Jianfei Zhang

Mathieu Rosenbaum, Jianfei Zhang

We train an LSTM network based on a pooled dataset made of hundreds of liquid stocks aiming to forecast the next daily realized volatility for all stocks. Showing the consistent outperformance of this universal LSTM relative to other asset-specific parametric models, we uncover nonparametric evidences of a universal volatility formation mechanism across assets relating past market realizations, including daily returns and volatilities, to current volatilities. A parsimonious parametric forecasting device combining the rough fractional stochastic volatility and quadratic rough Heston models with fixed parameters results in the same level of performance as the universal LSTM, which confirms the universality of the volatility formation process from a parametric perspective.

Jianfei Zhang, Mathieu Rosenbaum

News can convey bearish or bullish views on financial assets. Institutional investors need to evaluate automatically the implied news sentiment based on textual data. Given the huge amount of news articles published each day, most of which are neutral, we present a systematic news screening method to identify the ``true'' impactful ones, aiming for more effective development of news sentiment learning methods. Based on several liquidity-driven variables, including volatility, turnover, bid-ask spread, and book size, we associate each 5-min time bin to one of two specific liquidity modes. One represents the ``calm'' state at which the market stays for most of the time and the other, featured with relatively higher levels of volatility and trading volume, describes the regime driven by some exogenous events. Then we focus on the moments where the liquidity mode switches from the former to the latter and consider the news articles published nearby impactful. We apply naive Bayes on these filtered samples for news sentiment classification as an illustrative example. We show that the screened dataset leads to more effective feature capturing and thus superior performance on short-term asset return prediction compared to the original dataset.

Meituan LongCat Team, Anchun Gui, Bei Li et al.

We present LongCat-Flash-Thinking, an efficient 560-billion-parameter open-source Mixture-of-Experts (MoE) reasoning model. Its advanced capabilities are cultivated through a meticulously crafted training process, beginning with long Chain-of-Thought (CoT) data cold-start and culminating in large-scale Reinforcement Learning (RL). We first employ a well-designed cold-start training strategy, which significantly enhances the reasoning potential and equips the model with specialized skills in both formal and agentic reasoning. Then, a core innovation is our domain-parallel training scheme, which decouples optimization across distinct domains (e.g., STEM, Code, Agentic) and subsequently fuses the resulting expert models into a single, nearly Pareto-optimal model. This entire process is powered by our Dynamic ORchestration for Asynchronous rollout (DORA) system, a large-scale RL framework that delivers a greater than threefold training speedup over synchronous methods on tens of thousands of accelerators. As a result, LongCat-Flash-Thinking achieves state-of-the-art performance among open-source models on a suite of complex reasoning tasks. The model exhibits exceptional efficiency in agentic reasoning, reducing average token consumption by 64.5% (from 19, 653 to 6, 965) on AIME-25, without degrading task accuracy. We release LongCat-Flash-Thinking to promote further advances in reasoning systems and agentic AI research.

Qi Guo, Jianing Wang, Jianfei Zhang et al.

Autoformalization addresses the scarcity of data for Automated Theorem Proving (ATP) by translating mathematical problems from natural language into formal statements. Efforts in recent work shift from directly prompting large language models to training an end-to-end formalizer model from scratch, achieving remarkable advancements. However, existing formalizer still struggles to consistently generate valid statements that meet syntactic validity and semantic consistency. To address this issue, we propose the Autoformalizer with Tool Feedback (ATF), a novel approach that incorporates syntactic and consistency information as tools into the formalization process. By integrating Lean 4 compilers for syntax corrections and employing a multi-LLMs-as-judge approach for consistency validation, the model is able to adaptively refine generated statements according to the tool feedback, enhancing both syntactic validity and semantic consistency. The training of ATF involves a cold-start phase on synthetic tool-calling data, an expert iteration phase to improve formalization capabilities, and Direct Preference Optimization to alleviate ineffective revisions. Experimental results show that ATF markedly outperforms a range of baseline formalizer models, with its superior performance further validated by human evaluations. Subsequent analysis reveals that ATF demonstrates excellent inference scaling properties. Moreover, we open-source Numina-ATF, a dataset containing 750K synthetic formal statements to facilitate advancements in autoformalization and ATP research.

Zehan Li, Jianfei Zhang, Chuantao Yin et al.

Retrieval-based code question answering seeks to match user queries in natural language to relevant code snippets. Previous approaches typically rely on pretraining models using crafted bi-modal and uni-modal datasets to align text and code representations. In this paper, we introduce ProCQA, a large-scale programming question answering dataset extracted from the StackOverflow community, offering naturally structured mixed-modal QA pairs. To validate its effectiveness, we propose a modality-agnostic contrastive pre-training approach to improve the alignment of text and code representations of current code language models. Compared to previous models that primarily employ bimodal and unimodal pairs extracted from CodeSearchNet for pre-training, our model exhibits significant performance improvements across a wide range of code retrieval benchmarks.