23 citations · 23 across the 7 of their papers we have counts for
9 papers
The Independence Prior of SAEs Fragments Visual Concepts
Tommaso Mencattini, Giorgos Nikolaou, Donato Crisostomi +4
Sparse Autoencoders (SAEs) decompose model activations into sparse combinations of interpretable dictionary atoms. Although SAEs are grounded in the Linear Representation Hypothesi…
Rubric-Calibrated Preferences: Cross-Query Calibration of LLM Judgments via Item Response Theory
Fabian David Schmidt, Donato Crisostomi, Carlos Lassance +1
Rerankers decide which documents users and LLMs see, yet their standard metric, nDCG, relies on human relevance labels that are costly, sparse, noisy, and discretely graded. As rer…
Steering Vectors are an Adversarial Attack Surface
Abzal Aidakhmetov, Donato Crisostomi, Tommaso Mencattini +3
Activation steering has become a popular way to control Large Language Model (LLM) behavior without fine-tuning. Since the technique is plug-and-play, users share datasets and prec…
Model Merging: Foundations and Algorithms
Donato Crisostomi
Modern deep learning usually treats models as separate artifacts: trained independently, specialized for particular purposes, and replaced when improved versions appear. This thesi…
Multi-objective Evolutionary Merging Enables Efficient Reasoning Models
Mario Iacobelli, Adrian Robert Minut, Tommaso Mencattini +4
Reasoning models achieve strong performance on complex problems by leveraging long chains of thought, but this deliberate reasoning incurs substantial inference-time cost. The Long…
Model Merging Improves Zero-Shot Generalization in Bioacoustic Foundation Models
Davide Marincione, Donato Crisostomi, Roberto Dessi +2
Foundation models capable of generalizing across species and tasks represent a promising new frontier in bioacoustics, with NatureLM being one of the most prominent examples. While…
STAGE: Stemmed Accompaniment Generation through Prefix-Based Conditioning
Giorgio Strano, Chiara Ballanti, Donato Crisostomi +3
Recent advances in generative models have made it possible to create high-quality, coherent music, with some systems delivering production-level output. Yet, most existing models f…
MASS: MoErging through Adaptive Subspace Selection
Donato Crisostomi, Alessandro Zirilli, Antonio Andrea Gargiulo +5
Model merging has recently emerged as a lightweight alternative to ensembling, combining multiple fine-tuned models into a single set of parameters with no additional training over…
Humanity's Last Exam
Long Phan, Alice Gatti, Ziwen Han +1168
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…