Updated Mar 23 • 2

Graph Reasoning

29 items • Updated Apr 9 • 5

upvoted 5 papers 4 months ago

LIMA: Less Is More for Alignment

Paper • 2305.11206 • Published May 18, 2023 • 18

SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing

Paper • 1808.06226 • Published Aug 19, 2018 • 1

Finetuned Language Models Are Zero-Shot Learners

Paper • 2109.01652 • Published Sep 3, 2021 • 2

LLaMA: Open and Efficient Foundation Language Models

Paper • 2302.13971 • Published Feb 27, 2023 • 11

Adapting Large Language Models via Reading Comprehension

Paper • 2309.09530 • Published Sep 18, 2023 • 69

upvoted a collection 4 months ago

Most influential papers in AI

4 items • Updated Nov 16, 2023 • 25

upvoted 2 papers 4 months ago

Universal Language Model Fine-tuning for Text Classification

Paper • 1801.06146 • Published Jan 18, 2018 • 6

FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

Paper • 2205.14135 • Published May 27, 2022 • 8

upvoted a collection 5 months ago

Datasets based on UltraFeedback

This collection contains some datasets created on top of UltraFeedback using Argilla for the dataset exploration and curation, sorted by release date. • 6 items • Updated Mar 19 • 10

upvoted a collection 6 months ago

Notus 7B v1

Notus 7B v1 models (DPO fine-tune of Zephyr SFT) and datasets used. More information at https://github.com/argilla-io/notus • 11 items • Updated Dec 28, 2023 • 17