Paper Citation Record · LEDGER

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency

As of 14 August 2026, this Paper Citation Record lists 77 of 77 outbound references and 7 inbound Pith citation observations for arXiv:2411.16525.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2411.16525 v2

Coverage vector

measured 77 of 77 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T13:07:04.465221Z

measured 84 of 84 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-12T12:06:13.422429Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-05-11T21:51:30.206281Z

Reference resolution

77 of 77 outbound references displayed

verified exact1
verified fuzzy32
unresolved44
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a358fe05-ac2a-4734-a2b4-c2b40ea47bf1 · outbound

This paper cites write newline.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.105363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a05ab92e-2463-4ff6-ab56-e2ec3ec3a0a4 · outbound

This paper cites Optimal-degree polynomial approximations for exponentials and gaussian kernel density estimation.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Optimal-degree polynomial approximations for exponentials and gaussian kernel density estimation

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.112217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6539dac9-d5bf-41bd-812c-e4bf0bfe0b84 · outbound

This paper cites Sumformer: Universal approximation for efficient transformers.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Sumformer: Universal approximation for efficient transformers

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.865319Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0761637e-8cac-4320-ace4-49afdfdb80d3 · outbound

This paper cites Fast attention requires bounded entries.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Fast attention requires bounded entries

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.847182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a6da9b8c-20d6-4119-b53d-161f147b3710 · outbound

This paper cites Fundamental Limitations on Subquadratic Alternatives to Transformers.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Fundamental Limitations on Subquadratic Alternatives to Transformers

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.127924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b7aba20-3718-452d-a9c5-7ca6766e30fc · outbound

This paper cites An alternative softmax operator for reinforcement learning.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency An alternative softmax operator for reinforcement learning

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.829112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cc5e5f10-81c3-4543-bbaf-66dfbeed774d · outbound

This paper cites Birth of a transformer: A memory viewpoint.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Birth of a transformer: A memory viewpoint

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.139196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20e83213-fb5a-4b20-9470-6a55d62c9795 · outbound

This paper cites On the Opportunities and Risks of Foundation Models.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency On the Opportunities and Risks of Foundation Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.144874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66d9424b-018d-4799-abd6-ef9912bb29a8 · outbound

This paper cites Convex optimization.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Convex optimization

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.149988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fc06f70-16d4-42c1-bf68-447f242316a2 · outbound

This paper cites Language models are few-shot learners.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Language models are few-shot learners

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.156779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb16212e-a45c-4867-95ec-0fe9e47f74c2 · outbound

This paper cites PLOT : Prompt learning with optimal transport for vision-language models.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency PLOT : Prompt learning with optimal transport for vision-language models

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.760352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 19b5953c-9f92-4e8e-acb2-207809cf1041 · outbound

This paper cites On problems as hard as cnf-sat.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency On problems as hard as cnf-sat

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.742850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e721d176-9bc2-4b5e-b41d-f7747bd6b2be · outbound

This paper cites Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.168998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 061559cc-d32c-422d-9123-f3264f4c3c64 · outbound

This paper cites Parameter-efficient fine-tuning of large-scale pre-trained language models.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Parameter-efficient fine-tuning of large-scale pre-trained language models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.173803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1213db24-ddd7-4718-b67a-10469f82a57f · outbound

This paper cites A Survey on In-context Learning.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency A Survey on In-context Learning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.178564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e59cef1-3f06-432e-a6ea-904e3a4370ce · outbound

This paper cites Gpt-3: Its nature, scope, limits, and consequences.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Gpt-3: Its nature, scope, limits, and consequences

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.698923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a297c5c0-b6dd-4f13-aecf-6526fa04280a · outbound

This paper cites Nemesis: Normalizing the soft-prompt vectors of vision-language models.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Nemesis: Normalizing the soft-prompt vectors of vision-language models

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.679113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 62488b7c-9f36-4cca-b270-042940f23f4e · outbound

This paper cites Protein multimer structure prediction via prompt learning.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Protein multimer structure prediction via prompt learning

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.663380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3e820d22-c681-4a84-9cc4-e6f5a772bd98 · outbound

This paper cites Understanding scaling laws with statistical and approximation theory for transformer neural networks on intrinsically low-dimensional data.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Understanding scaling laws with statistical and approximation theory for transformer neural networks on intrinsically low-dimensional data

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.644430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 799766ff-6f91-4c6c-858e-c82402bfeb7c · outbound

