Sara Candussio

saracandu's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a dataset 6 days ago

saracandu/entropy-traces

Preview • Updated 6 days ago • 3.42k

updated a collection 15 days ago

🧙‍♂️ demistifying entropy-based token selection

Collection

1 item • Updated 15 days ago

published a dataset 20 days ago

saracandu/entropy-traces

Preview • Updated 6 days ago • 3.42k

updated a collection 25 days ago

🦜 a dialectic pipeline for improving LLMs robustness

Collection

master's thesis materials • 4 items • Updated 25 days ago

published a dataset 25 days ago

saracandu/wikihop_dataset

Viewer • Updated Jul 28, 2024 • 43.7k • 53

updated a collection 25 days ago

🦜 a dialectic pipeline for improving LLMs robustness

Collection

master's thesis materials • 4 items • Updated 25 days ago

published 4 datasets 25 days ago

saracandu/hotpotQA_nli

Viewer • Updated Aug 20, 2024 • 347 • 25

saracandu/msmarco_modified

Viewer • Updated May 9, 2024 • 82.3k • 29

saracandu/my_hotpotQA

Preview • Updated Jun 30, 2024 • 20

saracandu/my_wikihop

Viewer • Updated Jul 30, 2024 • 1k • 41

updated 2 collections 25 days ago

🔁 STLdec @ ECML-PKDD 2025

Collection

Materials for the paper "Bridging Logic and Learning: Decoding Temporal Logic Embeddings via Transformers" (Candussio et al.) @ ECML-PKDD 2025 • 13 items • Updated 25 days ago

⚗️​ distilling kernel into transformers

Collection

work-in-progress • 4 items • Updated 20 days ago

authored 3 papers 26 days ago

Bridging Logic and Learning: Decoding Temporal Logic Embeddings via Transformers

Paper • 2507.07808 • Published Jul 10, 2025

A Dialectic Pipeline for Improving LLM Robustness

Paper • 2601.20659 • Published Jan 28

Distilling Formal Logic into Neural Spaces: A Kernel Alignment Approach for Signal Temporal Logic

Paper • 2603.05198 • Published Mar 5

upvoted a collection 27 days ago

Gemma 3 - Reasoning/Thinking Models (incl uncensored)

Collection

Fine tunes (most uncensored) of Gemma3s to add reasoning/thinking. Increases output and image processing quality and general model metrics. • 18 items • Updated 14 days ago • 17

authored a paper about 1 month ago

RogueAI: A Reverse Turing Test for Detecting Licensed AI Deception in Dialogue

Paper • 2606.13310 • Published Jun 11

updated a dataset about 1 month ago

saracandu/olmo-activations

Viewer • Updated Jun 20 • 29.6k • 514