Image de couverture de livre

Language Models are Injective and Hence Invertible

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Nikolaou, Giorgos, Mencattini, Tommaso, Crisostomi, Donato, Santilli, Andrea, Panagakis, Yannis, Rodolà, Emanuele
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Mergenetic: a Simple Evolutionary Model Merging Library
par: Minut, Adrian Robert, et autres
Publié: (2025)

MERGE$^3$: Efficient Evolutionary Merging on Consumer-grade GPUs
par: Mencattini, Tommaso, et autres
Publié: (2025)

Multi-objective Evolutionary Merging Enables Efficient Reasoning Models
par: Iacobelli, Mario, et autres
Publié: (2026)

Model Merging Improves Zero-Shot Generalization in Bioacoustic Foundation Models
par: Marincione, Davide, et autres
Publié: (2025)

Model Merging: Foundations and Algorithms
par: Crisostomi, Donato
Publié: (2026)

Metric Based Few-Shot Graph Classification
par: Crisostomi, Donato, et autres
Publié: (2022)

ATM: Improving Model Merging by Alternating Tuning and Merging
par: Zhou, Luca, et autres
Publié: (2024)

Two-Scale Latent Dynamics for Recurrent-Depth Transformers
par: Pappone, Francesco, et autres
Publié: (2025)

On Task Vectors and Gradients
par: Zhou, Luca, et autres
Publié: (2025)

Multi-Way Representation Alignment
par: Achara, Akshit, et autres
Publié: (2026)

Implicit Inversion turns CLIP into a Decoder
par: D'Orazio, Antonio, et autres
Publié: (2025)

Preserving Privacy in Large Language Models: A Survey on Current Threats and Solutions
par: Miranda, Michele, et autres
Publié: (2024)

Communicating Sound Through Natural Language
par: Rossi, Emanuele, et autres
Publié: (2026)

Exploratory Causal Inference in SAEnce
par: Mencattini, Tommaso, et autres
Publié: (2025)

MASS: MoErging through Adaptive Subspace Selection
par: Crisostomi, Donato, et autres
Publié: (2025)

Accelerating Transformer Inference for Translation via Parallel Decoding
par: Santilli, Andrea, et autres
Publié: (2023)

$C^2M^3$: Cycle-Consistent Multi-Model Merging
par: Crisostomi, Donato, et autres
Publié: (2024)

LoopGen: Training-Free Loopable Music Generation
par: Marincione, Davide, et autres
Publié: (2025)

How Neural Losses Shape VAE Latents
par: Strano, Giorgio, et autres
Publié: (2026)

Metanetworks as Regulatory Operators: Learning to Edit for Requirement Compliance
par: Kalogeropoulos, Ioannis, et autres
Publié: (2025)

Scale Equivariant Graph Metanetworks
par: Kalogeropoulos, Ioannis, et autres
Publié: (2024)

Domain Elastic Transform: Bayesian Function Registration for High-Dimensional Scientific Data
par: Hirose, Osamu, et autres
Publié: (2026)

Exposing Hidden Biases in Text-to-Image Models via Automated Prompt Search
par: Plitsis, Manos, et autres
Publié: (2025)

Advancing Brainwave Modeling with a Codebook-Based Foundation Model
par: Barmpas, Konstantinos, et autres
Publié: (2025)

Are Large Brainwave Foundation Models Capable Yet? Insights from Fine-tuning
par: Lee, Na, et autres
Publié: (2025)

TOAST: Transformer Optimization using Adaptive and Simple Transformations
par: Cannistraci, Irene, et autres
Publié: (2024)

On the (Non) Injectivity of Piecewise Linear Janossy Pooling
par: Reshef, Ilai, et autres
Publié: (2025)

Membership and Dataset Inference Attacks on Large Audio Generative Models
par: Proboszcz, Jakub, et autres
Publié: (2025)

Task Singular Vectors: Reducing Task Interference in Model Merging
par: Gargiulo, Antonio Andrea, et autres
Publié: (2024)

Activation Patching for Interpretable Steering in Music Generation
par: Facchiano, Simone, et autres
Publié: (2025)

VINA: Variational Invertible Neural Architectures
par: Shekhar, Shubhanshu, et autres
Publié: (2026)

Can we ease the Injectivity Bottleneck on Lorentzian Manifolds for Graph Neural Networks?
par: Srinivasan, Srinitish, et autres
Publié: (2025)

Deploying Open-Source Large Language Models: A performance Analysis
par: Bendi-Ouis, Yannis, et autres
Publié: (2024)

Zero-Shot Quantization via Weight-Space Arithmetic
par: Solombrino, Daniele, et autres
Publié: (2026)

NeuroRVQ: Multi-Scale Biosignal Tokenization for Generative Foundation Models
par: Barmpas, Konstantinos, et autres
Publié: (2025)

Revisiting Uncertainty Quantification Evaluation in Language Models: Spurious Interactions with Response Length Bias Results
par: Santilli, Andrea, et autres
Publié: (2025)

This Probably Looks Exactly Like That: An Invertible Prototypical Network
par: Carmichael, Zachariah, et autres
Publié: (2024)

TART: Token-based Architecture Transformer for Neural Network Performance Prediction
par: He, Yannis Y.
Publié: (2025)

A survey on knowledge-enhanced multimodal learning
par: Lymperaiou, Maria, et autres
Publié: (2022)

ISR: Invertible Symbolic Regression
par: Tohme, Tony, et autres
Publié: (2024)