arXiv subjects

Shuai Jia

Publications and source records attributed to Shuai Jia.

16 recordsLinked to original sources

arXiv2026

Evaluating Investment Logic in Large Language Models: A Real-World Benchmark Towards Personalzied Financial Agents

Investment competence is inherently personalized: the same market evidence can justify different actions for investors with different goals, horizons, portfolios, and risk boundaries. Yet financial LLMs are evaluated either by static question answering or by terminal profit and loss. The former omits agency; the latter cannot reveal whether a profitable action was grounded, profile-consistent, or merely lucky. We ask whether the community is using the wrong ruler for consequential agents. We introduce \textsc{InvestLogicBench}, a process-native benchmark containing 201,247 documented decisions from 151 real-world investors. Each episode instantiates a \textbf{P$\rightarrow$E$\rightarrow$R$\rightarrow$D$\rightarrow$O} trace: investor \textit{Profile}, observable market \textit{Events}, investment \textit{Reasoning}, executable \textit{Decision}, and delayed \textit{Outcome}. The release includes profile construction, point-in-time event binding, structured logic, horizons, outcomes, and post-mortems, and supports comprehension, profile-conditioned generation, and end-to-end replay. Across four leading LLMs, logical plausibility remains near 4/5 while event grounding is only 0.8--2.8/5; return and process quality also disagree. These results expose polished but weakly grounded reasoning that outcome-only evaluation hides. We further argue that P$\rightarrow$E$\rightarrow$R$\rightarrow$D$\rightarrow$O should be a data-system interface, requiring versioned profiles, temporal provenance, inspectable retrieval, decision ledgers, and replayable outcomes. Finance is our stress test for a broader class of personalized, consequential agents.

cs.AI↗

arXiv2026

BizFinBench.v2: Towards Reliable LLMs in Finance via Real-User Data and Offline/Online Bilingual Evaluation

Large language models are becoming increasingly significant in financial applications. Nevertheless, prevailing benchmarks are largely dependent on simulated or generic data, which leads to a significant gap between reported performance and actual efficacy in real-world scenarios. To tackle this challenge, we present BizFinBench.v2, the first integrated offline and online benchmark built upon authentic user query-response data from both Chinese and U.S. equity markets. It comprises 28,860 questions across eight offline and two online tasks. Experimental results show that GPT-5 achieves a mere 61.5% accuracy, still failing to meet the practical business requirement (84.8%). Among the evaluated commercial models, DeepSeek-R1 exhibits superior investment efficacy. Error analysis grounded in real financial practice reveals persistent limitations in existing models. By overcoming the constraints of prior benchmarks, BizFinBench.v2 provides a substantiated foundation for advancing LLM deployment in the financial sector. Our data and code are available at https://github.com/HiThink-Research/BizFinBench.v2.

cs.AI↗

arXiv2026

U3DWind: A Low Altitude Wind Field Dataset and Benchmark for Urban Air Mobility

Urban Air Mobility (UAM) requires reliable assessment of low-altitude wind hazards, because winds, gusts, and building-induced turbulence have been recognized as critical factors affecting vehicle stability, route feasibility, vertiport siting, and airspace management. While wind-tunnel experiments, computational fluid dynamics (CFD), multiscale downscaling, reduced-order models, and UAV planning datasets have advanced wind-aware analysis, public resources for data-driven, city-scale UAM planning remain limited in geographic coverage, scenario diversity, vertical extent, building realism, and task-oriented benchmarking. To address this gap, we introduce U3DWind, a building-resolved low-altitude wind-field dataset generated using our GPU-accelerated Lattice Boltzmann Method--Large-Eddy Simulation (LBM-LES) framework for rapid urban flow simulation. U3DWind covers five megacities in China: Beijing, Shanghai, Guangzhou, Shenzhen, and Hong Kong. It contains 720 simulations, with 16 inflow directions, three reference wind speeds, and three seasonal atmospheric scenarios (annual, summer, and winter) for each city. At a 10 m grid resolution, the dataset provides three-dimensional three-component (3D3C) velocity, turbulent kinetic energy (TKE), flow density, and fluid--solid masks. To support operationally relevant evaluation, we further define five baseline tasks: wind-field prediction, sparse-sensor wind-field reconstruction, site wind-exposure ranking, airworthiness wind-compliance risk scoring, and noise propagation modeling. As a multi-city, building-resolved 3D urban wind-field dataset, U3DWind enables systematic evaluation of wind-induced impacts in low-altitude traffic scenarios and provides an open benchmark for urban airspace management and data-driven high-fidelity urban flow simulation.

