Beyond Activation Alignment: The Geometry of Neural Sensitivity
Fuente:
arXiv
Saved in:
| Main Authors: | Yavari, Amirhossein, Esfahlani, Farnaz Zamani |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
Convolutional versus Dense Neural Networks: Comparing the Two Neural Networks Performance in Predicting Building Operational Energy Use Based on the Building Shape
by: Nazari, Farnaz, et al.
Published: (2021)
by: Nazari, Farnaz, et al.
Published: (2021)
Temporal Alignment of Time Sensitive Facts with Activation Engineering
by: Govindan, Sanjay, et al.
Published: (2025)
by: Govindan, Sanjay, et al.
Published: (2025)
Neural Prior Estimation: Learning Class Priors from Latent Representations
by: Yavari, Masoud, et al.
Published: (2026)
by: Yavari, Masoud, et al.
Published: (2026)
Relative Geometry of Neural Forecasters: Linking Accuracy and Alignment in Learned Latent Geometry
by: Kucukahmetler, Deniz, et al.
Published: (2026)
by: Kucukahmetler, Deniz, et al.
Published: (2026)
Hyperbolic Graph Neural Networks Under the Microscope: The Role of Geometry-Task Alignment
by: Naddeo, Dionisia, et al.
Published: (2026)
by: Naddeo, Dionisia, et al.
Published: (2026)
ASEHybrid: When Geometry Matters Beyond Homophily in Graph Neural Networks
by: Manir, Shalima Binta, et al.
Published: (2026)
by: Manir, Shalima Binta, et al.
Published: (2026)
Beyond Morphology: Quantifying the Diagnostic Power of Color Features in Cancer Classification
by: Kheiri, Farnaz, et al.
Published: (2026)
by: Kheiri, Farnaz, et al.
Published: (2026)
Beyond ReLU: How Activations Affect Neural Kernels and Random Wide Networks
by: Holzmüller, David, et al.
Published: (2025)
by: Holzmüller, David, et al.
Published: (2025)
Differentiable Autoencoding Neural Operator for Interpretable and Integrable Latent Space Modeling
by: Viknesh, Siva, et al.
Published: (2025)
by: Viknesh, Siva, et al.
Published: (2025)
MetaSort: An Accelerated Approach for Non-uniform Compression and Few-shot Classification of Neural Spike Waveforms
by: Meyer, Luca M., et al.
Published: (2026)
by: Meyer, Luca M., et al.
Published: (2026)
FIRM: Federated In-client Regularized Multi-objective Alignment for Large Language Models
by: Nourzad, Fatemeh, et al.
Published: (2025)
by: Nourzad, Fatemeh, et al.
Published: (2025)
Guided Manifold Alignment with Geometry-Regularized Twin Autoencoders
by: Rhodes, Jake S., et al.
Published: (2025)
by: Rhodes, Jake S., et al.
Published: (2025)
Exact Attention Sensitivity and the Geometry of Transformer Stability
by: Emadi, Seyed Morteza
Published: (2026)
by: Emadi, Seyed Morteza
Published: (2026)
Robustness Certificates for Neural Networks against Adversarial Attacks
by: Taheri, Sara, et al.
Published: (2025)
by: Taheri, Sara, et al.
Published: (2025)
Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations
by: Sartor, Davide, et al.
Published: (2025)
by: Sartor, Davide, et al.
Published: (2025)
Transfer Learning for Control Systems via Neural Simulation Relations
by: Nadali, Alireza, et al.
Published: (2024)
by: Nadali, Alireza, et al.
Published: (2024)
Graph-Conditioned Mixture of Graph Neural Network Experts for Traffic Forecasting
by: Ghaffari, Amirhossein, et al.
Published: (2026)
by: Ghaffari, Amirhossein, et al.
Published: (2026)
SLE-FNO: Single-Layer Extensions for Task-Agnostic Continual Learning in Fourier Neural Operators
by: Elhadidy, Mahmoud, et al.
Published: (2026)
by: Elhadidy, Mahmoud, et al.
Published: (2026)
Semiring Activation in Neural Networks
by: Smets, Bart M. N., et al.
Published: (2024)
by: Smets, Bart M. N., et al.
Published: (2024)
Towards Neural Architecture Search for Transfer Learning in 6G Networks
by: Orucu, Adam, et al.
Published: (2024)
by: Orucu, Adam, et al.
Published: (2024)
Neural Probabilistic Amplitude Shaping for Nonlinear Fiber Channels
by: Askari, Mohammad Taha, et al.
Published: (2026)
by: Askari, Mohammad Taha, et al.
Published: (2026)
Revisiting Robustness for LLM Safety Alignment via Selective Geometry Control
by: Yang, Yonghui, et al.