This paper cites LoRA+: Efficient Low Rank Adaptation of Large Models.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency LoRA+: Efficient Low Rank Adaptation of Large Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.203848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebc63937-33a8-4286-82d1-d7b2df4addcf · outbound

This paper cites Lo RA : Low-rank adaptation of large language models.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Lo RA : Low-rank adaptation of large language models

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.627504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1ee04aec-8d95-4b1a-9aeb-f2cb540e86fb · outbound

This paper cites On sparse modern hopfield model.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency On sparse modern hopfield model

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.607951Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5e1dc248-59cc-4fef-8392-455267578404 · outbound

This paper cites Outlier-efficient hopfield layers for large transformer-based models.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Outlier-efficient hopfield layers for large transformer-based models

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.587985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cfa771f1-50e3-45dc-b79c-c9a3bc9aa567 · outbound

This paper cites On computational limits of modern hopfield models: A fine-grained complexity analysis.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency On computational limits of modern hopfield models: A fine-grained complexity analysis

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.564304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9164da7b-66a0-424f-a622-181f7a5031a5 · outbound

This paper cites Provably optimal memory capacity for modern hopfield models: Transformer-compatible dense associative memories as spherical codes.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Provably optimal memory capacity for modern hopfield models: Transformer-compatible dense associative memories as spherical codes

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.549701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3b1ac4ad-c7aa-4f1c-ba97-c8768092c735 · outbound

This paper cites Computational limits of low-rank adaptation (lora) fine-tuning for transformer models.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Computational limits of low-rank adaptation (lora) fine-tuning for transformer models

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.536498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b1a84f20-9463-4eda-80ec-44fbad341e13 · outbound

This paper cites On the complexity of k-sat.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency On the complexity of k-sat

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.523056Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6cc98e31-e040-4aeb-a5cb-5611d0da159b · outbound

This paper cites Dnabert: pre-trained bidirectional encoder representations from transformers model for dna-language in genome.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Dnabert: pre-trained bidirectional encoder representations from transformers model for dna-language in genome

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.243781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed85ed25-7d0e-4bcd-8dab-6c635b2c6547 · outbound

This paper cites Visual prompt tuning.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Visual prompt tuning

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.500444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9092890b-e811-4aa3-a5e3-7074e641d6db · outbound

This paper cites Approximation Rate of the Transformer Architecture for Sequence Modeling.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Approximation Rate of the Transformer Architecture for Sequence Modeling

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.259740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40670459-62d8-4284-9c44-5f733885c8a0 · outbound

This paper cites an unresolved cited work.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-12T13:07:05.486250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f42d89ae-ceaa-4c9a-8b54-47c92826d0be · outbound

This paper cites Optimal memorization capacity of transformers.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Optimal memorization capacity of transformers

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.471637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fcd0e476-f017-430a-8384-c5fa72311341 · outbound

This paper cites Maple: Multi-modal prompt learning.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Maple: Multi-modal prompt learning

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.457367Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7bcfb454-ceb7-4cc2-b826-888e9fcfd2ac · outbound

This paper cites Provable memorization capacity of transformers.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Provable memorization capacity of transformers

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.440184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c3a1d724-c36b-46d0-bb0b-e2024e991b6f · outbound

This paper cites The Power of Scale for Parameter-Efficient Prompt Tuning.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency The Power of Scale for Parameter-Efficient Prompt Tuning

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.284422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2526298-a7ad-4a41-aa84-1cc8ab3e7d1b · outbound

This paper cites When Can We Solve the Weighted Low Rank Approximation Problem in Truly Subquadratic Time?.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency When Can We Solve the Weighted Low Rank Approximation Problem in Truly Subquadratic Time?

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-08-12T13:07:04.939799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 10385b87-cfcd-4b68-bc45-39143f2a3fb0 · outbound

This paper cites Prefix-Tuning: Optimizing Continuous Prompts for Generation.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Prefix-Tuning: Optimizing Continuous Prompts for Generation

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.294833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59df1347-ed96-4ef7-9562-993e2b9892f2 · outbound

This paper cites Towards Infinite-Long Prefix in Transformer.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Towards Infinite-Long Prefix in Transformer

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.299330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecd19aa9-5f76-45af-8173-0115dbcc4ff2 · outbound

This paper cites Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.303699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 606f0501-c905-4218-9924-81eac6f6e9b1 · outbound

This paper cites Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.307992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc76cada-7ad7-4bca-ae0f-5e5f7bfea498 · outbound

This paper cites P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.311930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2cb4b70-ffaf-417d-9031-cd926654ebbb · outbound

