arXiv subjects

Yujin Zhang

Publications and source records attributed to Yujin Zhang.

9 recordsLinked to original sources

arXiv2026

HANSEL: Extracting Breadcrumbs from Web Agent Trajectories for Interactive Verification

AI web agents can perform complex, multi-step tasks such as searching for products, comparing options, and making purchases on behalf of users. However, verifying the correctness of an agent's output remains difficult. Existing transparency mechanisms, including full trajectory logs, source links, screenshots, and LLM-generated summaries, treat verification as a passive reading task, leaving users to sift through overwhelming logs or trust potentially unfaithful explanations. We present HANSEL (Highlighting Agent Navigation Steps as Evidence Links), a system that extracts interactive, verifiable evidence from web-agent trajectories. Given an agent trajectory, HANSEL extracts evidence pages and snippets and presents them as navigable, interactive views with relevant page state preserved (e.g., applied filters, search queries, and scroll positions), enabling users to verify how the agent arrived at its answer. When the agent's answer cannot be traced to any visited page, HANSEL explicitly flags this gap. A technical evaluation on 45 tasks from AssistantBench and Online-Mind2Web shows that HANSEL achieves 83.7% precision and 88.8% recall in identifying evidence pages, while reducing trajectory volume by 61.6%. In a controlled user study with 14 participants, HANSEL significantly reduced task completion time and perceived effort compared to a standard agent interface, while participants rated it significantly higher on usability, verification ease, and error identification. Our results demonstrate that reframing verification as an interactive activity, rather than passive consumption of agent explanations, leads to more efficient human oversight of AI agents.

cs.HC↗

arXiv2025

A Universal Deep Learning Force Field for Molecular Dynamic Simulation and Vibrational Spectra Prediction

Accurate and efficient simulation of infrared (IR) and Raman spectra is essential for molecular identification and structural analysis. Traditional quantum chemistry methods based on the harmonic approximation neglect anharmonicity and nuclear quantum effects, while ab initio molecular dynamics (AIMD) remains computationally expensive. Here, we integrate our deep equivariant tensor attention network (DetaNet) with a velocity-Verlet integrator to enable fast and accurate machine learning molecular dynamics (MLMD) simulations for spectral prediction. Trained on the QMe14S dataset containing energies, forces, dipole moments, and polarizabilities for 186,102 small organic molecules, DetaNet yields a universal and transferable force field with high-order tensor prediction capability. Using time-correlation functions derived from MLMD and ring-polymer molecular dynamics (RPMD) trajectories, we computed IR and Raman spectra that accurately reproduce anharmonic and nuclear quantum effects. Benchmark tests on isolated molecules, including polycyclic aromatic hydrocarbons, demonstrate that the DetaNet-based MD approach achieves near-experimental spectral accuracy with speedups up to three orders of magnitude over AIMD. Furthermore, the framework extends seamlessly to molecular and inorganic crystals, molecular aggregates, and biological macromolecules such as polypeptides with minimal fine-tuning. In all systems, DetaNet maintains high accuracy while significantly reducing computational cost. Overall, this work establishes a universal machine learning force field and tensor-aware MLMD framework that enable fast, accurate, and broadly applicable dynamic simulations and IR/Raman spectral predictions across diverse molecular and material systems.

physics.chem-ph↗

arXiv2024

Scaling Inter-procedural Dataflow Analysis on the Cloud

Apart from forming the backbone of compiler optimization, static dataflow analysis has been widely applied in a vast variety of applications, such as bug detection, privacy analysis, program comprehension, etc. Despite its importance, performing interprocedural dataflow analysis on large-scale programs is well known to be challenging. In this paper, we propose a novel distributed analysis framework supporting the general interprocedural dataflow analysis. Inspired by large-scale graph processing, we devise dedicated distributed worklist algorithms for both whole-program analysis and incremental analysis. We implement these algorithms and develop a distributed framework called BigDataflow running on a large-scale cluster. The experimental results validate the promising performance of BigDataflow -- BigDataflow can finish analyzing the program of millions lines of code in minutes. Compared with the state-of-the-art, BigDataflow achieves much more analysis efficiency.

cs.PL↗

arXiv2020

Master-Auxiliary: an efficient aggregation strategy for video anomaly detection

The aim of surveillance video anomaly detection is to detect events that rarely or never happened in a certain scene. Generally, different detectors can detect different anomalies. This paper proposes an efficient strategy to aggregate multiple detectors. First, the aggregation strategy chooses one detector as master detector by experience, and sets the remaining detectors as auxiliary detectors. Then, the aggregation strategy extracts credible information from auxiliary detectors, including credible abnormal (Cred-a) frames and credible normal (Cred-n) frames. After that, the frequencies that each video frame being judged as Cred-a and Cred-n are counted. Applying the events' time continuity property, more Cred-a and Cred-n frames can be inferred. Finally, the aggregation strategy utilizes the Cred-a and Cred-n frequencies to vote to calculate soft weights, and uses the soft weights to assist the master detector. Experiments are carried out on multiple datasets. Comparing with existing aggregation strategies, the proposed strategy achieves state-of-the-art performance.

