arXiv subjects

Yu Zhuang

Publications and source records attributed to Yu Zhuang.

14 recordsLinked to original sources

arXiv2026

AgentRewind: Recoverable Execution for Long-Horizon LLM Agents

Many real-world tasks require LLM agents to interact with their environments over long execution horizons. Errors that occur early in execution may propagate through both the agent context and environment state, and their effects may be difficult to reverse through subsequent actions. Existing methods mainly seek to reduce such errors through plan refinement and safety checks but provide little support after errors occur. To enable recovery during long-horizon execution, we present AgentRewind, a runtime recovery framework that records aligned checkpoints of the agent context and controlled environment, allowing agents to return to an earlier state and resume execution with information from previous attempts. We also construct MettleBench, a benchmark for evaluating task completion and partial progress on long-horizon engineering assignments containing a series of related requirements. Experiments across tasks, multiple models, execution strategies, and agent harnesses show that AgentRewind improves task success rate and average checklist progress over the compared baselines.

cs.AI↗

arXiv2026

Non-Hermitian Interaction between Light and Photonic Time Crystal Beyond the Floquet Quasinormal Mode Approximation

We report non-Hermitian mode couplings in a photonic time crystal induced by the light within its momentum bandgap. When the relative phase between the light and the photonic time crystal compensates for the detuning, we observe a periodic suppression of exponentially growing Floquet modes. In contrast, the optical response in this regime cannot be reproduced by the conventional Floquet expansion of the Green's function, revealing that the light induces effective mode couplings beyond the quasinormal mode approximation. We further investigate the parity-time phase transition through the exceptional point and quantitatively explain the suppression dynamics based on the phase, detuning, and modulation amplitude. The nontrivial interaction with light and the controllable non-Hermiticity indicate the great potential of photonic time crystals in temporally modulated nanophotonics.

physics.optics↗

arXiv2026

FutureWorld: A Live Reinforcement Learning Environment for Predictive Agents with Real-World Outcome Rewards

Live future prediction refers to the task of making predictions about real-world events before they unfold. This task is increasingly studied using large language model-based agent systems, and it is important for building agents that can continually learn from the real world. It can provide a large number of prediction questions grounded in diverse real-world events, while preventing answer leakage. To leverage the advantages of future prediction, we present FutureWorld, a live agentic reinforcement learning environment that closes the training loop between prediction, outcome realization, and parameter updates. Specifically, we modify and extend verl-tool, resulting in a new framework that we call verl-tool-future. Unlike standard reinforcement learning training frameworks that rely on immediate rewards, verl-tool-future stores prediction-time rollouts, backfills rewards after real-world outcomes become available, and then replays the completed trajectories for policy update. Across three open-source agents, successive FutureWorld training rounds lead to consistent improvements in prediction accuracy, probabilistic scoring, and calibration, demonstrating that delayed real-world outcome feedback can serve as an effective reinforcement learning signal.

cs.AI↗

arXiv2026

Harnessing Pre-Resolution Signals for Future Prediction Agents

Many high-stakes decisions depend on forecasts made before outcomes are known. In this future prediction setting, the central challenge is that public evidence evolves over time, while the main supervision signal arrives only after resolution: the realized outcome mainly assesses final correctness, offering only coarse guidance on what to track, what to verify, and which judgments to leave uncertain along the way. Our key observation is that revisiting the same unresolved question over time creates informative temporal contrasts across evolving evidence and repeated forecasts, exposing what earlier attempts missed before resolution and yielding a diagnostic signal we call the pre-resolution signal. We instantiate this idea in Milkyway, a future prediction agent with a persistent future prediction harness, an editable external state that stores reusable procedural guidance across revisits to the same unresolved question. As the same unresolved question is revisited, Milkyway extracts pre-resolution signals from evolving evidence and repeated forecasts, uses them to update the harness, and improves later forecasts on that question before resolution. After resolution, the realized outcome serves as a post-resolution check of provisional updates. On the FutureX and FutureWorld benchmarks, Milkyway achieves strong performance against competitive baselines, and a mechanism study suggests that the gains stem from harness evolution driven by pre-resolution signals rather than repeated prediction alone.