This paper cites Memorization Capacity of Multi-Head Attention in Transformers.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Memorization Capacity of Multi-Head Attention in Transformers

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.316421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a820368-a8d1-4cbc-bed5-b9a96d3a73c5 · outbound

This paper cites Large Language Models: A Survey.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Large Language Models: A Survey

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.321592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 966571fa-33d9-4495-b3ec-508f4797a7c3 · outbound

This paper cites Foundation models for generalist medical artificial intelligence.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Foundation models for generalist medical artificial intelligence

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.325844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fa3a54c-9da5-4eb4-a152-f7061ea2b186 · outbound

This paper cites Hyenadna: Long-range genomic sequence modeling at single nucleotide resolution.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Hyenadna: Long-range genomic sequence modeling at single nucleotide resolution

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.329521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbc37238-cd95-4d60-8752-d8fc583be9b7 · outbound

This paper cites On the role of attention in prompt-tuning.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency On the role of attention in prompt-tuning

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.354434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 24a7164f-35bf-4dc1-9217-d6405d8ac9e8 · outbound

This paper cites LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.337542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f736e22-2efd-4d8a-b0cc-f2c3eb7ffedf · outbound

This paper cites Provable memorization via deep neural networks using sub-linear parameters.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Provable memorization via deep neural networks using sub-linear parameters

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.336630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9b9801ab-6f19-4fe0-a4c6-29e6b6978708 · outbound

This paper cites When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.345300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58521379-b214-4147-accf-b03f5b1143f6 · outbound

This paper cites Prompting a Pretrained Transformer Can Be a Universal Approximator.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Prompting a Pretrained Transformer Can Be a Universal Approximator

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.349531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70433061-0f42-4cb4-81da-5c6ed047e6fe · outbound

This paper cites Hopfield Networks is All You Need.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Hopfield Networks is All You Need

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.354607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4fbbb79-cc7c-41ec-93e6-d0a6c22ceba5 · outbound

This paper cites De PT : Decomposed prompt tuning for parameter-efficient fine-tuning.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency De PT : Decomposed prompt tuning for parameter-efficient fine-tuning

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.320006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 67fbbfcd-c09e-44a8-9cc9-c8cacbcdf5df · outbound

This paper cites Why Larger Language Models Do In-context Learning Differently?.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Why Larger Language Models Do In-context Learning Differently?

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.364862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e793fce-85ec-42f4-a522-f108b821feb9 · outbound

This paper cites Large language models encode clinical knowledge.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Large language models encode clinical knowledge

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.369056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cbe3a52-4181-44fc-ad52-ce6dc5e6bc5a · outbound

This paper cites Large language models in medicine.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Large language models in medicine

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.373220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab1ea4ff-0963-47b3-81e8-4a784a57262c · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency LLaMA: Open and Efficient Foundation Language Models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.377199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de97c830-ddce-4657-a8c6-817566b1e0f1 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.381284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f542eeb6-c511-4121-ad40-80329eb98ac3 · outbound

This paper cites Learning Deep Transformer Models for Machine Translation.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Learning Deep Transformer Models for Machine Translation

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.386140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b64a869-5b15-4e50-9716-70991a17f1ed · outbound

This paper cites Universality and limitations of prompt tuning.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Universality and limitations of prompt tuning

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.271850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b7dbc03f-fa21-4e39-89e3-9ef2d0e683b4 · outbound

This paper cites Multitask prompt tuning enables parameter-efficient transfer learning.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Multitask prompt tuning enables parameter-efficient transfer learning

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.254371Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a45b0064-137a-4db2-81aa-f4cecb9cfdea · outbound

This paper cites Larger language models do in-context learning differently.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Larger language models do in-context learning differently

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.398193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8184bdd4-7580-4a83-864f-4d136ba084ec · outbound

This paper cites Hard prompts made easy: Gradient-based discrete optimization for prompt tuning and discovery.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Hard prompts made easy: Gradient-based discrete optimization for prompt tuning and discovery

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.402299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62f4e85e-53b2-46d9-8530-2a0603afc9a2 · outbound

This paper cites On some fine-grained questions in algorithms and complexity.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency On some fine-grained questions in algorithms and complexity

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.219855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 763e6db7-182c-4b87-8c9a-8582e7005e1f · outbound

This paper cites Uniform memory retrieval with larger capacity for modern hopfield models.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Uniform memory retrieval with larger capacity for modern hopfield models

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.202646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d986a35e-2609-4f4a-b27e-2f142148c696 · outbound

