Image de couverture de livre

Persistent Topological Features in Large Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gardinazzi, Yuri, Viswanathan, Karthik, Panerai, Giada, Ansuini, Alessio, Cazzaniga, Alberto, Biagetti, Matteo
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language Computational Geometry Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

The Geometry of Tokens in Internal Representations of Large Language Models
par: Viswanathan, Karthik, et autres
Publié: (2025)

The representation landscape of few-shot learning and fine-tuning in large language models
par: Doimo, Diego, et autres
Publié: (2024)

Zigzag Persistence of Neural Responses to Time-Varying Stimuli
par: Gardinazzi, Yuri, et autres
Publié: (2026)

Emergent representations in networks trained with the Forward-Forward algorithm
par: Tosato, Niccolò, et autres
Publié: (2023)

Probing Geometry of Next Token Prediction Using Cumulant Expansion of the Softmax Entropy
par: Viswanathan, Karthik, et autres
Publié: (2025)

The Flood Complex: Large-Scale Persistent Homology on Millions of Points
par: Graf, Florian, et autres
Publié: (2025)

Bias after Prompting: Persistent Discrimination in Large Language Models
par: Sivakumar, Nivedha, et autres
Publié: (2025)

The Narrow Gate: Localized Image-Text Communication in Native Multimodal Models
par: Serra, Alessandro Pietro, et autres
Publié: (2024)

Algorithm for Interpretable Graph Features via Motivic Persistent Cohomology
par: Maruyama, Yoshihiro
Publié: (2025)

Topological Autoencoders++: Fast and Accurate Cycle-Aware Dimensionality Reduction
par: Clémot, Mattéo, et autres
Publié: (2025)

Rotary Offset Features in Large Language Models
par: Jonasson, André
Publié: (2025)

Robust Barycenters of Persistence Diagrams
par: Sisouk, Keanu, et autres
Publié: (2025)

Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective
par: Aladrah, Nicola, et autres
Publié: (2026)

PHLP: Sole Persistent Homology for Link Prediction - Interpretable Feature Extraction
par: You, Junwon, et autres
Publié: (2024)

Automatically Interpreting Millions of Features in Large Language Models
par: Paulo, Gonçalo, et autres
Publié: (2024)

Semantic Structure of Feature Space in Large Language Models
par: Kozlowski, Austin C., et autres
Publié: (2026)

Latent Feature Mining for Predictive Model Enhancement with Large Language Models
par: Li, Bingxuan, et autres
Publié: (2024)

GeoLAN: Geometric Learning of Latent Explanatory Directions in Large Language Models
par: Pan, Tianyu Bell, et autres
Publié: (2026)

The Curved Spacetime of Transformer Architectures
par: Di Sipio, Riccardo, et autres
Publié: (2025)

Feature Alignment and Representation Transfer in Knowledge Distillation for Large Language Models
par: Yang, Junjie, et autres
Publié: (2025)

In-Context Symbolic Regression: Leveraging Large Language Models for Function Discovery
par: Merler, Matteo, et autres
Publié: (2024)

Head Pursuit: Probing Attention Specialization in Multimodal Transformers
par: Basile, Lorenzo, et autres
Publié: (2025)

Persistent Homology via Finite Topological Spaces
par: Kayacan, Selçuk
Publié: (2025)

Topological Machine Learning with Unreduced Persistence Diagrams
par: Abreu, Nicole, et autres
Publié: (2025)

Wu's Method can Boost Symbolic AI to Rival Silver Medalists and AlphaGeometry to Outperform Gold Medalists at IMO Geometry
par: Sinha, Shiven, et autres
Publié: (2024)

Pre-trained Large Language Models Use Fourier Features to Compute Addition
par: Zhou, Tianyi, et autres
Publié: (2024)

Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models
par: Deng, Boyi, et autres
Publié: (2026)

Topological Spatial Graph Coarsening
par: Calissano, Anna, et autres
Publié: (2025)

Cover Learning for Large-Scale Topology Representation
par: Scoccola, Luis, et autres
Publié: (2025)

Narrative Feature or Structured Feature? A Study of Large Language Models to Identify Cancer Patients at Risk of Heart Failure
par: Chen, Ziyi, et autres
Publié: (2024)

NeuroPrune: A Neuro-inspired Topological Sparse Training Algorithm for Large Language Models
par: Dhurandhar, Amit, et autres
Publié: (2024)

MoSE: Mixture of Slimmable Experts for Efficient and Adaptive Language Models
par: Tastan, Nurbek, et autres
Publié: (2026)

The Birth of Knowledge: Emergent Features across Time, Space, and Scale in Large Language Models
par: Sawmya, Shashata, et autres
Publié: (2025)

Certifying Robustness via Topological Representations
par: Agerberg, Jens, et autres
Publié: (2025)

Adaptive Feature-based Low-Rank Compression of Large Language Models via Bayesian Optimization
par: Ji, Yixin, et autres
Publié: (2024)

LLM-Select: Feature Selection with Large Language Models
par: Jeong, Daniel P., et autres
Publié: (2024)

Quantum Attention by Overlap Interference: Predicting Sequences from Classical and Many-Body Quantum Data
par: Pecilli, Alessio, et autres
Publié: (2026)

Rapid and Precise Topological Comparison with Merge Tree Neural Networks
par: Qin, Yu, et autres
Publié: (2024)

Knowledge-Driven Feature Selection and Engineering for Genotype Data with Large Language Models
par: Lee, Joseph, et autres
Publié: (2024)

Param$Δ$ for Direct Weight Mixing: Post-Train Large Language Model at Zero Cost
par: Cao, Sheng, et autres
Publié: (2025)