cs.AI↗

arXiv2026

PhysSFI-Net: Physics-informed Geometric Learning of Skeletal and Facial Interactions for Orthognathic Surgical Outcome Prediction

Orthognathic surgery repositions jaw bones to restore occlusion and enhance facial aesthetics. Accurate simulation of postoperative facial morphology is essential for preoperative planning. This study aims to develop and validate a physics-informed geometric deep learning framework named PhysSFI-Net for precise prediction of soft tissue deformation following orthognathic surgery. The model integrates a hierarchical feature extraction module with attention mechanisms to capture skeletal-facial interactions, an LSTM-based sequential predictor for incremental deformation, and a biomechanics-inspired reconstruction module for high-resolution facial modeling. The model was trained on 135 patients and externally validated on an independent cohort of 33 patients. Model performance was assessed using point cloud shape error, surface deviation error and landmark error between predicted facial shapes with corresponding ground truths. Quantitative analysis demonstrated that PhysSFI-Net achieved a global shape error of 1.070 +/- 0.088 mm, a surface deviation error of 1.296 +/- 0.349 mm and a landmark error of 2.445 +/- 1.326 mm. Comparative experiments indicated that PhysSFI-Net outperformed the state-of-the-art method ACMT-Net and baseline models. External validation further confirmed its robustness with a global HD of 1.431 +/- 0.087 mm and consistently lower subregional and mesh-based errors. In conclusion, PhysSFI-Net enables interpretable, high-resolution prediction of postoperative facial morphology, showing strong potential for clinical application in orthognathic surgical planning.

cs.CV↗

arXiv2025

Fast Clustering of Categorical Big Data

The K-Modes algorithm, developed for clustering categorical data, is of high algorithmic simplicity but suffers from unreliable performances in clustering quality and clustering efficiency, both heavily influenced by the choice of initial cluster centers. In this paper, we investigate Bisecting K-Modes (BK-Modes), a successive bisecting process to find clusters, in examining how good the cluster centers out of the bisecting process will be when used as initial centers for the K-Modes. The BK-Modes works by splitting a dataset into multiple clusters iteratively with one cluster being chosen and bisected into two clusters in each iteration. We use the sum of distances of data to their cluster centers as the selection metric to choose a cluster to be bisected in each iteration. This iterative process stops when K clusters are produced. The centers of these K clusters are then used as the initial cluster centers for the K-Modes. Experimental studies of the BK-Modes were carried out and were compared against the K-Modes with multiple sets of initial cluster centers as well as the best of the existing methods we found so far in our survey. Experimental results indicated good performances of BK-Modes both in the clustering quality and efficiency for large datasets.

cs.LG↗

arXiv2024

Flag-transitive point-primitive quasi-symmetric $2$-designs with block intersection numbers $0$ and $y\leq10$

In this paper, we show that for a non-trivial quasi-symmetric $2$-design $\mathcal{D}$ with two block intersection numbers $x=0$ and $2\leq y\leq10$, if $G\leq \mathrm{Aut}(\mathcal{D})$ is flag-transitive and point-primitive, then $G$ is either of affine type or almost simple type. Moreover, we prove that the socle of $G$ cannot be an alternating group. If the socle of $G$ is a sporadic group, then $\mathcal{D}$ and $G$ must be one of the following: $\mathcal{D}$ is a $2$-$(12,6,5)$ design with block intersection numbers $0,3$ and $G=\mathrm{M}_{11}$, or $\mathcal{D}$ is a $2$-$(22,6,5)$ design with block intersection numbers $0,2$ and $G=\mathrm{M}_{22}$ or $\mathrm{M}_{22}:2$.

