Image de couverture de livre

Distributional Surgery for Language Model Activations

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Nguyen, Bao, Nguyen, Binh, Nguyen, Duy, Nguyen, Viet Anh
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Computation and Language Optimization and Control
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Task-driven Layerwise Additive Activation Intervention
par: Nguyen, Hieu Trung, et autres
Publié: (2025)

Provably data-driven projection method for quadratic programming
par: Nguyen, Anh Tuan, et autres
Publié: (2025)

Coverage-Validity-Aware Algorithmic Recourse
par: Bui, Ngoc, et autres
Publié: (2023)

SCOPE: Spectral Concentration by Distributionally Robust Joint Covariance-Precision Estimation
par: Chen, Renjie, et autres
Publié: (2025)

A Geometric Unification of Distributionally Robust Covariance Estimators: Shrinking the Spectrum by Inflating the Ambiguity Set
par: Yue, Man-Chung, et autres
Publié: (2024)

Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learning
par: Kuhn, Daniel, et autres
Publié: (2019)

Selective Ambulance Dispatch Under Contextual Travel-Time Uncertainty
par: Lin, Zikun, et autres
Publié: (2026)

Bellman Optimal Stepsize Straightening of Flow-Matching Models
par: Nguyen, Bao, et autres
Publié: (2023)

Structured Pruning for Diverse Best-of-N Reasoning Optimization
par: Nguyen, Hieu Trung, et autres
Publié: (2025)

A Hyper-Transformer model for Controllable Pareto Front Learning with Split Feasibility Constraints
par: Tuan, Tran Anh, et autres
Publié: (2024)

HUANet: Hard-Constrained Unrolled ADMM for Constrained Convex Optimization
par: Tran, Trinh, et autres
Publié: (2026)

Reasoning Planning for Language Models
par: Nguyen, Bao, et autres
Publié: (2025)

Tight Robustness Certificates and Wasserstein Distributional Attacks for Deep Neural Networks
par: Le, Bach C., et autres
Publié: (2025)

Does Continued Pretraining on a Learner Corpus Improve Automated Essay Scoring on English Proficiency Tests? Evidence from EFCAMDAT
par: Nguyen, Duy Anh
Publié: (2026)

Lean and Mean Adaptive Optimization via Subset-Norm and Subspace-Momentum with Convergence Guarantees
par: Nguyen, Thien Hang, et autres
Publié: (2024)

Proactive DP: A Multple Target Optimization Framework for DP-SGD
par: van Dijk, Marten, et autres
Publié: (2021)

How to Set $β_1, β_2$ in Adam: An Online Learning Perspective
par: Nguyen, Quan
Publié: (2025)

On Unbalanced Optimal Transport: Gradient Methods, Sparsity and Approximation Error
par: Nguyen, Quang Minh, et autres
Publié: (2022)

Generative Conditional Distributions by Neural (Entropic) Optimal Transport
par: Nguyen, Bao, et autres
Publié: (2024)

Semidefinite Relaxations of the Gromov-Wasserstein Distance
par: Chen, Junyu, et autres
Publié: (2023)

Decentralized Federated Learning with Gradient Tracking over Time-Varying Directed Networks
par: Nguyen, Duong Thuy Anh, et autres
Publié: (2024)

Cost-Adaptive Recourse Recommendation by Adaptive Preference Elicitation
par: Nguyen, Duy, et autres
Publié: (2024)

Adjusted Shuffling SARAH: Advancing Complexity Analysis via Dynamic Gradient Weighting
par: Nguyen, Duc Toan, et autres
Publié: (2025)

Gap Safe Screening Rules for Fast Training of Robust Support Vector Machines under Feature Noise
par: Nguyen, Tan-Hau, et autres
Publié: (2026)

A Novel Approach in Solving Stochastic Generalized Linear Regression via Nonconvex Programming
par: Anh, Vu Duc, et autres
Publié: (2024)

Adaptive multi-gradient methods for quasiconvex vector optimization and applications to multi-task learning
par: Minh, Nguyen Anh, et autres
Publié: (2024)

Efficient Online Large-Margin Classification via Dual Certificates
par: Ho-Nguyen, Nam, et autres
Publié: (2025)

Robustifying Conditional Portfolio Decisions via Optimal Transport
par: Nguyen, Viet Anh, et autres
Publié: (2021)

Optimizing Stochastic Gradient Push under Broadcast Communications
par: Nguyen, Tuan, et autres
Publié: (2026)

Controllable Expensive Multi-objective Learning with Warm-starting Bayesian Optimization
par: Nguyen, Quang-Huy, et autres
Publié: (2023)

Boolean Variation and Boolean Logic BackPropagation
par: Nguyen, Van Minh
Publié: (2023)

FSNet: Feasibility-Seeking Neural Network for Constrained Optimization with Guarantees
par: Nguyen, Hoang T., et autres
Publié: (2025)

Nash Equilibrium and Minimax Theorems via Variational Tools of Convex Analysis
par: Bao, Nguyen Xuan Duy, et autres
Publié: (2024)

When In-Distribution Gains Fail: Evaluating Weak-to-Strong Reward Models under Preference Shift
par: Le, Khoi, et autres
Publié: (2026)

Adaptive Rollout Allocation for Online Reinforcement Learning with Verifiable Rewards
par: Nguyen, Hieu Trung, et autres
Publié: (2026)

Don't Read Everything: A Curvature-Conditioned Query for Linear Attention
par: Le, Dong, et autres
Publié: (2026)

VFOG: Variance-Reduced Fast Optimistic Gradient Methods for a Class of Nonmonotone Generalized Equations
par: Tran-Dinh, Quoc, et autres
Publié: (2025)

Fréchet Regression on the Bures-Wasserstein Manifold
par: Nguyen, Duc Toan, et autres
Publié: (2026)

Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models
par: Kunstner, Frederik, et autres
Publié: (2024)

Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training
par: Liu, Hong, et autres
Publié: (2023)