Yifan Dong

Yifan Dong, Suhang Wu, Fandong Meng et al. · tsinghua

Multi-modal keyphrase generation aims to produce a set of keyphrases that represent the core points of the input text-image pair. In this regard, dominant methods mainly focus on multi-modal fusion for keyphrase generation. Nevertheless, there are still two main drawbacks: 1) only a limited number of sources, such as image captions, can be utilized to provide auxiliary information. However, they may not be sufficient for the subsequent keyphrase generation. 2) the input text and image are often not perfectly matched, and thus the image may introduce noise into the model. To address these limitations, in this paper, we propose a novel multi-modal keyphrase generation model, which not only enriches the model input with external knowledge, but also effectively filters image noise. First, we introduce external visual entities of the image as the supplementary input to the model, which benefits the cross-modal semantic alignment for keyphrase generation. Second, we simultaneously calculate an image-text matching score and image region-text correlation scores to perform multi-granularity image noise filtering. Particularly, we introduce the correlation scores between image regions and ground-truth keyphrases to refine the calculation of the previously-mentioned correlation scores. To demonstrate the effectiveness of our model, we conduct several groups of experiments on the benchmark dataset. Experimental results and in-depth analyses show that our model achieves the state-of-the-art performance. Our code is available on https://github.com/DeepLearnXMU/MM-MKP.

Hünkar Can Tun, Yifan Dong, Andreas Pavlogiannis

Atomicity is a fundamental abstraction in concurrency, specifying that program behavior can be understood by considering specific code blocks executing atomically. However, atomicity invariants are tricky to maintain while also optimizing for code efficiency, and atomicity violations are a common root cause of many concurrency bugs. To address this problem, several dynamic techniques have been developed for testing whether a program execution adheres to an atomicity specification, most often instantiated as \emph{conflict serializability}. The efficiency of the analysis has been targeted in various papers, with the state-of-the-art algorithms \textsc{RegionTrack} and \textsc{Aerodrome} achieving a time complexity $O(nk^3)$ and $O(nk(k + v + \ell))$, respectively, for a trace $σ$ of $n$ events, $k$ threads, $v$ locations, and $\ell$ locks. In this paper we introduce \textsc{AtomSanitizer}, a new algorithm for testing conflict serializability, with time complexity $O(nk^2)$. \textsc{AtomSanitizer} operates in an efficient streaming style, is theoretically faster than all existing algorithms, and also has a smaller memory footprint. Moreover, \textsc{AtomSanitizer} is the first algorithm designed to incur minimal locking when deployed in a concurrent monitoring setting. Experiments on standard benchmarks indicate that \textsc{AtomSanitizer} is always faster in practice than all existing conflict-serializability testers. Finally, we also implement \textsc{AtomSanitizer} inside the TSAN framework, for monitoring atomicity in real time. Our experiments reveal that \textsc{AtomSanitizer} incurs minimal time and space overhead compared to the data-race detection engine of TSAN, and thus is the first algorithm for conflict serializability demonstrated to be suitable for a runtime monitoring setting.

Jun Han, Shuo Zhang, Wei Li et al.

Financial markets are noisy and non-stationary, making alpha mining highly sensitive to noise in backtesting results and sudden market regime shifts. While recent agentic frameworks improve alpha mining automation, they often lack controllable multi-round search and reliable reuse of validated experience. To address these challenges, we propose QuantaAlpha, an evolutionary alpha mining framework that treats each end-to-end mining run as a trajectory and improves factors through trajectory-level mutation and crossover operations. QuantaAlpha localizes suboptimal steps in each trajectory for targeted revision and recombines complementary high-reward segments to reuse effective patterns, enabling structured exploration and refinement across mining iterations. During factor generation, QuantaAlpha enforces semantic consistency across the hypothesis, factor expression, and executable code, while constraining the complexity and redundancy of the generated factor to mitigate crowding. Extensive experiments on the China Securities Index 300 (CSI 300) demonstrate consistent gains over strong baseline models and prior agentic systems. When utilizing GPT-5.2, QuantaAlpha achieves an Information Coefficient (IC) of 0.1501, with an Annualized Rate of Return (ARR) of 27.75% and a Maximum Drawdown (MDD) of 7.98%. Moreover, factors mined on CSI 300 transfer effectively to the China Securities Index 500 (CSI 500) and the Standard & Poor's 500 Index (S&P 500), delivering 160% and 137% cumulative excess return over four years, respectively, which indicates strong robustness of QuantaAlpha under market distribution shifts.

Lingfeng Zeng, Fangqi Lou, Zixuan Wang et al.

The booming development of AI agents presents unprecedented opportunities for automating complex tasks across various domains. However, their multi-step, multi-tool collaboration capabilities in the financial sector remain underexplored. This paper introduces FinGAIA, an end-to-end benchmark designed to evaluate the practical abilities of AI agents in the financial domain. FinGAIA comprises 407 meticulously crafted tasks, spanning seven major financial sub-domains: securities, funds, banking, insurance, futures, trusts, and asset management. These tasks are organized into three hierarchical levels of scenario depth: basic business analysis, asset decision support, and strategic risk management. We evaluated 10 mainstream AI agents in a zero-shot setting. The best-performing agent, ChatGPT, achieved an overall accuracy of 48.9\%, which, while superior to non-professionals, still lags financial experts by over 35 percentage points. Error analysis has revealed five recurring failure patterns: Cross-modal Alignment Deficiency, Financial Terminological Bias, Operational Process Awareness Barrier, among others. These patterns point to crucial directions for future research. Our work provides the first agent benchmark closely related to the financial domain, aiming to objectively assess and promote the development of agents in this crucial field. Partial data is available at https://github.com/SUFE-AIFLM-Lab/FinGAIA.