physics.flu-dyn↗

arXiv2026

SGCR: A Specification-Grounded Framework for Trustworthy LLM Code Review

Automating code review with Large Language Models (LLMs) shows immense promise, yet practical adoption is hampered by their lack of reliability, context-awareness, and control. To address this, we propose Specification-Grounded Code Review (SGCR), a framework that grounds LLMs in human-authored specifications to produce trustworthy and relevant feedback. SGCR features a novel dual-pathway architecture: an explicit path ensures deterministic compliance with predefined rules derived from these specifications, while an implicit path heuristically discovers and verifies issues beyond those rules. Deployed in a live industrial environment at HiThink Research, SGCR's suggestions achieved a 42% developer adoption rate-a 90.9% relative improvement over a baseline LLM (22%). Our work demonstrates that specification-grounding is a powerful paradigm for bridging the gap between the generative power of LLMs and the rigorous reliability demands of software engineering.

cs.SE↗

arXiv2025

Patch-Discontinuity Mining for Generalized Deepfake Detection

The rapid advancement of generative artificial intelligence has enabled the creation of highly realistic fake facial images, posing serious threats to personal privacy and the integrity of online information. Existing deepfake detection methods often rely on handcrafted forensic cues and complex architectures, achieving strong performance in intra-domain settings but suffering significant degradation when confronted with unseen forgery patterns. In this paper, we propose GenDF, a simple yet effective framework that transfers a powerful large-scale vision model to the deepfake detection task with a compact and neat network design. GenDF incorporates deepfake-specific representation learning to capture discriminative patterns between real and fake facial images, feature space redistribution to mitigate distribution mismatch, and a classification-invariant feature augmentation strategy to enhance generalization without introducing additional trainable parameters. Extensive experiments demonstrate that GenDF achieves state-of-the-art generalization performance in cross-domain and cross-manipulation settings while requiring only 0.28M trainable parameters, validating the effectiveness and efficiency of the proposed framework.

cs.CV↗

arXiv2025

Parameter-Free Fine-tuning via Redundancy Elimination for Vision Foundation Models

Vision foundation models (VFMs) have demonstrated remarkable capabilities in learning universal visual representations. However, adapting these models to downstream tasks conventionally requires parameter updates, with even parameter-efficient fine-tuning methods necessitating the modification of thousands to millions of weights. In this paper, we investigate the redundancies in the segment anything model (SAM) and then propose a novel parameter-free fine-tuning method. Unlike traditional fine-tuning methods that adjust parameters, our method emphasizes selecting, reusing, and enhancing pre-trained features, offering a new perspective on fine-tuning foundation models. Specifically, we introduce a channel selection algorithm based on the model's output difference to identify redundant and effective channels. By selectively replacing the redundant channels with more effective ones, we filter out less useful features and reuse more task-irrelevant features to downstream tasks, thereby enhancing the task-specific feature representation. Experiments on both out-of-domain and in-domain datasets demonstrate the efficiency and effectiveness of our method in different vision tasks (e.g., image segmentation, depth estimation and image classification). Notably, our approach can seamlessly integrate with existing fine-tuning strategies (e.g., LoRA, Adapter), further boosting the performance of already fine-tuned models. Moreover, since our channel selection involves only model inference, our method significantly reduces GPU memory overhead.

cs.CV↗

arXiv2025

PapMOT: Exploring Adversarial Patch Attack against Multiple Object Tracking

Tracking multiple objects in a continuous video stream is crucial for many computer vision tasks. It involves detecting and associating objects with their respective identities across successive frames. Despite significant progress made in multiple object tracking (MOT), recent studies have revealed the vulnerability of existing MOT methods to adversarial attacks. Nevertheless, all of these attacks belong to digital attacks that inject pixel-level noise into input images, and are therefore ineffective in physical scenarios. To fill this gap, we propose PapMOT, which can generate physical adversarial patches against MOT for both digital and physical scenarios. Besides attacking the detection mechanism, PapMOT also optimizes a printable patch that can be detected as new targets to mislead the identity association process. Moreover, we introduce a patch enhancement strategy to further degrade the temporal consistency of tracking results across video frames, resulting in more aggressive attacks. We further develop new evaluation metrics to assess the robustness of MOT against such attacks. Extensive evaluations on multiple datasets demonstrate that our PapMOT can successfully attack various architectures of MOT trackers in digital scenarios. We also validate the effectiveness of PapMOT for physical attacks by deploying printed adversarial patches in the real world.

