Adam Kovacs's picture

Open to Collab

Adam Kovacs PRO

adaamko

·

AI & ML interests

Explainable AI, rule-based models, hallucination detection, fact-checking LLMs

Recent Activity

updated a model 1 day ago

KRLabsOrg/squeez-2b

liked a model 1 day ago

KRLabsOrg/verbatim-rag-modern-bert-v2

updated a model 1 day ago

KRLabsOrg/verbatim-rag-modern-bert-v2

View all activity

Organizations

upvoted 2 articles 12 days ago

Article

Squeez: Task-Conditioned Tool-Output Pruning for Coding Agents

18 days ago

•

2

Article

Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers

13 days ago

•

65

upvoted an article 19 days ago

Article

Multimodal Embedding & Reranker Models with Sentence Transformers

20 days ago

•

52

upvoted a paper 20 days ago

Squeez: Task-Conditioned Tool-Output Pruning for Coding Agents

Paper • 2604.04979 • Published 25 days ago • 10

upvoted an article 20 days ago

Article

Welcome Gemma 4: Frontier multimodal intelligence on device

+5

27 days ago

•

882

upvoted 2 articles 3 months ago

Article

How We Built a Semantic Highlight Model To Save Token Cost for RAG

Jan 15

•

67

Article

🥃 Distilling Tiny Embeddings

Jan 10

•

22

upvoted an article 4 months ago

Article

Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval

+1

Mar 22, 2024

•

131

upvoted 2 papers 6 months ago

When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA

Paper • 2510.04849 • Published Oct 6, 2025 • 117

Fantastic (small) Retrievers and How to Train Them: mxbai-edge-colbert-v0 Tech Report

Paper • 2510.14880 • Published Oct 16, 2025 • 19

upvoted an article 7 months ago

Article

Granite Embedding R2: Setting New Standards for Enterprise Retrieval

Oct 14, 2025

•

16

upvoted a paper 8 months ago

mmBERT: A Modern Multilingual Encoder with Annealed Language Learning

Paper • 2509.06888 • Published Sep 8, 2025 • 15

upvoted 2 articles 8 months ago

Article

mmBERT: ModernBERT goes Multilingual

+4

Sep 9, 2025

•

145

Article

Welcome EmbeddingGemma, Google's new efficient embedding model

+4

Sep 4, 2025

•

273

upvoted 2 collections 8 months ago

Medical and Scientific Literature Models

Models for working with medical and scientific literature. • 17 items • Updated 22 minutes ago • 12

Hallucination detection

Trained ModernBERT (base and large) for detection hallucinations in LLM responses. The models are trained as token classifications. • 4 items • Updated May 18, 2025 • 19

upvoted an article 8 months ago

Article

Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications

Aug 29, 2025

•

27

upvoted a collection 8 months ago

TinyLettuce

This Collection contains our small, Ettin-encoder (https://arxiv.org/abs/2507.11412) based models trained on synthetic and RagTruth data. • 6 items • Updated Aug 31, 2025 • 4

upvoted an article 8 months ago

Article

🥬 TinyLettuce: Efficient Hallucination Detection with 17–68M Encoders

Aug 31, 2025

•

16

upvoted a collection 9 months ago

Turkish Hallucination Detection Models

10 items • Updated Mar 2 • 6