The paper introduces Market‑1T, a massive dataset of nearly one trillion 1‑Hz observations of U.S. equities spanning 2008‑2025, and establishes a rigorous evaluation protocol for financial representation learning. It conducts a large‑scale comparison of 18 encoder‑training strategies across two decades of market regimes, assessing their predictive performance on common finance tasks and probing latent structure. The study reveals that encoders with similar predictive accuracy can organize market state in markedly different ways, providing a foundation for training and evaluating representations for financial world models such as DINO‑WM, V‑JEPA 2, and LeWM.
By Humzah Merchant, Alec Guthrie, Simon Mahns, Randall Balestriero, Bradford Levy
arXiv:2609.04239v2 Announce Type: replace
Abstract: This technical report presents EXAONE Forecast for Finance (EXAONE Finance), a financial time series foundation model (TSFM) tailored to financial...
By Seunghan Lee, Jaehoon Lee, Jun Seo, Tae Yoon Lim, Dongwan Kang, Hwanil Choi, Minjae Kim, Sungdong Yoo, Junhyeok Kang, Sangjun Han, Soonyoung Lee, Wonbin Ahn
EXAONE Forecast for Finance (EXAONE Finance) is a financial time‑series foundation model designed to overcome the limitations of existing models that rely on self‑attention and assume fully observed data. It replaces self‑attention with a causal 1D convolution for temporal mixing and a group‑aware pooling MLP for variate mixing, achieving linear‑time complexity. The model is pretrained on a large, diverse financial corpus and, through masked context augmentation, learns to handle missing data, ultimately topping the FinVerse benchmark across accuracy, ranking, and profitability metrics.
By Seunghan Lee, Jaehoon Lee, Jun Seo, Tae Yoon Lim, Dongwan Kang, Hwanil Choi, Minjae Kim, Sungdong Yoo, Junhyeok Kang, Sangjun Han, Soonyoung Lee, Wonbin Ahn
arXiv:2605.28853v2 Announce Type: replace-cross
Abstract: Portfolio optimization in real-world financial markets is notoriously difficult due to non-stationarity, noisy data, and high transaction cos...
By Rahul Fernandes, Travis Desell
arXiv:2606. 09104v1 Announce Type: cross Abstract: Deep reinforcement learning (DRL) frameworks for portfolio optimization have shown promise for their ability to learn allocation rules dynamically from market data.
By Daniil Mikriukov (University of Liverpool, Xi'an Jiaotong-Liverpool University), Ruoyu Sun (Xi'an Jiaotong-Liverpool University), Angelos Stefanidis (Xi'an Jiaotong-Liverpool University), Jionglong Su (Xi'an Jiaotong-Liverpool University), Zhengyong Jiang (Xi'an Jiaotong-Liverpool University)
The paper introduces Future‑Aligned Soft Contrastive Learning (FASCL), a representation learning framework that uses pairwise future return correlations as continuous supervision to improve asset retrieval. FASCL’s soft contrastive loss aligns retrieved assets with correlated future returns, and the authors propose a new evaluation protocol to directly assess future trajectory similarity. Experiments on 5,631 US‑listed securities outperform 14 baselines in future return correlation, rank information coefficient, trend consistency, and gross Sharpe ratio across various retrieval depths and basket sizes.
By Hyeongmin Lee, Chanyeol Choi, Jihoon Kwon, Yoon Kim, Alejandro Lopez-Lira, Wonbin Ahn, Justin Xu, Srijan Sood, Qingsong Wen, Chun-Li Yang, Yongjae Lee
The paper explores optimal trading under partial information, modeling the trading signal as an Ornstein‑Uhlenbeck process with regime switching. It proposes three reinforcement‑learning approaches that integrate recurrent neural networks to filter latent market regimes, comparing a one‑step method and two two‑step methods that use posterior regime probabilities or signal forecasts. Simulations and an equity pairs‑trading case study show that using posterior probability estimates of the latent regime yields the best cumulative rewards and more interpretable strategies.
By Andrea Macr\`i, Sebastian Jaimungal, Fabrizio Lillo
arXiv:2606. 06823v1 Announce Type: cross Abstract: While deep learning has excelled in various domains, its application to sequential decision-making in finance remains challenging due to the low Signal-to-Noise Ratio (SNR) and non-stationarity of financial data.
By Yuqi Li, Siyuan Liu, Bingjun Liu
The paper addresses look‑ahead bias in large language models (LLMs) used for financial prediction, which arises because LLMs are trained on long time‑series data. It proposes a low‑cost solution that adjusts the logits of a base model at inference time using two smaller, specialized models—one fine‑tuned to forget certain information and another to retain it. Experiments show that this method removes both verbatim and semantic knowledge, corrects biases, and outperforms previous approaches.
By Humzah Merchant, Bradford Levy
arXiv:2608. 27076v1 Announce Type: new Abstract: Algorithmic trading now represents a market exceeding $20 billion, where even marginal gains in signal robustness can translate into economically significant returns.
By Joshua Le Grice
arXiv:2602. 03395v4 Announce Type: replace Abstract: While deep learning has revolutionized financial forecasting through sophisticated architectures, the design of the supervision signal itself is rarely scrutinized.
By Chen-Hui Song, Shuoling Liu, Liyuan Chen
arXiv:2508. 19006v2 Announce Type: replace-cross Abstract: This study investigates the pre-trained RNN attention models with the mainstream attention mechanisms, such as additive attention, Luong's three attentions, global self-attention and sliding window sparse attention, for the empirical asset pricing research on the top 420 large-cap US stocks.
By Shanyan Lai