---
title: Track record
url: https://www.ml-quant.com/track-record/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
---


# Track record

What became of every paper Quant Letter featured: citations and journal publications from Semantic Scholar, refreshed weekly.

- Finance papers featured when new: 2396
- Now published (of those featured at least a year ago): 26%
- Cited 100+ times: 10
- Median days from release to feature: 5.0

## We called it: most cited, featured within two weeks of release

- [FinGPT: Open-Source Financial Large Language Models](https://arxiv.org/abs/2306.06031): 492 citations; featured 2023-06-14, 5 days after release; not yet published
- [FinMem: A Performance-Enhanced LLM Trading Agent With Layered Memory and Character Design](https://arxiv.org/abs/2311.13743): 253 citations; featured 2023-11-29, 6 days after release; IEEE Transactions on Big Data
- [HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction](https://arxiv.org/abs/2408.04948): 231 citations; featured 2024-08-15, 6 days after release; Proceedings of the 5th ACM International Conference on AI in Finance
- [TradingAgents: Multi-Agents LLM Financial Trading Framework](http://arxiv.org/abs/2412.20138v1): 220 citations; featured 2025-01-01, 4 days after release; not yet published
- [TKAN: Temporal Kolmogorov-Arnold Networks](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4825654): 189 citations; featured 2024-05-15, 3 days after release; not yet published
- [Instruct-FinGPT: Financial Sentiment Analysis by Instruction Tuning of General-Purpose Large Language Models](https://arxiv.org/abs/2306.12659): 140 citations; featured 2023-06-28, 6 days after release; not yet published
- [Designing Heterogeneous LLM Agents for Financial Sentiment Analysis](http://arxiv.org/abs/2401.05799): 138 citations; featured 2024-01-17, 6 days after release; ACM Transactions on Management Information Systems
- [FinGPT: Democratizing Internet-scale Data for Financial Large Language Models](https://arxiv.org/abs/2307.10485): 124 citations; featured 2023-07-26, 7 days after release; not yet published
- [Trillion Dollar Words: A New Financial Dataset, Task & Market Analysis](https://arxiv.org/abs/2305.07972): 106 citations; featured 2023-05-18, 5 days after release; Annual Meeting of the Association for Computational Linguistics
- [ESG Reputation Risk Matters: An Event Study Based on Social Media Data](https://arxiv.org/abs/2307.11571): 106 citations; featured 2023-07-26, 5 days after release; not yet published
- [A Scoping Review of ChatGPT Research in Accounting and Finance](http://dx.doi.org/10.1016/j.accinf.2024.100715): 99 citations; featured 2024-12-12, 11 days after release; International Journal of Accounting Information Systems
- [The Global Governance of Artificial Intelligence: Next Steps for Empirical and Normative Research](https://arxiv.org/abs/2305.11528): 97 citations; featured 2023-05-24, 5 days after release; not yet published

## Now out in journals

- [Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Models](https://arxiv.org/abs/2402.03659): Proceedings of the ACM Web Conference 2024, 83 citations
- [Alpha-GPT: Human-AI Interactive Alpha Mining for Quantitative Investment](https://arxiv.org/abs/2308.00016): Conference on Empirical Methods in Natural Language Processing, 81 citations
- [Using Large Language Models for Qualitative Analysis can Introduce Serious Bias](https://arxiv.org/abs/2309.17147): Sociological Methods & Research, 78 citations
- [LSTM-ARIMA as a hybrid approach in algorithmic investment strategies](https://arxiv.org/abs/2406.18206): Knowl. Based Syst., 61 citations
- [Extracting Financial Data from Unstructured Sources: Leveraging Large Language Models](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4567607): J. Inf. Syst., 51 citations
- [Attention-based Dynamic Multilayer Graph Neural Networks for Loan Default Prediction](https://arxiv.org/abs/2402.00299): European Journal of Operational Research, 49 citations
- [ChatGPT-Based Investment Portfolio Selection](https://arxiv.org/abs/2308.06260): Operations Research Forum, 46 citations
- [Bubble economics](https://arxiv.org/abs/2311.03638): Journal of Mathematical Economics, 43 citations
- [Enhancing Investment Analysis: Optimizing AI-Agent Collaboration in Financial Research](http://arxiv.org/abs/2411.04788v1): Proceedings of the 5th ACM International Conference on AI in Finance, 42 citations
- [Energy Security and Resilience: Reviewing Concepts and Advancing Planning Perspectives for Transforming Integrated Energy Systems](http://arxiv.org/abs/2504.18396v1): Energy Policy, 42 citations