cs.CV↗

arXiv2019

Behavioral Security in Covert Communication Systems

The purpose of the covert communication system is to implement the communication process without causing third party perception. In order to achieve complete covert communication, two aspects of security issues need to be considered. The first one is to cover up the existence of information, that is, to ensure the content security of information; the second one is to cover up the behavior of transmitting information, that is, to ensure the behavioral security of communication. However, most of the existing information hiding models are based on the "Prisoners' Model", which only considers the content security of carriers, while ignoring the behavioral security of the sender and receiver. We think that this is incomplete for the security of covert communication. In this paper, we propose a new covert communication framework, which considers both content security and behavioral security in the process of information transmission. In the experimental part, we analyzed a large amount of collected real Twitter data to illustrate the security risks that may be brought to covert communication if we only consider content security and neglect behavioral security. Finally, we designed a toy experiment, pointing out that in addition to most of the existing content steganography, under the proposed new framework of covert communication, we can also use user's behavior to implement behavioral steganography. We hope this new proposed framework will help researchers to design better covert communication systems.

cs.CR↗

arXiv2018

A Wasserstein GAN model with the total variational regularization

It is well known that the generative adversarial nets (GANs) are remarkably difficult to train. The recently proposed Wasserstein GAN (WGAN) creates principled research directions towards addressing these issues. But we found in practice that gradient penalty WGANs (GP-WGANs) still suffer from training instability. In this paper, we combine a Total Variational (TV) regularizing term into the WGAN formulation instead of weight clipping or gradient penalty, which implies that the Lipschitz constraint is enforced on the critic network. Our proposed method is more stable at training than GP-WGANs and works well across varied GAN architectures. We also present a method to control the trade-off between image diversity and visual quality. It does not bring any computation burden.

cs.CV↗

arXiv2018

Automatically Generate Steganographic Text Based on Markov Model and Huffman Coding

Steganography, as one of the three basic information security systems, has long played an important role in safeguarding the privacy and confidentiality of data in cyberspace. The text is the most widely used information carrier in people's daily life, using text as a carrier for information hiding has broad research prospects. However, due to the high coding degree and less information redundancy in the text, it has been an extremely challenging problem to hide information in it for a long time. In this paper, we propose a steganography method which can automatically generate steganographic text based on the Markov chain model and Huffman coding. It can automatically generate fluent text carrier in terms of secret information which need to be embedded. The proposed model can learn from a large number of samples written by people and obtain a good estimate of the statistical language model. We evaluated the proposed model from several perspectives. Experimental results show that the performance of the proposed model is superior to all the previous related methods in terms of information imperceptibility and information hidden capacity.

cs.CR↗

arXiv2018

An Image dehazing approach based on the airlight field estimation

This paper proposes a scheme for single image haze removal based on the airlight field (ALF) estimation. Conventional image dehazing methods which are based on a physical model generally take the global atmospheric light as a constant. However, the constant-airlight assumption may be unsuitable for images with large sky regions, which causes unacceptable brightness imbalance and color distortion in recovery images. This paper models the atmospheric light as a field function, and presents a maximum a-priori (MAP) method for jointly estimating the airlight field, the transmission rate and the haze free image. We also introduce a valid haze-level prior for effective estimate of transmission. Evaluation on real world images shows that the proposed approach outperforms existing methods in single image dehazing, especially when the large sky region is included.

cs.CV↗

arXiv2016

Creating Interactive Behaviors in Early Sketch by Recording and Remixing Crowd Demonstrations

In the early stages of designing graphical user interfaces (GUIs), the look (appearance) can be easily presented by sketching, but the feel (interactive behaviors) cannot, and often requires an accompanying description of how it works (Myers et al. 2008). We propose to use crowdsourcing to augment early sketches with interactive behaviors generated, used, and reused by collective "wizards-of-oz" as opposed to a single wizard as in prior work (Davis et al. 2007). This demo presents an extension of Apparition (Lasecki et al. 2015), a crowd-powered prototyping tool that allows end users to create functional GUIs using speech and sketch. In Apparition, crowd workers collaborate in real-time on a shared canvas to refine the user-requested sketch interactively, and with the assistance of the end users. Our demo extends this functionality to let crowd workers "demonstrate" the canvas changes that are needed for a behavior and refine their demonstrations to improve the fidelity of interactive behaviors. The system then lets workers "remix" these behaviors to make creating future behaviors more efficient.

cs.HC↗