Cover Image

Geometric Organization of Cognitive States in Transformer Embedding Spaces

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Zhao, Sophie
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning
by: Wang, Juyuan, et al.
Published: (2025)

DisEmbed: Transforming Disease Understanding through Embeddings
by: Faroz, Salman
Published: (2024)

Challenging Assumptions in Learning Generic Text Style Embeddings
by: Ostheimer, Phil, et al.
Published: (2025)

A Comparative Analysis of Contextual Representation Flow in State-Space and Transformer Architectures
by: Hoang, Nhat M., et al.
Published: (2025)

Cognitive Fatigue in Autoregressive Transformers: Formalization and Measurement
by: Marwah, Riju, et al.
Published: (2026)

Rethinking Token Reduction for State Space Models
by: Zhan, Zheng, et al.
Published: (2024)

State Stream Transformer (SST) V2: Parallel Training of Nonlinear Recurrence for Latent Space Reasoning
by: Aviss, Thea
Published: (2026)

A Novel Spinor-Based Embedding Model for Transformers
by: White, Rick
Published: (2024)

Sharing Parameter by Conjugation for Knowledge Graph Embeddings in Complex Space
by: Feng, Xincan, et al.
Published: (2024)

MapFormer: Self-Supervised Learning of Cognitive Maps with Input-Dependent Positional Embeddings
by: Rambaud, Victor, et al.
Published: (2025)

On Pruning State-Space LLMs
by: Ghattas, Tamer, et al.
Published: (2025)

Bifocal Attention: Harmonizing Geometric and Spectral Positional Embeddings for Algorithmic Generalization
by: Awadhiya, Kanishk
Published: (2026)

The Geometric Anatomy of Capability Acquisition in Transformers
by: Billa, Jayadev
Published: (2026)

Grammar as a Behavioral Biometric: Using Cognitively Motivated Grammar Models for Authorship Verification
by: Nini, Andrea, et al.
Published: (2024)

Repeat After Me: Transformers are Better than State Space Models at Copying
by: Jelassi, Samy, et al.
Published: (2024)

Employing Sentence Space Embedding for Classification of Data Stream from Fake News Domain
by: Zyblewski, Paweł, et al.
Published: (2024)

Unsupervised Text Embedding Space Generation Using Generative Adversarial Networks for Text Synthesis
by: Lee, Jun-Min, et al.
Published: (2023)

Rotation Control Unlearning: Quantifying and Controlling Continuous Unlearning for LLM with The Cognitive Rotation Space
by: Zhang, Xiang, et al.
Published: (2025)

Fine-tuning and Prompt Engineering with Cognitive Knowledge Graphs for Scholarly Knowledge Organization
by: Rabby, Gollam, et al.
Published: (2024)

The Illusion of State in State-Space Models
by: Merrill, William, et al.
Published: (2024)

Lost in State Space: Probing Frozen Mamba Representations
by: Wagh, Bhagyashree, et al.
Published: (2026)

Parameter-Efficient Fine-Tuning of State Space Models
by: Galim, Kevin, et al.
Published: (2024)

Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity
by: Kuratov, Yuri, et al.
Published: (2025)

CareerBERT: Matching Resumes to ESCO Jobs in a Shared Embedding Space for Generic Job Recommendations
by: Rosenberger, Julian, et al.
Published: (2025)

Position Information Emerges in Causal Transformers Without Positional Encodings via Similarity of Nearby Embeddings
by: Zuo, Chunsheng, et al.
Published: (2024)

Flexible Language Modeling in Continuous Space with Transformer-based Autoregressive Flows
by: Zhang, Ruixiang, et al.
Published: (2025)

Empowering Diffusion Models on the Embedding Space for Text Generation
by: Gao, Zhujin, et al.
Published: (2022)

Demystifying Embedding Spaces using Large Language Models
by: Tennenholtz, Guy, et al.
Published: (2023)

MambaByte: Token-free Selective State Space Model
by: Wang, Junxiong, et al.
Published: (2024)

LOCOST: State-Space Models for Long Document Abstractive Summarization
by: Bronnec, Florian Le, et al.
Published: (2024)

Mimetic Initialization Helps State Space Models Learn to Recall
by: Trockman, Asher, et al.
Published: (2024)

Exploring the Impact of a Transformer's Latent Space Geometry on Downstream Task Performance
by: Marbut, Anna C., et al.
Published: (2024)

The UNDO Flip-Flop: A Controlled Probe for Reversible Semantic State Management in State Space Model
by: Zhou, Hongxu
Published: (2026)

Finite State Automata Inside Transformers with Chain-of-Thought: A Mechanistic Study on State Tracking
by: Zhang, Yifan, et al.
Published: (2025)

Inducing Systematicity in Transformers by Attending to Structurally Quantized Embeddings
by: Jiang, Yichen, et al.
Published: (2024)

Context-Free Recognition with Transformers
by: Jerad, Selim, et al.
Published: (2026)

From Topology to Retrieval: Decoding Embedding Spaces with Unified Signatures
by: Rottach, Florian, et al.
Published: (2025)

Group-Sparse Matrix Factorization for Transfer Learning of Word Embeddings
by: Xu, Kan, et al.
Published: (2021)

Data Kernel Perspective Space Performance Guarantees for Synthetic Data from Transformer Models
by: Browder, Michael, et al.
Published: (2026)

RichSpace: Enriching Text-to-Video Prompt Space via Text Embedding Interpolation
by: Cao, Yuefan, et al.
Published: (2025)