## Most cited featured papers

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://arxiv.org/pdf/2312.00752.pdf): 9205 citations (preprint), featured 2024-06-05
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://arxiv.org/abs/2402.03300): 9003 citations (preprint), featured 2024-02-07
- [Mistral 7B](https://arxiv.org/abs/2310.06825): 3920 citations (preprint), featured 2023-10-16
- [Depth Anything V2](https://arxiv.org/abs/2406.09414): 2228 citations (Neural Information Processing Systems), featured 2024-06-20
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://arxiv.org/abs/2406.01574): 2199 citations (Neural Information Processing Systems), featured 2024-10-09
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://arxiv.org/abs/2408.03314): 2189 citations (preprint), featured 2024-08-07
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://arxiv.org/abs/2405.21060): 1953 citations (International Conference on Machine Learning), featured 2024-06-05
- [Octo: An Open-Source Generalist Robot Policy](https://arxiv.org/abs/2405.12213): 1880 citations (Robotics: Science and Systems Conference), featured 2024-05-22
- [AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration](https://arxiv.org/abs/2306.00978): 1800 citations (GetMobile: Mobile Computing and Communications), featured 2024-07-24
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://arxiv.org/abs/2412.05271): 1775 citations (preprint), featured 2024-12-12
- [Qwen2.5-Coder Technical Report](https://arxiv.org/abs/2409.12186): 1558 citations (preprint), featured 2024-09-25
- [s1: Simple test-time scaling](https://arxiv.org/pdf/2501.19393): 1462 citations (Conference on Empirical Methods in Natural Language Processing), featured 2025-02-05
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://arxiv.org/abs/2405.04434): 1459 citations (preprint), featured 2024-05-22
- [Mastering Diverse Domains through World Models](https://arxiv.org/abs/2301.04104): 1418 citations (preprint), featured 2024-04-24
- [MemGPT: Towards LLMs as Operating Systems](https://arxiv.org/abs/2310.08560): 1373 citations (preprint), featured 2023-10-16
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](http://dx.doi.org/10.48550/arxiv.2303.08896): 1236 citations (Conference on Empirical Methods in Natural Language Processing), featured 2023-10-16
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://arxiv.org/abs/2405.14734): 1173 citations (Neural Information Processing Systems), featured 2024-07-10
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://arxiv.org/abs/2404.02905): 1169 citations (Neural Information Processing Systems), featured 2024-06-12
- [A Simple and Effective Pruning Approach for Large Language Models](https://arxiv.org/pdf/2306.11695.pdf): 981 citations (International Conference on Learning Representations), featured 2024-05-08
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://arxiv.org/abs/2310.00426): 967 citations (International Conference on Learning Representations), featured 2024-01-03
- [TinyLlama: An Open-Source Small Language Model](https://arxiv.org/abs/2401.02385): 902 citations (preprint), featured 2024-01-09
- [TÜLU 3: Pushing Frontiers in Open Language Model Post-Training](https://arxiv.org/abs/2411.15124): 888 citations (preprint), featured 2025-02-05
- [Simple and Effective Masked Diffusion Language Models](https://arxiv.org/abs/2406.07524): 850 citations (Neural Information Processing Systems), featured 2024-06-12
- [Training Large Language Models to Reason in a Continuous Latent Space](https://arxiv.org/abs/2412.06769): 742 citations (preprint), featured 2024-12-12
- [Fourier Neural Operator with Learned Deformations for PDEs on General Geometries](https://arxiv.org/abs/2207.05209): 727 citations (J. Mach. Learn. Res.), featured 2024-05-08
- [KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization](https://arxiv.org/abs/2401.18079): 701 citations (Neural Information Processing Systems), featured 2024-04-10
- [FAST: Efficient Action Tokenization for Vision-Language-Action Models](https://arxiv.org/abs/2501.09747): 673 citations (Robotics), featured 2025-01-23
- [LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS](https://arxiv.org/abs/2311.17245): 660 citations (Neural Information Processing Systems), featured 2024-04-03
- [Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting](https://arxiv.org/pdf/2310.10642.pdf): 627 citations (International Conference on Learning Representations), featured 2023-10-18
- [Scalable Extraction of Training Data from (Production) Language Models](https://arxiv.org/abs/2311.17035): 619 citations (preprint), featured 2023-12-06
- [Ferret: Refer and Ground Anything Anywhere at Any Granularity](https://arxiv.org/abs/2310.07704): 604 citations (International Conference on Learning Representations), featured 2023-10-16
- [BLINK: Multimodal Large Language Models Can See but Not Perceive](https://arxiv.org/pdf/2404.12390.pdf): 603 citations (European Conference on Computer Vision), featured 2024-04-24
- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://arxiv.org/abs/2311.18259): 603 citations (2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)), featured 2024-05-01
- [Continuous 3D Perception Model with Persistent State](https://arxiv.org/abs/2501.12387): 593 citations (2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)), featured 2025-01-23
- [Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks](https://arxiv.org/abs/2404.02151): 580 citations (International Conference on Learning Representations), featured 2024-06-20
- [TOFU: A Task of Fictitious Unlearning for LLMs](https://arxiv.org/abs/2401.06121): 579 citations (preprint), featured 2024-01-17
- [FateZero: Fusing Attentions for Zero-shot Text-based Video Editing](https://arxiv.org/abs/2303.09535): 574 citations (2023 IEEE/CVF International Conference on Computer Vision (ICCV)), featured 2023-10-16
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://arxiv.org/abs/2305.00050): 571 citations (Trans. Mach. Learn. Res.), featured 2024-08-21
- [LlaVA-CoT: Let Vision Language Models Reason Step-By-Step](https://arxiv.org/abs/2411.10440): 566 citations (2025 IEEE/CVF International Conference on Computer Vision (ICCV)), featured 2024-11-20
- [Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models](https://arxiv.org/abs/2405.01535): 541 citations (Conference on Empirical Methods in Natural Language Processing), featured 2024-05-08
- [Gated Linear Attention Transformers with Hardware-Efficient Training](https://arxiv.org/abs/2312.06635): 539 citations (International Conference on Machine Learning), featured 2023-12-13
- [Llemma: An Open Language Model For Mathematics](https://arxiv.org/abs/2310.10631): 497 citations (International Conference on Learning Representations), featured 2023-10-18
- [FinGPT: Open-Source Financial Large Language Models](https://arxiv.org/abs/2306.06031): 492 citations (preprint), featured 2023-06-14
- [CAT3D: Create Anything in 3D with Multi-View Diffusion Models](http://arxiv.org/abs/2405.10314): 482 citations (Neural Information Processing Systems), featured 2024-05-22
- [Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation](https://arxiv.org/abs/2410.13848): 481 citations (2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)), featured 2024-10-23
- [Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model](https://arxiv.org/abs/2408.11039): 480 citations (preprint), featured 2024-08-21
- [SliceGPT: Compress Large Language Models by Deleting Rows and Columns](https://arxiv.org/abs/2401.15024): 466 citations (International Conference on Learning Representations), featured 2024-01-30
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://arxiv.org/abs/2406.20094): 466 citations (preprint), featured 2024-07-03
- [Training Language Models to Self-Correct via Reinforcement Learning](https://arxiv.org/abs/2409.12917): 460 citations (International Conference on Learning Representations), featured 2024-10-09
- [Capabilities of Gemini Models in Medicine](https://arxiv.org/abs/2404.18416): 446 citations (preprint), featured 2024-05-08
- [An Embodied Generalist Agent in 3D World](https://arxiv.org/abs/2311.12871): 443 citations (International Conference on Machine Learning), featured 2024-05-15
- [The Platonic Representation Hypothesis](https://arxiv.org/abs/2405.07987): 429 citations (International Conference on Machine Learning), featured 2024-05-15
- [NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking](http://arxiv.org/abs/2406.15349v1): 425 citations (Neural Information Processing Systems), featured 2024-11-06
- [PGSR: Planar-Based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction](https://arxiv.org/pdf/2406.06521): 415 citations (IEEE Transactions on Visualization and Computer Graphics), featured 2024-06-12
- [Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models](http://dx.doi.org/10.2139/ssrn.4412788): 403 citations (preprint), featured 2023-07-05
- [RAFT: Adapting Language Model to Domain Specific RAG](https://arxiv.org/abs/2403.10131): 401 citations (preprint), featured 2024-06-12
- [Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models](https://arxiv.org/abs/2501.01423): 395 citations (2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)), featured 2025-01-08
- [Data Selection for Language Models via Importance Resampling](https://arxiv.org/abs/2302.03169): 371 citations (Neural Information Processing Systems), featured 2023-10-25
- [To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning](https://arxiv.org/abs/2409.12183): 371 citations (International Conference on Learning Representations), featured 2024-09-25
- [OminiControl: Minimal and Universal Control for Diffusion Transformer](https://arxiv.org/abs/2411.15098): 370 citations (2025 IEEE/CVF International Conference on Computer Vision (ICCV)), featured 2024-11-27

All rows: https://www.ml-quant.com/api/v1/track-record.json