Nandan Thakur's picture

Nandan Thakur

nthakur

·

https://thakur-nandan.github.io

AI & ML interests

NLP, IR, QA

Recent Activity

updated a Space 4 days ago

rlhn/README

upvoted a collection 5 days ago

liked a model 11 days ago

rl-research/DR-Tulu-8B

View all activity

Organizations

upvoted a collection 5 days ago

Ministral 3

A collection of edge models, with Base, Instruct and Reasoning variants, in 3 different sizes: 3B, 8B and 14B. All with vision capabilities. • 9 items • Updated 5 days ago • 113

upvoted an article about 2 months ago

Article

Introducing MTEB v2: Evaluation of embedding and retrieval systems for more than just text

Oct 20

•

33

upvoted an article 2 months ago

Article

Introducing RTEB: A New Standard for Retrieval Evaluation

+4

Oct 1

•

128

upvoted a collection 3 months ago

EmbeddingGemma

3 items • Updated Sep 11 • 102

upvoted an article 3 months ago

Article

Welcome EmbeddingGemma, Google's new efficient embedding model

+4

Sep 4

•

263

upvoted a paper 4 months ago

BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent

Paper • 2508.06600 • Published Aug 8 • 41

upvoted an article 5 months ago

Article

Training and Finetuning Sparse Embedding Models with Sentence Transformers v5

Jul 1

•

130

upvoted a collection 6 months ago

Qwen3-Embedding

6 items • Updated Jul 21 • 138

upvoted a paper 7 months ago

Fixing Data That Hurts Performance: Cascading LLMs to Relabel Hard Negatives for Robust Information Retrieval

Paper • 2505.16967 • Published May 22 • 24

upvoted 2 collections 7 months ago

RLHN Datasets

RLHN: Cleaned Training Datasets with False Negatives Identified & Relabeled as ground truth. • 5 items • Updated May 23 • 4

Multilingual SFT & DPO Datasets

These SFT or DPO datasets were translated from English using the Mistral-7B-Instruct-v0.2 or taken from other sources. • 8 items • Updated Mar 31 • 3

upvoted a paper 8 months ago

FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents

Paper • 2504.13128 • Published Apr 17 • 7

upvoted a collection 8 months ago

Multimodal DSE Retrievers

A collection of DSE models for multimodal retrieval • 5 items • Updated Apr 15 • 15

upvoted 3 collections 9 months ago

🌐 NoMIRACL Dataset [EMNLP'24]

A collection of multilingual relevance assessment datasets. We also have SFT fine-tuned models (Mistral-7B & Llama-3 8B) • 7 items • Updated Mar 31 • 1

🏜️MIRAGE-Bench [NAACL'25]

Dataset Collection from the MIRAGE-Bench paper • 13 items • Updated Mar 31 • 2

DRAMA

A collection of small (sub-1B) multilingual dense retrievers that generalize well across a number of tasks and languages. • 3 items • Updated Feb 26 • 8

upvoted a paper 10 months ago

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Paper • 2501.12948 • Published Jan 22 • 429

upvoted a paper about 1 year ago

NoMIRACL: Knowing When You Don't Know for Robust Multilingual Retrieval-Augmented Generation

Paper • 2312.11361 • Published Dec 18, 2023 • 1

upvoted an article about 1 year ago

Article

Visually Multilingual: Introducing mcdse-2b

Oct 27, 2024

•

41

upvoted a paper over 1 year ago

MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark

Paper • 2406.01574 • Published Jun 3, 2024 • 51