cs.CV↗

arXiv2025

Robust SAM: On the Adversarial Robustness of Vision Foundation Models

The Segment Anything Model (SAM) is a widely used vision foundation model with diverse applications, including image segmentation, detection, and tracking. Given SAM's wide applications, understanding its robustness against adversarial attacks is crucial for real-world deployment. However, research on SAM's robustness is still in its early stages. Existing attacks often overlook the role of prompts in evaluating SAM's robustness, and there has been insufficient exploration of defense methods to balance the robustness and accuracy. To address these gaps, this paper proposes an adversarial robustness framework designed to evaluate and enhance the robustness of SAM. Specifically, we introduce a cross-prompt attack method to enhance the attack transferability across different prompt types. Besides attacking, we propose a few-parameter adaptation strategy to defend SAM against various adversarial attacks. To balance robustness and accuracy, we use the singular value decomposition (SVD) to constrain the space of trainable parameters, where only singular values are adaptable. Experiments demonstrate that our cross-prompt attack method outperforms previous approaches in terms of attack success rate on both SAM and SAM 2. By adapting only 512 parameters, we achieve at least a 15\% improvement in mean intersection over union (mIoU) against various adversarial attacks. Compared to previous defense methods, our approach enhances the robustness of SAM while maximally maintaining its original performance.

cs.CV↗

arXiv2023

Integrating Stock Features and Global Information via Large Language Models for Enhanced Stock Return Prediction

The remarkable achievements and rapid advancements of Large Language Models (LLMs) such as ChatGPT and GPT-4 have showcased their immense potential in quantitative investment. Traders can effectively leverage these LLMs to analyze financial news and predict stock returns accurately. However, integrating LLMs into existing quantitative models presents two primary challenges: the insufficient utilization of semantic information embedded within LLMs and the difficulties in aligning the latent information within LLMs with pre-existing quantitative stock features. We propose a novel framework consisting of two components to surmount these challenges. The first component, the Local-Global (LG) model, introduces three distinct strategies for modeling global information. These approaches are grounded respectively on stock features, the capabilities of LLMs, and a hybrid method combining the two paradigms. The second component, Self-Correlated Reinforcement Learning (SCRL), focuses on aligning the embeddings of financial news generated by LLMs with stock features within the same semantic space. By implementing our framework, we have demonstrated superior performance in Rank Information Coefficient and returns, particularly compared to models relying only on stock features in the China A-share market.

cs.CL↗

arXiv2022

Adv-Attribute: Inconspicuous and Transferable Adversarial Attack on Face Recognition

Deep learning models have shown their vulnerability when dealing with adversarial attacks. Existing attacks almost perform on low-level instances, such as pixels and super-pixels, and rarely exploit semantic clues. For face recognition attacks, existing methods typically generate the l_p-norm perturbations on pixels, however, resulting in low attack transferability and high vulnerability to denoising defense models. In this work, instead of performing perturbations on the low-level pixels, we propose to generate attacks through perturbing on the high-level semantics to improve attack transferability. Specifically, a unified flexible framework, Adversarial Attributes (Adv-Attribute), is designed to generate inconspicuous and transferable attacks on face recognition, which crafts the adversarial noise and adds it into different attributes based on the guidance of the difference in face recognition features from the target. Moreover, the importance-aware attribute selection and the multi-objective optimization strategy are introduced to further ensure the balance of stealthiness and attacking strength. Extensive experiments on the FFHQ and CelebA-HQ datasets show that the proposed Adv-Attribute method achieves the state-of-the-art attacking success rates while maintaining better visual effects against recent attack methods.

cs.CV↗

arXiv2022

Exploring Frequency Adversarial Attacks for Face Forgery Detection

Various facial manipulation techniques have drawn serious public concerns in morality, security, and privacy. Although existing face forgery classifiers achieve promising performance on detecting fake images, these methods are vulnerable to adversarial examples with injected imperceptible perturbations on the pixels. Meanwhile, many face forgery detectors always utilize the frequency diversity between real and fake faces as a crucial clue. In this paper, instead of injecting adversarial perturbations into the spatial domain, we propose a frequency adversarial attack method against face forgery detectors. Concretely, we apply discrete cosine transform (DCT) on the input images and introduce a fusion module to capture the salient region of adversary in the frequency domain. Compared with existing adversarial attacks (e.g. FGSM, PGD) in the spatial domain, our method is more imperceptible to human observers and does not degrade the visual quality of the original images. Moreover, inspired by the idea of meta-learning, we also propose a hybrid adversarial attack that performs attacks in both the spatial and frequency domains. Extensive experiments indicate that the proposed method fools not only the spatial-based detectors but also the state-of-the-art frequency-based detectors effectively. In addition, the proposed frequency attack enhances the transferability across face forgery detectors as black-box attacks.