Published: (2026)
by: Yang, Yonghui, et al.
Published: (2026)
Adaptive Weighted LSSVM for Multi-View Classification
by: Lighvan, Farnaz Faramarzi, et al.
Published: (2025)
by: Lighvan, Farnaz Faramarzi, et al.
Published: (2025)
Beyond RLHF: A Unified Theoretical Framework of Alignment
by: Yun, Jihun, et al.
Published: (2025)
by: Yun, Jihun, et al.
Published: (2025)
From Data Leak to Secret Misses: The Impact of Data Leakage on Secret Detection Models
by: Soltaniani, Farnaz, et al.
Published: (2026)
by: Soltaniani, Farnaz, et al.
Published: (2026)
BCAmirs at SemEval-2024 Task 4: Beyond Words: A Multimodal and Multilingual Exploration of Persuasion in Memes
by: Abaskohi, Amirhossein, et al.
Published: (2024)
by: Abaskohi, Amirhossein, et al.
Published: (2024)
GSVD for Geometry-Grounded Dataset Comparison: An Alignment Angle Is All You Need
by: Marques, Eduarda de Souza, et al.
Published: (2026)
by: Marques, Eduarda de Souza, et al.
Published: (2026)
Learning Neural Networks with Sparse Activations
by: Awasthi, Pranjal, et al.
Published: (2024)
by: Awasthi, Pranjal, et al.
Published: (2024)
RVPO: Risk-Sensitive Alignment via Variance Regularization
by: Montero, Ivan, et al.
Published: (2026)
by: Montero, Ivan, et al.
Published: (2026)
Beyond Neural Incompatibility: Cross-Scale Knowledge Transfer in Language Models through Latent Semantic Alignment
by: Gu, Jian, et al.
Published: (2025)
by: Gu, Jian, et al.
Published: (2025)
EdgeCodec: Onboard Lightweight High Fidelity Neural Compressor with Residual Vector Quantization
by: Hodo, Benjamin, et al.
Published: (2025)
by: Hodo, Benjamin, et al.
Published: (2025)
Cumulative-Goodness Free-Riding in Forward-Forward Networks: Real, Repairable, but Not Accuracy-Dominant
by: Yousefiramandi, Amirhossein
Published: (2026)
by: Yousefiramandi, Amirhossein
Published: (2026)
Beyond Binary Preferences: A Principled Framework for Reward Modeling with Ordinal Feedback
by: Afsharrad, Amirhossein, et al.
Published: (2026)
by: Afsharrad, Amirhossein, et al.
Published: (2026)
Exploring Differential Geometry in Neural Implicits
by: Novello, Tiago, et al.
Published: (2022)
by: Novello, Tiago, et al.
Published: (2022)
Transfer Learning for Assessing Heavy Metal Pollution in Seaports Sediments
by: Lai, Tin, et al.
Published: (2025)
by: Lai, Tin, et al.
Published: (2025)
Edge Caching Optimization with PPO and Transfer Learning for Dynamic Environments
by: Niknia, Farnaz, et al.
Published: (2024)
by: Niknia, Farnaz, et al.
Published: (2024)
MGDA-Decoupled: Geometry-Aware Multi-Objective Optimisation for DPO-based LLM Alignment
by: Vári-Kakas, Andor, et al.
Published: (2026)
by: Vári-Kakas, Andor, et al.
Published: (2026)
Spherical Steering: Geometry-Aware Activation Rotation for Language Models
by: You, Zejia, et al.
Published: (2026)
by: You, Zejia, et al.
Published: (2026)
The Geometry of Alignment Collapse: When Fine-Tuning Breaks Safety
by: Springer, Max, et al.
Published: (2026)
by: Springer, Max, et al.
Published: (2026)
Latent Geometry Beyond Search: Amortizing Planning in World Models
by: Nguyen, Hoang, et al.
Published: (2026)
by: Nguyen, Hoang, et al.
Published: (2026)
Similar Items
-
Convolutional versus Dense Neural Networks: Comparing the Two Neural Networks Performance in Predicting Building Operational Energy Use Based on the Building Shape
by: Nazari, Farnaz, et al.
Published: (2021) -
Temporal Alignment of Time Sensitive Facts with Activation Engineering
by: Govindan, Sanjay, et al.
Published: (2025) -
Neural Prior Estimation: Learning Class Priors from Latent Representations
by: Yavari, Masoud, et al.
Published: (2026) -
Relative Geometry of Neural Forecasters: Linking Accuracy and Alignment in Learned Latent Geometry
by: Kucukahmetler, Deniz, et al.
Published: (2026) -
Hyperbolic Graph Neural Networks Under the Microscope: The Role of Geometry-Task Alignment
by: Naddeo, Dionisia, et al.
Published: (2026)