Cover Image

Post-Training Probability Manifold Correction via Structured SVD Pruning and Self-Referential Distillation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Flouro, Aaron R., Chadwick, Shawn P.
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computation and Language 68T05 I.2.6
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Multi-Teacher Ensemble Distillation: A Mathematical Framework for Probability-Domain Knowledge Aggregation
by: Flouro, Aaron R., et al.
Published: (2026)

Adaptive Weighting in Knowledge Distillation: An Axiomatic Framework for Multi-Scale Teacher Ensemble Optimization
by: Flouro, Aaron R., et al.
Published: (2026)

Sparse Knowledge Distillation: A Mathematical Framework for Probability-Domain Temperature Scaling and Multi-Stage Compression
by: Flouro, Aaron R., et al.
Published: (2026)

Recursive Meta-Distillation: An Axiomatic Framework for Iterative Knowledge Refinement
by: Flouro, Aaron R., et al.
Published: (2026)

Hallucinations Live in Variance
by: Flouro, Aaron R., et al.
Published: (2026)

Tracking Changing Probabilities via Dynamic Learners
by: Madani, Omid
Published: (2024)

Syntactic Framing Fragility: An Audit of Robustness in LLM Ethical Decisions
by: Elkins, Katherine, et al.
Published: (2025)

Hybrid Gated Flow (HGF): Stabilizing 1.58-bit LLMs via Selective Low-Rank Correction
by: Pizzo, David Alejandro Trejo
Published: (2026)

mHC-SSM: Manifold-Constrained Hyper-Connections for State Space Language Models with Stream-Specialized Adapters
by: Mutlu, Abdulvahap, et al.
Published: (2026)

ARF-RLHF: Adaptive Reward-Following for RLHF through Emotion-Driven Self-Supervision and Trace-Biased Dynamic Optimization
by: Zhang, YuXuan
Published: (2025)

lmfaoooo at SemEval-2026 Task 1: Humor Is an Audience. Preference Modeling for Constrained Humor Generation
by: Tikhonov, Alexey, et al.
Published: (2026)

No Memorization, No Detection: Output Distribution-Based Contamination Detection in Small Language Models
by: Sela, Omer
Published: (2026)

Latent Object Permanence: Topological Phase Transitions, Free-Energy Principles, and Renormalization Group Flows in Deep Transformer Manifolds
by: Alpay, Faruk, et al.
Published: (2026)

Emergence of Goal-Directed Behaviors via Active Inference with Self-Prior
by: Kim, Dongmin, et al.
Published: (2025)

How much do LLMs learn from negative examples?
by: Hamdan, Shadi, et al.
Published: (2025)

BitSkip: An Empirical Analysis of Quantization and Early Exit Composition in Transformers
by: Bhuvaneswaran, Ramshankar, et al.
Published: (2025)

Manipulating Transformer-Based Models: Controllability, Steerability, and Robust Interventions
by: Alpay, Faruk, et al.
Published: (2025)

An Automatic Text Classification Method Based on Hierarchical Taxonomies, Neural Networks and Document Embedding: The NETHIC Tool
by: Lomasto, Luigi, et al.
Published: (2026)

GoldenStart: Q-Guided Priors and Entropy Control for Distilling Flow Policies
by: Zhang, He, et al.
Published: (2026)

Multi-Scale Graph Learning for Anti-Sparse Downscaling
by: Fan, Yingda, et al.
Published: (2025)

KDSTM: Neural Semi-supervised Topic Modeling with Knowledge Distillation
by: Xu, Weijie, et al.
Published: (2023)

XAutoLM: Efficient Fine-Tuning of Language Models via Meta-Learning and AutoML
by: Estevanell-Valladares, Ernesto L., et al.
Published: (2025)

Measuring and curing reasoning rigidity: from decorative chain-of-thought to genuine faithfulness
by: Basu, Abhinaba, et al.
Published: (2026)

From Noise to Diversity: Random Embedding Injection in LLM Reasoning
by: Kim, Heejun, et al.
Published: (2026)

BreakFun: Jailbreaking LLMs via Schema Exploitation
by: Oskooei, Amirkia Rafiei, et al.
Published: (2025)

Mitigating Position-Shift Failures in Text-Based Modular Arithmetic via Position Curriculum and Template Diversity
by: Yudin, Nikolay
Published: (2026)

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

Actor-Curator: Co-adaptive Curriculum Learning via Policy-Improvement Bandits for RL Post-Training
by: Gu, Zhengyao, et al.
Published: (2026)

Tool-Genesis: A Task-Driven Tool Creation Benchmark for Self-Evolving Language Agent
by: Xia, Bowei, et al.
Published: (2026)

ReFactor GNNs: Revisiting Factorisation-based Models from a Message-Passing Perspective
by: Chen, Yihong, et al.
Published: (2022)

When Your Own Output Becomes Your Training Data: Noise-to-Meaning Loops and a Formal RSI Trigger
by: Ando, Rintaro
Published: (2025)

Correction and Corruption: A Two-Rate View of Error Flow in LLM Protocols
by: Reitich, Fernando
Published: (2026)

Cross-Domain Malware Detection via Probability-Level Fusion of Lightweight Gradient Boosting Models
by: Mohamed, Omar Khalid Ali
Published: (2025)

Dynamic Dual-Granularity Skill Bank for Agentic RL
by: Tu, Songjun, et al.
Published: (2026)

MACS: Multi-Agent Reinforcement Learning for Optimization of Crystal Structures
by: Zamaraeva, Elena, et al.
Published: (2025)

Effects of Initialization Biases on Deep Neural Network Training Dynamics
by: Pellegrino, Nicholas, et al.
Published: (2025)

The Mirror Loop: Recursive Non-Convergence in Generative Reasoning Systems
by: DeVilling, Bentley
Published: (2025)

Distinguished In Uniform: Self Attention Vs. Virtual Nodes
by: Rosenbluth, Eran, et al.
Published: (2024)

Harnessing non-adversarial robustness in large language models
by: Zhou, Qinghua, et al.
Published: (2026)

A social path to human-like artificial intelligence
by: Duéñez-Guzmán, Edgar A., et al.
Published: (2024)