math.CO↗

arXiv2024

A novel reliability attack of Physical Unclonable Functions

Physical Unclonable Functions (PUFs) are emerging as promising security primitives for IoT devices, providing device fingerprints based on physical characteristics. Despite their strengths, PUFs are vulnerable to machine learning (ML) attacks, including conventional and reliability-based attacks. Conventional ML attacks have been effective in revealing vulnerabilities of many PUFs, and reliability-based ML attacks are more powerful tools that have detected vulnerabilities of some PUFs that are resistant to conventional ML attacks. Since reliability-based ML attacks leverage information of PUFs' unreliability, we were tempted to examine the feasibility of building defense using reliability enhancing techniques, and have discovered that majority voting with reasonably high repeats provides effective defense against existing reliability-based ML attack methods. It is known that majority voting reduces but does not eliminate unreliability, we are motivated to investigate if new attack methods exist that can capture the low unreliability of highly but not-perfectly reliable PUFs, which led to the development of a new reliability representation and the new representation-enabled attack method that has experimentally cracked PUFs enhanced with majority voting of high repetitions.

cs.CR↗

arXiv2024

A lightweight PUF-based authentication protocol

Lightweight authentication is essential for resource-constrained Internet-of-Things (IoT). Implementable with low resource and operable with low power, Physical Unclonable Functions (PUFs) have the potential as hardware primitives for implementing lightweight authentication protocols. The arbiter PUF (APUF) is probably the most lightweight strong PUF capable of generating exponentially many challenge-response pairs (CRPs), a desirable property for authentication protocols, but APUF is severely weak against modeling attacks. Efforts on PUF design have led to many PUFs of higher resistance to modeling attacks and also higher area overhead. There are also substantial efforts on protocol development, some leverage PUFs' strength in fighting modeling attacks, and some others employ carefully designed protocol techniques to obfuscate either the challenges or the responses with modest increase of area overhead for some or increased operations for some others. To attain both low resource footprint and high modeling attack resistance, in this paper we propose a co-design of PUF and protocol, where the PUF consists of an APUF and a zero-transistor interface that obfuscates the true challenge bits fed to the PUF. The obfuscated PUF possesses rigorously proven potential and experimentally supported performance against modeling attacks when a condition is met, and the protocol provides the condition required by the PUF and leverages the PUF's modeling resistance to arrive at low resource overhead and high operational simplicity, enabling lightweight authentications while resisting modeling attacks.

cs.CR↗

arXiv2022

Lightweight Strategy for XOR PUFs as Security Primitives for Resource-constrained IoT device

Physical Unclonable Functions (PUFs) are promising security primitives for resource-constrained IoT devices. And the XOR Arbiter PUF (XOR-PUF) is one of the most studied PUFs, out of an effort to improve the resistance against machine learning attacks of probably the most lightweight delay-based PUFs - the Arbiter PUFs. However, recent attack studies reveal that even XOR-PUFs with large XOR sizes are still not safe against machine learning attacks. Increasing PUF stages or components and using different challenges for different components are two ways to improve the security of APUF-based PUFs, but more stages or components lead to more hardware cost and higher operation power, and different challenges for different components require the transmission of more bits during operations, which also leads to higher power consumption. In this paper, we present a strategy that combines the choice of XOR Arbiter PUF (XOR-PUF) architecture parameters with the way XOR-PUFs are used to achieve lightweights in hardware cost and energy consumption as well as security against machine learning attacks. Experimental evaluations show that with the proposed strategy, highly lightweight component-differentially challenged XOR-PUFs can withstand the most powerful machine learning attacks developed so far and maintain excellent intra-device and inter-device performance, rendering this strategy a potential blueprint for the fabrication and use of XOR-PUFs for resource-constrained IoT applications.

cs.CR↗

arXiv2022

A New Security Boundary of Component Differentially Challenged XOR PUFs Against Machine Learning Modeling Attacks

