mlsanityData to 7 Oct 2026

Consistent estimation of generative model representations in the data kernel perspective space

arXiv 2409.17308 ↗First posted 25 Sep 2024cs.LG math.ST stat.THcited by 10

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Generative models, such as large language models and text-to-image diffusion models, produce relevant information when presented a query. Different models may produce different information when presented the same query. As the landscape of generative models evolves, it is important to develop techniques to study and analyze differences in model behaviour. In this paper we present novel theoretical results for embedding-based representations of generative models in the context of a set of queries. In particular, we establish sufficient conditions for the consistent estimation of the model embeddings in situations where the query set and the number of models grow.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 18 of its 24 references that are in the map. First posted on arXiv 25 Sep 2024.

Builds on

18 of 24 references.

References · 18

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  5. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,725
  6. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
  7. 2022Text and Code Embeddings by Contrastive Pre-Trainingcited by 358
  8. 2022VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidancecited by 285
  9. 2024Nomic Embed: Training a Reproducible Long Context Text Embeddercited by 255
  10. 2023Planning with Large Language Models for Code Generationcited by 179
  11. 2023Perspectives on Large Language Models for Relevance Judgmentcited by 84
  12. 2017Deep Voice: Real-time Neural Text-to-Speechcited by 83
6 more
  1. 2019GraSPy: Graph Statistics in Pythoncited by 15
  2. 2023Comparing Foundation Models using Data Kernelscited by 14
  3. 2024Tracking the perspectives of interacting language modelscited by 14
  4. 2022Mental State Classification Using Multi-graph Featurescited by 7
  5. 2021Inducing a hierarchy for multi-class classification problemscited by 5
  6. 2024Continuous Multidimensional Scalingcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 3; 2026: 5.

10 papers.

  1. 2024Statistical inference on black-box generative models in the data kernel perspective spacecited by 9
  2. 2024Investigating social alignment via mirroring in a system of interacting language modelscited by 5
  3. 2025Detecting Perspective Shifts in Multi-agent Systemscited by 4
  4. 2026Query-efficient model evaluation using cached responsescited by 2
  5. 2025Toward a digital twin of U.S. Congresscited by 1
  6. 2025Concentration bounds on response-based vector embeddings of black-box generative modelscited by 1
  7. 2026Black-box model classification under the discriminative factorizationcited by 1
  8. 2026Control Charts for Multi-agent Systemscited by 1
  9. 2026Data Kernel Perspective Space Performance Guarantees for Synthetic Data from Transformer Modelscited by 0
  10. 2026Jailbreak susceptibility prediction and mitigation via the behavioral geometry of modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Generative Embedding Benchmark: How Much Information Survives in a Dense Embedding?
  2. 2023The Curse of Recursion: Training on Generated Data Makes Models Forget
  3. 2023Localizing and Editing Knowledge in Text-to-Image Generative Models
  4. 2025Exploring Training and Inference Scaling Laws in Generative Retrieval
  5. 2024BBScoreV2: Learning Time-Evolution and Latent Alignment from Stochastic Representation
  6. 2025Understanding the Influence of Synthetic Data for Text Embedders
  7. 2025How Much Data Is Enough? Uniform Convergence Bounds for Generative & Vision-Language Models under Low-Dimensional Structure
  8. 2024Generative Representational Instruction Tuning