Cover Image

Harnessing the Universal Geometry of Embeddings

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jha, Rishi, Zhang, Collin, Shmatikov, Vitaly, Morris, John X.
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

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

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

Self-interpreting Adversarial Images
by: Zhang, Tingwei, et al.
Published: (2024)

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

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

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

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

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

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

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

Rerouting LLM Routers
by: Shafran, Avital, et al.
Published: (2025)

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

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

Recursive State Inference for Linear PASFA
by: Rishi, Vishal
Published: (2025)

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

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

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

Geometric framework for biological evolution
by: Vanchurin, Vitaly
Published: (2026)

SMIXAE: Towards Unsupervised Manifold Discovery in Language Models
by: Francel, Collin
Published: (2026)

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

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

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

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

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

Geometric Learning Dynamics
by: Vanchurin, Vitaly
Published: (2025)

Emergent field theories from neural networks
by: Vanchurin, Vitaly
Published: (2024)

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

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

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

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

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

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

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

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

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

Universal Embeddings of Tabular Data
by: Franz, Astrid, et al.
Published: (2025)

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

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