Imagen de Portada

Harnessing the Universal Geometry of Embeddings

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Jha, Rishi, Zhang, Collin, Shmatikov, Vitaly, Morris, John X.
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Extracting Prompts by Inverting LLM Outputs
por: Zhang, Collin, et al.
Publicado: (2024)

Adversarial Illusions in Multi-Modal Embeddings
por: Zhang, Tingwei, et al.
Publicado: (2023)

Multi-Agent Systems Execute Arbitrary Malicious Code
por: Triedman, Harold, et al.
Publicado: (2025)

Universal Zero-shot Embedding Inversion
por: Zhang, Collin, et al.
Publicado: (2025)

Self-interpreting Adversarial Images
por: Zhang, Tingwei, et al.
Publicado: (2024)

Breaking and Fixing Defenses Against Control-Flow Hijacking in Multi-Agent Systems
por: Jha, Rishi, et al.
Publicado: (2025)

Adversarial Decoding: Generating Readable Documents for Adversarial Objectives
por: Zhang, Collin, et al.
Publicado: (2024)

MillStone: How Open-Minded Are LLMs?
por: Triedman, Harold, et al.
Publicado: (2025)

Learning to Detect Language Model Training Data via Active Reconstruction
por: Yin, Junjie Oscar, et al.
Publicado: (2026)

Adversarial Hubness in Multi-Modal Retrieval
por: Zhang, Tingwei, et al.
Publicado: (2024)

Machine Against the RAG: Jamming Retrieval-Augmented Generation with Blocker Documents
por: Shafran, Avital, et al.
Publicado: (2024)

How to Steal Reasoning Without Reasoning Traces
por: Zhang, Tingwei, et al.
Publicado: (2026)

Rerouting LLM Routers
por: Shafran, Avital, et al.
Publicado: (2025)

Agent Meltdowns: The Road to Hell Is Paved with Helpful Agents
por: Jha, Rishi, et al.
Publicado: (2026)

Differential Degradation Vulnerabilities in Censorship Circumvention Systems
por: Sun, Zhen, et al.
Publicado: (2024)

Recursive State Inference for Linear PASFA
por: Rishi, Vishal
Publicado: (2025)

Do language models plan ahead for future tokens?
por: Wu, Wilson, et al.
Publicado: (2024)

Learning to Reason in 13 Parameters
por: Morris, John X., et al.
Publicado: (2026)

Correction of Transformer-Based Models with Smoothing Pseudo-Projector
por: Bulgakov, Vitaly
Publicado: (2026)

Geometric framework for biological evolution
por: Vanchurin, Vitaly
Publicado: (2026)

SMIXAE: Towards Unsupervised Manifold Discovery in Language Models
por: Francel, Collin
Publicado: (2026)

Crafting Interpretable Embeddings by Asking LLMs Questions
por: Benara, Vinamra, et al.
Publicado: (2024)

Approximating Language Model Training Data from Weights
por: Morris, John X., et al.
Publicado: (2025)

Privacy amplification by random allocation
por: Feldman, Vitaly, et al.
Publicado: (2025)

Efficient privacy loss accounting for subsampling and random allocation
por: Feldman, Vitaly, et al.
Publicado: (2026)

Deep-Research Agents Can Be Poisoned via User-Generated Content
por: Zhang, Tingwei, et al.
Publicado: (2026)

Geometric Learning Dynamics
por: Vanchurin, Vitaly
Publicado: (2025)

Emergent field theories from neural networks
por: Vanchurin, Vitaly
Publicado: (2024)

Shared Global and Local Geometry of Language Model Embeddings
por: Lee, Andrew, et al.
Publicado: (2025)

Geometry-Preserving Aggregation for Mixture-of-Experts Embedding Models
por: Kachuee, Sajjad, et al.
Publicado: (2026)

Harnessing Scale and Physics: A Multi-Graph Neural Operator Framework for PDEs on Arbitrary Geometries
por: Li, Zhihao, et al.
Publicado: (2024)

Geometry-Preserving Neural Architectures on Manifolds with Boundary
por: Elamvazhuthi, Karthik, et al.
Publicado: (2026)

GeoFlowVLM: Geometry-Aware Joint Uncertainty for Frozen Vision-Language Embedding
por: Nautiyal, Mayank, et al.
Publicado: (2026)

Geometry-Aware Backdoor Attacks: Leveraging Curvature in Hyperbolic Embeddings
por: Baheri, Ali
Publicado: (2025)

From Autoencoders to CycleGAN: Robust Unpaired Face Manipulation via Adversarial Learning
por: Guo, Collin, et al.
Publicado: (2025)

Q-Fusion: Diffusing Quantum Circuits
por: Beaudoin, Collin, et al.
Publicado: (2025)

Evaluating Effects of Augmented SELFIES for Molecular Understanding Using QK-LSTM
por: Beaudoin, Collin, et al.
Publicado: (2025)

Universal Embeddings of Tabular Data
por: Franz, Astrid, et al.
Publicado: (2025)

Causes in neuron diagrams, and testing causal reasoning in Large Language Models. A glimpse of the future of philosophy?
por: Vervoort, Louis, et al.
Publicado: (2025)

Neural-Schwarz Tiling for Geometry-Universal PDE Solving at Scale
por: Secchi, Paolo, et al.
Publicado: (2026)