This paper cites Stanhop: Sparse tandem hopfield model for memory-enhanced time series prediction.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Stanhop: Sparse tandem hopfield model for memory-enhanced time series prediction

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.185680Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 30c4ff04-c8c6-4d35-8683-00a306cde251 · outbound

This paper cites BloombergGPT: A Large Language Model for Finance.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency BloombergGPT: A Large Language Model for Finance

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.418264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86c881b0-2761-4d90-ba7d-f709617dde69 · outbound

This paper cites On layer normalization in the transformer architecture.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency On layer normalization in the transformer architecture

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.169031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b3ce10b1-ef14-428a-81a2-6fb574ed8115 · outbound

This paper cites Do large language models have compositional ability? an investigation into limitations and scalability.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Do large language models have compositional ability? an investigation into limitations and scalability

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.155166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5f58862a-4844-456c-8c97-07ec7c4a6048 · outbound

This paper cites Fingpt: Open-source financial large language models.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Fingpt: Open-source financial large language models

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.430689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47273abd-2f64-481a-90e1-94f117b6a010 · outbound

This paper cites Are transformers universal approximators of sequence-to-sequence functions? In International Conference on Learning Representations (ICLR), 2020.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Are transformers universal approximators of sequence-to-sequence functions? In International Conference on Learning Representations (ICLR), 2020

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.134495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 65134c16-a04b-40d5-a7eb-7f3a94dcddf1 · outbound

This paper cites LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.438638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08a27a26-d261-4102-a522-af5be2970db8 · outbound

This paper cites DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genome.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genome

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.442804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39e7c5b8-b543-471e-ad0f-167ec5b624e6 · outbound

This paper cites DNABERT-S: Pioneering Species Differentiation with Species-Aware DNA Embeddings.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency DNABERT-S: Pioneering Species Differentiation with Species-Aware DNA Embeddings

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.447314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1dc3827b-ee5d-4219-921c-27bc0fe2e7d3 · outbound

This paper cites Genomeocean: An efficient genome foundation model trained on large-scale metagenomic assemblies.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Genomeocean: An efficient genome foundation model trained on large-scale metagenomic assemblies

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.451726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fccf3696-b493-4059-82bf-b1ac42c47063 · outbound

This paper cites @esa (Ref.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency @esa (Ref

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.456075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac0f97d7-febe-4411-bb05-9bfff571ef9a · outbound

This paper cites an unresolved cited work.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency Unresolved cited work

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-12T13:07:04.460845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e37165d-1f82-4772-ac9c-c0615e1a98ec · outbound

This paper cites The authors also thank the authors of wang2024universality for their clarifications, and thank the anonymous reviewers and program chairs for constructive comments.

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency The authors also thank the authors of wang2024universality for their clarifications, and thank the anonymous reviewers and program chairs for constructive comments

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T13:07:05.091878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Pith citing papers

Observation 4bec54fc-7eb3-4491-a94f-5a4fa5a76441 · inbound

On Statistical Rates of Conditional Diffusion Transformers: Approximation, Estimation and Minimax Optimality cites this paper.

On Statistical Rates of Conditional Diffusion Transformers: Approximation, Estimation and Minimax Optimality Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T12:06:13.422429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e727fbf-f98f-4e48-834c-6dee3f2f25f5 · inbound

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond cites this paper.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.901765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02f76022-7d7e-41ca-a9bd-aeb60fc5832f · inbound

Circuit Complexity Bounds for Visual Autoregressive Model cites this paper.

Circuit Complexity Bounds for Visual Autoregressive Model Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T21:42:46.258192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a4fceec-ddc9-4c56-968a-f85de8a9c26d · inbound

Video Latent Flow Matching: Optimal Polynomial Projections for Video Interpolation and Extrapolation cites this paper.

Video Latent Flow Matching: Optimal Polynomial Projections for Video Interpolation and Extrapolation Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-09T18:51:12.471856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2711a5c6-4232-449a-b24c-059d00dcfd1e · inbound

High-Order Matching for One-Step Shortcut Diffusion Models cites this paper.

High-Order Matching for One-Step Shortcut Diffusion Models Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-09T18:10:53.069659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4b2a72f-3a03-4ee5-b9ed-06a00ebbe1dc · inbound

Universal Approximation of Visual Autoregressive Transformers cites this paper.

Universal Approximation of Visual Autoregressive Transformers Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-08T16:39:14.179374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40da8e62-187c-4710-9db4-8d29428e96b5 · inbound

Transformer Approximations from ReLUs cites this paper.

Transformer Approximations from ReLUs Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:51:30.210788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.