Physical Unclonable Functions (PUFs) are promising security primitives for resource-constrained network nodes. The XOR Arbiter PUF (XOR PUF or XPUF) is an intensively studied PUF invented to improve the security of the Arbiter PUF, probably the most lightweight delay-based PUF. Recently, highly powerful machine learning attack methods were discovered and were able to easily break large-sized XPUFs, which were highly secure against earlier machine learning attack methods. Component-differentially-challenged XPUFs (CDC-XPUFs) are XPUFs with different component PUFs receiving different challenges. Studies showed they were much more secure against machine learning attacks than the conventional XPUFs, whose component PUFs receive the same challenge. But these studies were all based on earlier machine learning attack methods, and hence it is not clear if CDC-XPUFs can remain secure under the recently discovered powerful attack methods. In this paper, the two current most powerful two machine learning methods for attacking XPUFs are adapted by fine-tuning the parameters of the two methods for CDC-XPUFs. Attack experiments using both simulated PUF data and silicon data generated from PUFs implemented on field-programmable gate array (FPGA) were carried out, and the experimental results showed that some previously secure CDC-XPUFs of certain circuit parameter values are no longer secure under the adapted new attack methods, while many more CDC-XPUFs of other circuit parameter values remain secure. Thus, our experimental attack study has re-defined the boundary between the secure region and the insecure region of the PUF circuit parameter space, providing PUF manufacturers and IoT security application developers with valuable information in choosing PUFs with secure parameter values.

cs.CR↗

arXiv2021

A Challenge Obfuscating Interface for Arbiter PUF Variants against Machine Learning Attacks

Security is of critical importance for the Internet of Things (IoT). Many IoT devices are resource-constrained, calling for lightweight security protocols. Physical unclonable functions (PUFs) leverage integrated circuits' variations to produce responses unique for individual devices, and hence are not reproducible even by the manufacturers. Implementable with simplistic circuits of thousands of transistors and operable with low energy, Physical unclonable functions are promising candidates as security primitives for resource-constrained IoT devices. Arbiter PUFs (APUFs) are a group of delay-based PUFs which are highly lightweight in resource requirements but suffer from high susceptibility to machine learning attacks. To defend APUF variants against machine learning attacks, we introduce challenge input interface, which incurs low resource overhead. With the interface, experimental attack study shows that all tested PUFs have substantially improved their resistance against machine learning attacks, rendering interfaced APUF variants promising candidates for security critical applications.

cs.CR↗

arXiv2019

Semiclassical vibrational spectroscopy with Hessian databases

We report on a new approach to ease the computational overhead of ab initio on-the-fly semiclassical dynamics simulations for vibrational spectroscopy. The well known bottleneck of such computations lies in the necessity to estimate the Hessian matrix for propagating the semiclassical pre-exponential factor at each step along the dynamics. The procedure proposed here is based on the creation of a dynamical database of Hessians and associated molecular geometries able to speed up calculations while preserving the accuracy of results at a satisfactory level. This new approach can be interfaced to both analytical potential energy surfaces and on-the-fly dynamics, allowing one to study even large systems previously not achievable. We present results obtained for semiclassical vibrational power spectra of methane, glycine, and N-acetyl-L-phenylalaninyl-L-methionine-amide, a molecule of biological interest made of 46 atoms.

physics.comp-ph↗

arXiv2017

Performance optimizations for scalable CFD applications on hybrid CPU+MIC heterogeneous computing system with millions of cores

For computational fluid dynamics (CFD) applications with a large number of grid points/cells, parallel computing is a common efficient strategy to reduce the computational time. How to achieve the best performance in the modern supercomputer system, especially with heterogeneous computing resources such as hybrid CPU+GPU, or a CPU + Intel Xeon Phi (MIC) co-processors, is still a great challenge. An in-house parallel CFD code capable of simulating three dimensional structured grid applications is developed and tested in this study. Several methods of parallelization, performance optimization and code tuning both in the CPU-only homogeneous system and in the heterogeneous system are proposed based on identifying potential parallelism of applications, balancing the work load among all kinds of computing devices, tuning the multi-thread code toward better performance in intra-machine node with hundreds of CPU/MIC cores, and optimizing the communication among inter-nodes, inter-cores, and between CPUs and MICs. Some benchmark cases from model and/or industrial CFD applications are tested on the Tianhe-1A and Tianhe-2 supercomputer to evaluate the performance. Among these CFD cases, the maximum number of grid cells reached 780 billion. The tuned solver successfully scales up to half of the entire Tianhe-2 supercomputer system with over 1.376 million of heterogeneous cores. The test results and performance analysis are discussed in detail.

cs.PF↗