Nandan Thakur's picture

Nandan Thakur

nthakur

·

https://thakur-nandan.github.io

AI & ML interests

NLP, IR, QA

Recent Activity

new activity 2 days ago

BeIR/cqadupstack-qrels:cqadupstack document collection

updated a dataset 3 days ago

BeIR/cqadupstack

published a dataset 3 days ago

BeIR/cqadupstack

View all activity

Organizations

upvoted a collection 10 days ago

ORBIT-v0.1

A collection of ORBIT training datasets and search agents • 4 items • Updated 10 days ago • 2

upvoted an article 11 days ago

Article

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

+7

Mar 10

•

124

upvoted a collection 18 days ago

Splade-Code

Learned Sparse Retrieval Models for Code • 3 items • Updated 19 days ago • 4

upvoted a collection about 1 month ago

🤏 Smol-Data

Tried and tested mixes for strong pretraining. Inspired by https://huggingface.co/blog/codelion/optimal-dataset-mixing • 14 items • Updated Mar 2 • 12

upvoted a paper about 2 months ago

RexBERT: Context Specialized Bidirectional Encoders for E-commerce

Paper • 2602.04605 • Published Feb 4 • 2

upvoted an article 2 months ago

Article

Nano-BEIR: A Multilingual Information Retrieval Benchmark with Quality-Enhanced Queries

Dec 22, 2025

•

9

upvoted 2 collections 2 months ago

Bharat-NanoBEIR: Indian Language Retrieval Benchmarks

NanoBEIR retrieval benchmarks translated into 22 Indian languages across 13 datasets. • 22 items • Updated Dec 13, 2025 • 5

Bharat-NanoBEIR

Indian Language Information Retrieval Dataset • 286 items • Updated Jan 26, 2025 • 2

upvoted a paper 4 months ago

M3DR: Towards Universal Multilingual Multimodal Document Retrieval

Paper • 2512.03514 • Published Dec 3, 2025 • 9

upvoted a collection 4 months 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 Dec 2, 2025 • 164

upvoted 2 articles 6 months ago

Article

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

Oct 20, 2025

•

38

Article

Introducing RTEB: A New Standard for Retrieval Evaluation

+4

Oct 1, 2025

•

140

upvoted a collection 7 months ago

EmbeddingGemma

3 items • Updated Mar 12 • 116

upvoted an article 7 months ago

Article

Welcome EmbeddingGemma, Google's new efficient embedding model

+4

Sep 4, 2025

•

273

upvoted a paper 8 months ago

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

Paper • 2508.06600 • Published Aug 8, 2025 • 42

upvoted an article 10 months ago

Article

Training and Finetuning Sparse Embedding Models with Sentence Transformers v5

Jul 1, 2025

•

137

upvoted a collection 10 months ago

Qwen3-Embedding

6 items • Updated Dec 31, 2025 • 155

upvoted a paper 11 months ago

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

Paper • 2505.16967 • Published May 22, 2025 • 24

upvoted 2 collections 11 months ago

RLHN Datasets

RLHN: Cleaned Training Datasets with False Negatives Identified & Relabeled as ground truth. • 5 items • Updated May 23, 2025 • 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, 2025 • 3