{"total":36,"rows":[{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939,"area":null},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"id":"2103.03404","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","created":"2021-03-05","cited_by_count":419,"area":null},{"id":"2112.10668","title":"Few-shot Learning with Multilingual Language Models","created":"2021-12-20","cited_by_count":278,"area":null},{"id":"2203.03540","title":"GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records","created":"2022-02-02","cited_by_count":238,"area":null},{"id":"2109.07740","title":"Scaling Laws for Neural Machine Translation","created":"2021-09-16","cited_by_count":111,"area":null},{"id":"2210.15424","title":"What Language Model to Train if You Have One Million GPU Hours?","created":"2022-10-27","cited_by_count":92,"area":null},{"id":"2302.06015","title":"A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity","created":"2023-02-12","cited_by_count":77,"area":null},{"id":"2306.13596","title":"Max-Margin Token Selection in Attention Mechanism","created":"2023-06-23","cited_by_count":58,"area":null},{"id":"2412.02975","title":"Theoretical limitations of multi-layer Transformer","created":"2024-12-04","cited_by_count":45,"area":null},{"id":"2102.09972","title":"Implicit Regularization in Tensor Factorization","created":"2021-02-19","cited_by_count":44,"area":null},{"id":"2110.06821","title":"Leveraging redundancy in attention with Reuse Transformers","created":"2021-10-13","cited_by_count":33,"area":null},{"id":"2305.18475","title":"Approximation Rate of the Transformer Architecture for Sequence Modeling","created":"2023-05-29","cited_by_count":28,"area":null},{"id":"2201.11729","title":"Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks","created":"2022-01-27","cited_by_count":27,"area":null},{"id":"2202.00528","title":"Examining Scaling and Transfer of Language Model Architectures for Machine Translation","created":"2022-02-01","cited_by_count":26,"area":null},{"id":"2105.03928","title":"Which transformer architecture fits my data? A vocabulary bottleneck in self-attention","created":"2021-05-09","cited_by_count":16,"area":null},{"id":"2302.03848","title":"Controlling Personality Style in Dialogue with Zero-Shot Prompt-Based Learning","created":"2023-02-08","cited_by_count":14,"area":null},{"id":"2211.16494","title":"On the Ability of Graph Neural Networks to Model Interactions Between Vertices","created":"2022-11-29","cited_by_count":12,"area":null},{"id":"2102.05628","title":"On the Regularity of Attention","created":"2021-02-10","cited_by_count":11,"area":null},{"id":"2503.21023","title":"Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework","created":"2025-03-26","cited_by_count":9,"area":null},{"id":"2502.17356","title":"Random Scaling of Emergent Capabilities","created":"2025-02-24","cited_by_count":7,"area":null},{"id":"2308.05749","title":"Introducing Hybrid Modeling with Time-series-Transformers: A Comparative Study of Series and Parallel Approach in Batch Crystallization","created":"2023-07-25","cited_by_count":5,"area":null},{"id":"2505.20802","title":"Leaner Transformers: More Heads, Less Depth","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2301.04605","title":"Exploring the Approximation Capabilities of Multiplicative Neural Networks for Smooth Functions","created":"2023-01-11","cited_by_count":4,"area":null},{"id":"2306.03099","title":"CrystalGPT: Enhancing system-to-system transferability in crystallization prediction and control using time-series-transformers","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2605.08297","title":"A Qualitative Test-Risk Mechanism for Scaling Behavior in Normalized Residual Networks","created":"2026-05-08","cited_by_count":4,"area":null},{"id":"2601.20994","title":"The Depth Delusion: Why Transformers Should Be Wider, Not Deeper","created":"2026-01-28","cited_by_count":2,"area":null},{"id":"2609.19107","title":"How Model Growth, Recursion, and Boundary Operators Influence Scaling Exponents","created":"2026-09-16","cited_by_count":2,"area":null},{"id":"2510.20386","title":"NeoDictaBERT: Pushing the Frontier of BERT models for Hebrew","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2606.18246","title":"Variable-Width Transformers","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2609.32534","title":"DepthBench: Measuring How Residual Connections Enable More Computational Depth","created":"2026-09-26","cited_by_count":1,"area":null},{"id":"2208.08191","title":"Transformer Vs. MLP-Mixer: Exponential Expressive Gap For NLP Problems","created":"2022-08-17","cited_by_count":0,"area":null},{"id":"2604.14702","title":"Gating Enables Curvature: A Geometric Expressivity Gap in Attention","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2607.13929","title":"VAIOM: Continuous-Input, Discrete-Output Decoder-Only Financial Sequence Modeling","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2608.14664","title":"Quantifying Depth Sufficiency in Residual Neural Networks: A First-Order Criterion","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2610.06784","title":"How to scale your HEP ML models: A recipe for robust architecture comparisons at scale","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}