Alessio Miaschi

alemiaschi

·

https://alemiaschi.github.io/

AI & ML interests

Analysis and interpretability of small- and large-scale LMs

Recent Activity

liked a model about 9 hours ago

openeurollm/prelude

upvoted a paper 25 days ago

Parts-of-Speech as Emergent Categories in SAE Latent Space

updated a Space about 1 month ago

cruciverb-it/README

View all activity

Organizations

upvoted a paper 25 days ago

Parts-of-Speech as Emergent Categories in SAE Latent Space

Paper • 2609.29362 • Published 30 days ago • 19

upvoted an article 3 months ago

Article

J-Space: Yet Another LLM Mind Reader?

dlouapre

•

Jul 13

• 44

upvoted a paper 4 months ago

What Intermediate Layers Know: Detecting Jailbreaks from Entropy Dynamics

Paper • 2606.25182 • Published Jun 23 • 5

upvoted a collection 6 months ago

Qwen3.5-text-only

Text-only versions of Qwen-3.5 without the vision encoders for a smaller memory and storage footprint. • 4 items • Updated Jun 5 • 15

upvoted a collection 8 months ago

Qwen3.5

Qwen3.5 is Qwen's new model family including Qwen3.5 Small: 0.8B, 2B, 4B, 9B and Qwen3.5 Medium: 35B-A3B, 27B, 122B-A10B and 397B-A17B. • 25 items • Updated Aug 26 • 167

upvoted a paper 8 months ago

Agents of Chaos

Paper • 2602.20021 • Published Feb 23 • 36

upvoted an article 10 months ago

Article

EuroLLM-22B

eurollm-team

•

Dec 14, 2025

• 56

upvoted a paper 12 months ago

Language Models are Injective and Hence Invertible

Paper • 2510.15511 • Published Oct 17, 2025 • 70

upvoted 2 papers over 1 year ago

Beyond Correlation: Interpretable Evaluation of Machine Translation Metrics

Paper • 2410.05183 • Published Oct 7, 2024 • 1

Right Answer, Wrong Score: Uncovering the Inconsistencies of LLM Evaluation in Multiple-Choice Question Answering

Paper • 2503.14996 • Published Mar 19, 2025 • 3

upvoted an article over 1 year ago

Article

Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders

thomwolf, matthieu-lapeyre

•

Jul 9, 2025

• 817

upvoted a collection over 1 year ago

Stress-Testing MGT Detecors via Stylistic Alignment

Dataset and Models for the ACL 2025 paper "Stress-testing Machine Generated Text Detection: Shifting Language Models Writing Style to Fool Detectors" • 10 items • Updated Jul 4, 2025 • 1

upvoted 2 papers over 1 year ago

Decomposing MLP Activations into Interpretable Features via Semi-Nonnegative Matrix Factorization

Paper • 2506.10920 • Published Jun 12, 2025 • 5

Stress-testing Machine Generated Text Detection: Shifting Language Models Writing Style to Fool Detectors

Paper • 2505.24523 • Published May 30, 2025 • 10

upvoted a collection over 1 year ago

Evaluating Lexical Proficiency in Neural Language Models

Public collection for our paper: "Evaluating Lexical Proficiency in Neural Language Models", C. Ciaccio, A. Miaschi, F. Dell'Orletta (ACL 2025) • 5 items • Updated May 26, 2025 • 2

upvoted 2 papers over 1 year ago

Steering Large Language Models for Machine Translation Personalization

Paper • 2505.16612 • Published May 22, 2025 • 6

ViPlan: A Benchmark for Visual Planning with Symbolic Predicates and Vision-Language Models

Paper • 2505.13180 • Published May 19, 2025 • 13

upvoted 3 collections over 1 year ago

EuroBERT

Scaling Multilingual Encoders for European Languages • 4 items • Updated Mar 10, 2025 • 15

Mistral-7B-v0.1-Adapted

5 items • Updated Jan 23, 2025 • 2

Gemma Neogenesis 💎🌍🇮🇹

Datasets and models for Neogenesis: Post-training recipe for improving Gemma 2 for a specific language. Notebook: https://t.ly/iuKdy • 12 items • Updated Oct 25, 2025 • 5