Copertina

Beyond Activation Alignment: The Geometry of Neural Sensitivity

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yavari, Amirhossein, Esfahlani, Farnaz Zamani
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Convolutional versus Dense Neural Networks: Comparing the Two Neural Networks Performance in Predicting Building Operational Energy Use Based on the Building Shape
di: Nazari, Farnaz, et al.
Pubblicazione: (2021)

Temporal Alignment of Time Sensitive Facts with Activation Engineering
di: Govindan, Sanjay, et al.
Pubblicazione: (2025)

Neural Prior Estimation: Learning Class Priors from Latent Representations
di: Yavari, Masoud, et al.
Pubblicazione: (2026)

Relative Geometry of Neural Forecasters: Linking Accuracy and Alignment in Learned Latent Geometry
di: Kucukahmetler, Deniz, et al.
Pubblicazione: (2026)

Hyperbolic Graph Neural Networks Under the Microscope: The Role of Geometry-Task Alignment
di: Naddeo, Dionisia, et al.
Pubblicazione: (2026)

ASEHybrid: When Geometry Matters Beyond Homophily in Graph Neural Networks
di: Manir, Shalima Binta, et al.
Pubblicazione: (2026)

Beyond Morphology: Quantifying the Diagnostic Power of Color Features in Cancer Classification
di: Kheiri, Farnaz, et al.
Pubblicazione: (2026)

Beyond ReLU: How Activations Affect Neural Kernels and Random Wide Networks
di: Holzmüller, David, et al.
Pubblicazione: (2025)

Differentiable Autoencoding Neural Operator for Interpretable and Integrable Latent Space Modeling
di: Viknesh, Siva, et al.
Pubblicazione: (2025)

MetaSort: An Accelerated Approach for Non-uniform Compression and Few-shot Classification of Neural Spike Waveforms
di: Meyer, Luca M., et al.
Pubblicazione: (2026)

FIRM: Federated In-client Regularized Multi-objective Alignment for Large Language Models
di: Nourzad, Fatemeh, et al.
Pubblicazione: (2025)

Guided Manifold Alignment with Geometry-Regularized Twin Autoencoders
di: Rhodes, Jake S., et al.
Pubblicazione: (2025)

Exact Attention Sensitivity and the Geometry of Transformer Stability
di: Emadi, Seyed Morteza
Pubblicazione: (2026)

Robustness Certificates for Neural Networks against Adversarial Attacks
di: Taheri, Sara, et al.
Pubblicazione: (2025)

Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations
di: Sartor, Davide, et al.
Pubblicazione: (2025)

Transfer Learning for Control Systems via Neural Simulation Relations
di: Nadali, Alireza, et al.
Pubblicazione: (2024)

Graph-Conditioned Mixture of Graph Neural Network Experts for Traffic Forecasting
di: Ghaffari, Amirhossein, et al.
Pubblicazione: (2026)

SLE-FNO: Single-Layer Extensions for Task-Agnostic Continual Learning in Fourier Neural Operators
di: Elhadidy, Mahmoud, et al.
Pubblicazione: (2026)

Semiring Activation in Neural Networks
di: Smets, Bart M. N., et al.
Pubblicazione: (2024)

Towards Neural Architecture Search for Transfer Learning in 6G Networks
di: Orucu, Adam, et al.
Pubblicazione: (2024)

Neural Probabilistic Amplitude Shaping for Nonlinear Fiber Channels
di: Askari, Mohammad Taha, et al.
Pubblicazione: (2026)

Revisiting Robustness for LLM Safety Alignment via Selective Geometry Control
di: Yang, Yonghui, et al.
Pubblicazione: (2026)

Adaptive Weighted LSSVM for Multi-View Classification
di: Lighvan, Farnaz Faramarzi, et al.
Pubblicazione: (2025)

Beyond RLHF: A Unified Theoretical Framework of Alignment
di: Yun, Jihun, et al.
Pubblicazione: (2025)

From Data Leak to Secret Misses: The Impact of Data Leakage on Secret Detection Models
di: Soltaniani, Farnaz, et al.
Pubblicazione: (2026)

BCAmirs at SemEval-2024 Task 4: Beyond Words: A Multimodal and Multilingual Exploration of Persuasion in Memes
di: Abaskohi, Amirhossein, et al.
Pubblicazione: (2024)

GSVD for Geometry-Grounded Dataset Comparison: An Alignment Angle Is All You Need
di: Marques, Eduarda de Souza, et al.
Pubblicazione: (2026)

Learning Neural Networks with Sparse Activations
di: Awasthi, Pranjal, et al.
Pubblicazione: (2024)

RVPO: Risk-Sensitive Alignment via Variance Regularization
di: Montero, Ivan, et al.
Pubblicazione: (2026)

Beyond Neural Incompatibility: Cross-Scale Knowledge Transfer in Language Models through Latent Semantic Alignment
di: Gu, Jian, et al.
Pubblicazione: (2025)

EdgeCodec: Onboard Lightweight High Fidelity Neural Compressor with Residual Vector Quantization
di: Hodo, Benjamin, et al.
Pubblicazione: (2025)

Cumulative-Goodness Free-Riding in Forward-Forward Networks: Real, Repairable, but Not Accuracy-Dominant
di: Yousefiramandi, Amirhossein
Pubblicazione: (2026)

Beyond Binary Preferences: A Principled Framework for Reward Modeling with Ordinal Feedback
di: Afsharrad, Amirhossein, et al.
Pubblicazione: (2026)

Exploring Differential Geometry in Neural Implicits
di: Novello, Tiago, et al.
Pubblicazione: (2022)

Transfer Learning for Assessing Heavy Metal Pollution in Seaports Sediments
di: Lai, Tin, et al.
Pubblicazione: (2025)

Edge Caching Optimization with PPO and Transfer Learning for Dynamic Environments
di: Niknia, Farnaz, et al.
Pubblicazione: (2024)

MGDA-Decoupled: Geometry-Aware Multi-Objective Optimisation for DPO-based LLM Alignment
di: Vári-Kakas, Andor, et al.
Pubblicazione: (2026)

Spherical Steering: Geometry-Aware Activation Rotation for Language Models
di: You, Zejia, et al.
Pubblicazione: (2026)

The Geometry of Alignment Collapse: When Fine-Tuning Breaks Safety
di: Springer, Max, et al.
Pubblicazione: (2026)

Latent Geometry Beyond Search: Amortizing Planning in World Models
di: Nguyen, Hoang, et al.
Pubblicazione: (2026)