41 50 27

Solomatin Roman

Samoed

AI & ML interests

None yet

Recent Activity

new activity about 5 hours ago

mteb/CodeFeedbackST:Improve dataset card with correct task category and paper link

upvoted a paper 1 day ago

Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA

updated a dataset 2 days ago

DeepPavlov/XRISAWOZ

View all activity

Organizations

Samoed's activity

upvoted a paper 1 day ago

Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA

Paper • 2505.21115 • Published 15 days ago • 111

upvoted a paper 16 days ago

Quartet: Native FP4 Training Can Be Optimal for Large Language Models

Paper • 2505.14669 • Published 21 days ago • 73

upvoted a paper about 1 month ago

ReasonIR: Training Retrievers for Reasoning Tasks

Paper • 2504.20595 • Published Apr 29 • 55

upvoted an article about 2 months ago

Article

MIEB: The Benchmark That Stress-Tests Image-Text Embeddings Like Never Before

and 2 others •

Apr 24

• 14

upvoted a collection about 2 months ago

USER2

Collection

Universal Sentence Encoder for Russian based on RuModernBERT, with support for context lengths up to 8,192 tokens and Matryoshka representation lear • 2 items • Updated Apr 18 • 4

upvoted a paper about 2 months ago

MIEB: Massive Image Embedding Benchmark

Paper • 2504.10471 • Published Apr 14 • 18

upvoted an article 3 months ago

Article

Training and Finetuning Reranker Models with Sentence Transformers v4

•

Mar 26

• 135

upvoted 6 papers 3 months ago

When Less is Enough: Adaptive Token Reduction for Efficient Image Representation

Paper • 2503.16660 • Published Mar 20 • 73

Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders

Paper • 2503.03601 • Published Mar 5 • 234

Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss

Paper • 2410.17243 • Published Oct 22, 2024 • 95

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Paper • 2502.14786 • Published Feb 20 • 145

Rank1: Test-Time Compute for Reranking in Information Retrieval

Paper • 2502.18418 • Published Feb 25 • 27

GHOST 2.0: generative high-fidelity one shot transfer of heads

Paper • 2502.18417 • Published Feb 25 • 67

upvoted 4 papers 4 months ago

LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers

Paper • 2502.15007 • Published Feb 20 • 175

upvoted an article 4 months ago

Article

Train 400x faster Static Embedding Models with Sentence Transformers

•

Jan 15

• 187

upvoted a paper 4 months ago

The Differences Between Direct Alignment Algorithms are a Blur

Paper • 2502.01237 • Published Feb 3 • 115

upvoted a collection 4 months ago

NanoBEIR 🍺

Collection

A collection of smaller versions of BEIR datasets with 50 queries and up to 10K documents each. • 13 items • Updated Sep 11, 2024 • 17