Copertina

Layer-wise Linear Mode Connectivity

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Adilova, Linara, Andriushchenko, Maksym, Kamp, Michael, Fischer, Asja, Jaggi, Martin
Natura:	Preprint
Pubblicazione:	2023
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Landscaping Linear Mode Connectivity
di: Singh, Sidak Pal, et al.
Pubblicazione: (2024)

When Flatness Does (Not) Guarantee Adversarial Robustness
di: Walter, Nils Philipp, et al.
Pubblicazione: (2025)

The Uncanny Valley: Exploring Adversarial Robustness from a Flatness Perspective
di: Walter, Nils Philipp, et al.
Pubblicazione: (2024)

Flatness is Necessary, Neural Collapse is Not: Rethinking Generalization via Grokking
di: Han, Ting, et al.
Pubblicazione: (2025)

QuantSightBench: Evaluating LLM Quantitative Forecasting with Prediction Intervals
di: Qin, Jeremy, et al.
Pubblicazione: (2026)

Does Refusal Training in LLMs Generalize to the Past Tense?
di: Andriushchenko, Maksym, et al.
Pubblicazione: (2024)

Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections
di: Schmotz, David, et al.
Pubblicazione: (2025)

Fisher information flow in artificial neural networks
di: Weimar, Maximilian, et al.
Pubblicazione: (2025)

Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
di: Andriushchenko, Maksym, et al.
Pubblicazione: (2024)

Why Do We Need Weight Decay in Modern Deep Learning?
di: D'Angelo, Francesco, et al.
Pubblicazione: (2023)

Critical Influence of Overparameterization on Sharpness-aware Minimization
di: Shin, Sungbin, et al.
Pubblicazione: (2023)

Exploring Memorization and Copyright Violation in Frontier LLMs: A Study of the New York Times v. OpenAI 2023 Lawsuit
di: Freeman, Joshua, et al.
Pubblicazione: (2024)

Single-Model Attribution of Generative Models Through Final-Layer Inversion
di: Laszkiewicz, Mike, et al.
Pubblicazione: (2023)

Generalized Linear Mode Connectivity for Transformers
di: Theus, Alexander, et al.
Pubblicazione: (2025)

On the regularization of Wasserstein GANs
di: Petzka, Henning, et al.
Pubblicazione: (2017)

Connecting Independently Trained Modes via Layer-Wise Connectivity
di: Tian, Yongding, et al.
Pubblicazione: (2025)

Is In-Context Learning Sufficient for Instruction Following in LLMs?
di: Zhao, Hao, et al.
Pubblicazione: (2024)

Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
di: Schmotz, David, et al.
Pubblicazione: (2026)

Linear Mode Connectivity in Differentiable Tree Ensembles
di: Kanoh, Ryuichi, et al.
Pubblicazione: (2024)

On Linear Mode Connectivity of Mixture-of-Experts Architectures
di: Tran, Viet-Hoang, et al.
Pubblicazione: (2025)

Capability-Based Scaling Trends for LLM-Based Red-Teaming
di: Panfilov, Alexander, et al.
Pubblicazione: (2025)

Analyzing the Role of Permutation Invariance in Linear Mode Connectivity
di: Zhan, Keyao, et al.
Pubblicazione: (2025)

Linear Mode Connectivity in Sparse Neural Networks
di: McDermott, Luke, et al.
Pubblicazione: (2023)

Learning Sparse Codes with Entropy-Based ELBOs
di: Velychko, Dmytro, et al.
Pubblicazione: (2023)

Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents
di: Talokar, Nivya, et al.
Pubblicazione: (2026)

Theoretical Learning Performance of Graph Neural Networks: The Impact of Jumping Connections and Layer-wise Sparsification
di: Sun, Jiawei, et al.
Pubblicazione: (2025)

Comparative Study on Noise-Augmented Training and its Effect on Adversarial Robustness in ASR Systems
di: Pizzi, Karla, et al.
Pubblicazione: (2024)

Robustifying automatic speech recognition by extracting slowly varying features
di: Pizarro, Matías, et al.
Pubblicazione: (2021)

Precision-Varying Prediction (PVP): Robustifying ASR systems against adversarial attacks
di: Pizarro, Matías, et al.
Pubblicazione: (2026)

Proving Linear Mode Connectivity of Neural Networks via Optimal Transport
di: Ferbach, Damien, et al.
Pubblicazione: (2023)

DistriBlock: Identifying adversarial audio samples by leveraging characteristics of the output distribution
di: Pizarro, Matías, et al.
Pubblicazione: (2023)

Integrating uncertainty quantification into randomized smoothing based robustness guarantees
di: Däubener, Sina, et al.
Pubblicazione: (2024)

Layer-wise Derivative Controlled Networks
di: Martnishn, Rowan, et al.
Pubblicazione: (2026)

Linear Mode Connectivity under Data Shifts for Deep Ensembles of Image Classifiers
di: Hepburn, C., et al.
Pubblicazione: (2025)

Impact of Bottleneck Layers and Skip Connections on the Generalization of Linear Denoising Autoencoders
di: Ham, Jonghyun, et al.
Pubblicazione: (2025)

Do We Really Need Permutations? Impact of Model Width on Linear Mode Connectivity
di: Ito, Akira, et al.
Pubblicazione: (2025)

Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks
di: Kosson, Atli, et al.
Pubblicazione: (2023)

HyperINF: Unleashing the HyperPower of the Schulz's Method for Data Influence Estimation
di: Zhou, Xinyu, et al.
Pubblicazione: (2024)

Analyzing & Reducing the Need for Learning Rate Warmup in GPT Training
di: Kosson, Atli, et al.
Pubblicazione: (2024)

Benchmarking Optimizers for Large Language Model Pretraining
di: Semenov, Andrei, et al.
Pubblicazione: (2025)