Copertina

Spectral Compact Training: Pre-Training Large Language Models via Permanent Truncated SVD and Stiefel QR Retraction

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Kohlberger, Björn Roman
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence I.2.6
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Large Language Models as Attribution Regularizers for Efficient Model Training
di: Vukadin, Davor, et al.
Pubblicazione: (2025)

Post-Training Probability Manifold Correction via Structured SVD Pruning and Self-Referential Distillation
di: Flouro, Aaron R., et al.
Pubblicazione: (2026)

Architectural Proprioception in State Space Models: Thermodynamic Training Induces Anticipatory Halt Detection
di: Noon, Jay
Pubblicazione: (2026)

Painless Activation Steering: An Automated, Lightweight Approach for Post-Training Large Language Models
di: Cui, Sasha, et al.
Pubblicazione: (2025)

Training Artificial Neural Networks by Coordinate Search Algorithm
di: Rokhsatyazdi, Ehsan, et al.
Pubblicazione: (2024)

Deep Memory Search: A Metaheuristic Approach for Optimizing Heuristic Search
di: Hedar, Abdel-Rahman, et al.
Pubblicazione: (2024)

Entropy-Based Measurement of Value Drift and Alignment Work in Large Language Models
di: Fadli, Samih
Pubblicazione: (2025)

The Geometry of Thought: How Scale Restructures Reasoning In Large Language Models
di: Anderson, Samuel Cyrenius
Pubblicazione: (2026)

How Does Unfaithful Reasoning Emerge from Autoregressive Training? A Study of Synthetic Experiments
di: Wang, Fuxin, et al.
Pubblicazione: (2026)

On the Role of Pre-trained Embeddings in Binary Code Analysis
di: Maier, Alwin, et al.
Pubblicazione: (2025)

Reasoning Large Language Model Errors Arise from Hallucinating Critical Problem Features
di: Heyman, Alex, et al.
Pubblicazione: (2025)

The Anti-Ouroboros Effect: Emergent Resilience in Large Language Models from Recursive Selective Feedback
di: Adapala, Sai Teja Reddy
Pubblicazione: (2025)

Approximate Domain Unlearning for Vision-Language Models
di: Kawamura, Kodai, et al.
Pubblicazione: (2025)

Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement
di: Actor, Jonas A., et al.
Pubblicazione: (2025)

Combining Trained Models in Reinforcement Learning
di: Patil, Ujjwal, et al.
Pubblicazione: (2026)

Scaling Offline RL via Efficient and Expressive Shortcut Models
di: Espinosa-Dice, Nicolas, et al.
Pubblicazione: (2025)

Self-Training Doesn't Flatten Language -- It Restructures It: Surface Markers Amplify While Deep Syntax Dies
di: Liu, Ming
Pubblicazione: (2026)

Model Fusion via Retrofitting
di: Luenam, Phoomraphee, et al.
Pubblicazione: (2025)

Physics-Informed Spectral Modeling for Hyperspectral Imaging
di: Gawrysiak, Zuzanna, et al.
Pubblicazione: (2025)

Dynamical Priors as a Training Objective in Reinforcement Learning
di: Subaharan, Sukesh
Pubblicazione: (2026)

Better Schedules for Low Precision Training of Deep Neural Networks
di: Wolfe, Cameron R., et al.
Pubblicazione: (2024)

Multi-Task Reinforcement Learning with Language-Encoded Gated Policy Networks
di: Arora, Rushiv
Pubblicazione: (2025)

Democratic Preference Alignment via Sortition-Weighted RLHF
di: Sana, Suvadip, et al.
Pubblicazione: (2026)

DPO Unchained: Your Training Algorithm is Secretly Disentangled in Human Choice Theory
di: Zhou, Wenxuan, et al.
Pubblicazione: (2025)

Unlearning at Scale: Implementing the Right to be Forgotten in Large Language Models
di: X, Abdullah
Pubblicazione: (2025)

Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models
di: Zhang, Gongbo, et al.
Pubblicazione: (2026)

Evaluating Model Explanations without Ground Truth
di: Rawal, Kaivalya, et al.
Pubblicazione: (2025)

Grokking Beyond the Euclidean Norm of Model Parameters
di: Notsawo, Pascal Jr Tikeng, et al.
Pubblicazione: (2025)

Cognitive Load Limits in Large Language Models: Benchmarking Multi-Hop Reasoning
di: Adapala, Sai Teja Reddy
Pubblicazione: (2025)

Alif: Advancing Urdu Large Language Models via Multilingual Synthetic Data Distillation
di: Shafique, Muhammad Ali, et al.
Pubblicazione: (2025)

Black Box Model Explanations and the Human Interpretability Expectations -- An Analysis in the Context of Homicide Prediction
di: Ribeiro, José, et al.
Pubblicazione: (2022)

A Practical Approach to using Supervised Machine Learning Models to Classify Aviation Safety Occurrences
di: Siow, Bryan Y.
Pubblicazione: (2025)

A Framework for Neurosymbolic Robot Action Planning using Large Language Models
di: Capitanelli, Alessio, et al.
Pubblicazione: (2023)

Beyond Hallucinations: A Composite Score for Measuring Reliability in Open-Source Large Language Models
di: Salla, Rohit Kumar, et al.
Pubblicazione: (2025)

Ground-Compose-Reinforce: Grounding Language in Agentic Behaviours using Limited Data
di: Li, Andrew C., et al.
Pubblicazione: (2025)

BLOCK-EM: Preventing Emergent Misalignment via Latent Blocking
di: Ustaomeroglu, Muhammed, et al.
Pubblicazione: (2026)

Closing the Distribution Gap in Adversarial Training for LLMs
di: Hu, Chengzhi, et al.
Pubblicazione: (2026)

Embedded Safety-Aligned Intelligence via Differentiable Internal Alignment Embeddings
di: Rathva, Harsh, et al.
Pubblicazione: (2025)

Reducing the Sensitivity of Neural Physics Simulators to Mesh Topology via Pretraining
di: Vaska, Nathan, et al.
Pubblicazione: (2025)

Training AI to be Loyal
di: Oh, Sewoong, et al.
Pubblicazione: (2025)