Robust Weight Imprinting: Insights from Neural Collapse and Proxy-Based Aggregation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Westerhoff, Justus, Atefi, Golzar, Koddenbrock, Mario, Figueroa, Alexei, Löser, Alexander, Rodner, Erik, Gers, Felix A.
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Comply: Learning Sentences with Complex Weights inspired by Fruit Fly Olfaction
di: Figueroa, Alexei, et al.
Pubblicazione: (2025)

SCAM: A Real-World Typographic Robustness Evaluation for Multimodal Foundation Models
di: Westerhoff, Justus, et al.
Pubblicazione: (2025)

Feedback-driven object detection and iterative model improvement
di: Tenckhoff, Sönke, et al.
Pubblicazione: (2024)

LLMStructBench: Benchmarking Large Language Model Structured Data Extraction
di: Tenckhoff, Sönke, et al.
Pubblicazione: (2026)

On the Domain Robustness of Contrastive Vision-Language Models
di: Koddenbrock, Mario, et al.
Pubblicazione: (2025)

RamanBench: A Large-Scale Benchmark for Machine Learning on Raman Spectroscopy
di: Koddenbrock, Mario, et al.
Pubblicazione: (2026)

ConceptTracer: Interactive Analysis of Concept Saliency and Selectivity in Neural Representations
di: Knauer, Ricardo, et al.
Pubblicazione: (2026)

Squeezing Lemons with Hammers: An Evaluation of AutoML and Tabular Deep Learning for Data-Scarce Classification Applications
di: Knauer, Ricardo, et al.
Pubblicazione: (2024)

In Search of Grandmother Cells: Tracing Interpretable Neurons in Tabular Representations
di: Knauer, Ricardo, et al.
Pubblicazione: (2026)

"Oh LLM, I'm Asking Thee, Please Give Me a Decision Tree": Zero-Shot Decision Tree Induction and Embedding with Large Language Models
di: Knauer, Ricardo, et al.
Pubblicazione: (2024)

FuelCast: Benchmarking Tabular and Temporal Models for Ship Fuel Consumption
di: Viga, Justus, et al.
Pubblicazione: (2025)

PMLBmini: A Tabular Classification Benchmark Suite for Data-Scarce Applications
di: Knauer, Ricardo, et al.
Pubblicazione: (2024)

Towards Explainable TOPSIS: Visual Insights into the Effects of Weights and Aggregations on Rankings
di: Susmaga, Robert, et al.
Pubblicazione: (2023)

MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Data
di: Han, Tianyu, et al.
Pubblicazione: (2023)

Same Meaning, Different Scores: Lexical and Syntactic Sensitivity in LLM Evaluation
di: Kostić, Bogdan, et al.
Pubblicazione: (2026)

Fast Proxies for LLM Robustness Evaluation
di: Beyer, Tim, et al.
Pubblicazione: (2025)

LLMs as Policy-Agnostic Teammates: A Case Study in Human Proxy Design for Heterogeneous Agent Teams
di: Justus, Aju Ani, et al.
Pubblicazione: (2025)

Beyond Weighted Summation: Learnable Nonlinear Aggregation Functions for Robust Artificial Neurons
di: Bozyigit, Berke Deniz
Pubblicazione: (2026)

OptiProxy-NAS: Optimization Proxy based End-to-End Neural Architecture Search
di: Lyu, Bo, et al.
Pubblicazione: (2025)

SBOMs into Agentic AIBOMs: Schema Extensions, Agentic Orchestration, and Reproducibility Evaluation
di: Radanliev, Petar, et al.
Pubblicazione: (2026)

Hallucination Detection via Activations of Open-Weight Proxy Analyzers
di: Singh, Akshita, et al.
Pubblicazione: (2026)

Transferring Causal Effects using Proxies
di: Iglesias-Alonso, Manuel, et al.
Pubblicazione: (2025)

Aggregation Artifacts in Subjective Tasks Collapse Large Language Models' Posteriors
di: Chochlakis, Georgios, et al.
Pubblicazione: (2024)

Intrinsic Structure as a Proxy for Saliency: SVD-Based Weight Preservation for Mixed-Precision Quantization in Large Language Models
di: Landge, Shashank, et al.
Pubblicazione: (2025)

The Prevalence of Neural Collapse in Neural Multivariate Regression
di: Andriopoulos, George, et al.
Pubblicazione: (2024)

Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning
di: Li, Miao, et al.
Pubblicazione: (2026)

Proxy-Based Approximation of Shapley and Banzhaf Interactions
di: Thies, Santo M. A. R., et al.
Pubblicazione: (2026)

From Confidence to Collapse in LLM Factual Robustness
di: Fastowski, Alina, et al.
Pubblicazione: (2025)

Operationalising Artificial Intelligence Bills of Materials (AIBOMs) for Verifiable AI Provenance and Lifecycle Assurance
di: Radanliev, Petar, et al.
Pubblicazione: (2026)

Diffusion-Based Neural Network Weights Generation
di: Soro, Bedionita, et al.
Pubblicazione: (2024)

Robust Weight Initialization for Tanh Neural Networks with Fixed Point Analysis
di: Lee, Hyunwoo, et al.
Pubblicazione: (2024)

Enhancing Pre-Trained Model-Based Class-Incremental Learning through Neural Collapse
di: He, Kun, et al.
Pubblicazione: (2025)

Collapse or Preserve: Data-Dependent Temporal Aggregation for Spiking Neural Network Acceleration
di: Qin, Jiahao
Pubblicazione: (2026)

Grokking and Generalization Collapse: Insights from \texttt{HTSR} theory
di: Prakash, Hari K., et al.
Pubblicazione: (2025)

Cycle-Consistent Search: Question Reconstructability as a Proxy Reward for Search Agent Training
di: An, Sohyun, et al.
Pubblicazione: (2026)

Context Collapse: In-Context Learning and Model Collapse
di: Ott, Josef
Pubblicazione: (2026)

Roundtable Policy: Confidence-Weighted-Consensus Aggregation Improves Multi-Agent-System Reasoning
di: Yao, Yu, et al.
Pubblicazione: (2025)

CliniBench: A Clinical Outcome Prediction Benchmark for Generative and Encoder-Based Language Models
di: Grundmann, Paul, et al.
Pubblicazione: (2025)

Spiking Neural Networks for Continuous Control via End-to-End Model-Based Learning
di: Huebotter, Justus, et al.
Pubblicazione: (2025)

Data Augmentation Techniques to Reverse-Engineer Neural Network Weights from Input-Output Queries
di: Beiser, Alexander, et al.
Pubblicazione: (2025)