cs.CV↗

arXiv2021

IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking

Adversarial attack arises due to the vulnerability of deep neural networks to perceive input samples injected with imperceptible perturbations. Recently, adversarial attack has been applied to visual object tracking to evaluate the robustness of deep trackers. Assuming that the model structures of deep trackers are known, a variety of white-box attack approaches to visual tracking have demonstrated promising results. However, the model knowledge about deep trackers is usually unavailable in real applications. In this paper, we propose a decision-based black-box attack method for visual object tracking. In contrast to existing black-box adversarial attack methods that deal with static images for image classification, we propose IoU attack that sequentially generates perturbations based on the predicted IoU scores from both current and historical frames. By decreasing the IoU scores, the proposed attack method degrades the accuracy of temporal coherent bounding boxes (i.e., object motions) accordingly. In addition, we transfer the learned perturbations to the next few frames to initialize temporal motion attack. We validate the proposed IoU attack on state-of-the-art deep trackers (i.e., detection based, correlation filter based, and long-term trackers). Extensive experiments on the benchmark datasets indicate the effectiveness of the proposed IoU attack method. The source code is available at https://github.com/VISION-SJTU/IoUattack.

cs.CV↗

arXiv2020

Robust Tracking against Adversarial Attacks

While deep convolutional neural networks (CNNs) are vulnerable to adversarial attacks, considerably few efforts have been paid to construct robust deep tracking algorithms against adversarial attacks. Current studies on adversarial attack and defense mainly reside in a single image. In this work, we first attempt to generate adversarial examples on top of video sequences to improve the tracking robustness against adversarial attacks. To this end, we take temporal motion into consideration when generating lightweight perturbations over the estimated tracking results frame-by-frame. On one hand, we add the temporal perturbations into the original video sequences as adversarial examples to greatly degrade the tracking performance. On the other hand, we sequentially estimate the perturbations from input sequences and learn to eliminate their effect for performance restoration. We apply the proposed adversarial attack and defense approaches to state-of-the-art deep tracking algorithms. Extensive evaluations on the benchmark datasets demonstrate that our defense method not only eliminates the large performance drops caused by adversarial attacks, but also achieves additional performance gains when deep trackers are not under adversarial attacks.

cs.CV↗

arXiv2018

Quantum plasmonic hot-electron injection in lateral WSe2/MoSe2 heterostructures

Lateral two-dimensional (2D) transitional metal dichalcogenide (TMD) heterostructures have recently attracted a wide attention as promising materials for optoelectronic nanodevices. Due to the nanoscale width of lateral heterojunctions, the study of their optical properties is challenging and requires using subwavelength optical characterization techniques. We investigated the photoresponse of a lateral 2D WSe2/MoSe2 heterostructure using tip-enhanced photoluminescence (TEPL) with nanoscale spatial resolution and with picoscale tip-sample distance dependence. We demonstrate the observation of quantum plasmonic effects in 2D heterostructures on a non-metallic substrate, and we report the nano-optical measurements of the lateral 2D TMD heterojunction width of ~ 150 nm and the charge tunneling distance of ~ 20 pm. Controlling the plasmonic tip location allows for both nano-optical imaging and plasmon-induced hot electron injection into the heterostructure. By adjusting the tip-sample distance, we demonstrated the controllability of the hot-electron injection via the competition of two quantum plasmonic photoluminescence (PL) enhancement and quenching mechanisms. The directional charge transport in the depletion region leads to the increased hot electron injection, enhancing the MoSe2 PL signal. The properties of the directional hot-electron injection in the quantum plasmonic regime make the lateral 2D MoSe2/WSe2 heterostructures promising for quantum nanodevices with tunable photoresponse.

physics.optics↗

arXiv2017

Janus Monolayer Transition Metal Dichalcogenides

A novel crystal configuration of sandwiched S-Mo-Se structure (Janus SMoSe) at the monolayer limit has been synthesized and carefully characterized in this work. By controlled sulfurization of monolayer MoSe2 the top layer of selenium atoms are substituted by sulfur atoms while the bottom selenium layer remains intact. The peculiar structure of this new material is systematically investigated by Raman, photoluminescence and X-ray photoelectron spectroscopy and confirmed by transmission-electron microscopy and time-of-flight secondary ion mass spectrometry. Density-functional theory calculations are performed to better understand the Raman vibration modes and electronic structures of the Janus SMoSe monolayer, which are found to correlate well with corresponding experimental results. Finally, high basal plane hydrogen evolution reaction (HER) activity is discovered for the Janus monolayer and DFT calculation implies that the activity originates from the synergistic effect of the intrinsic defects and structural strain inherent in the Janus structure.

cond-mat.mtrl-sci↗

arXiv2017

Nano-optical imaging of monolayer MoSe2 using tip-enhanced photoluminescence

Band gap tuning in two-dimensional transitional metal dichalcogenides (TMDs) is crucial in fabricating new optoelectronic devices. High resolution photoluminescence (PL) microscopy is needed for accurate band gap characterization. We performed tip-enhanced photoluminescence (TEPL) measurements of monolayer MoSe2 with nanoscale spatial resolution, providing an improved characterization of the band gap correlated with the topography compared with the conventional far field spectroscopy. We also observed PL shifts at the edges and investigated the spatial dependence of the TEPL enhancement factors.

physics.optics↗