Xiangyu Zhang

Anlin Zheng, Yuang Zhang, Xiangyu Zhang et al.

In this paper, we propose a new query-based detection framework for crowd detection. Previous query-based detectors suffer from two drawbacks: first, multiple predictions will be inferred for a single object, typically in crowded scenes; second, the performance saturates as the depth of the decoding stage increases. Benefiting from the nature of the one-to-one label assignment rule, we propose a progressive predicting method to address the above issues. Specifically, we first select accepted queries prone to generate true positive predictions, then refine the rest noisy queries according to the previously accepted predictions. Experiments show that our method can significantly boost the performance of query-based detectors in crowded scenes. Equipped with our approach, Sparse RCNN achieves 92.0\% $\text{AP}$, 41.4\% $\text{MR}^{-2}$ and 83.2\% $\text{JI}$ on the challenging CrowdHuman \cite{shao2018crowdhuman} dataset, outperforming the box-based method MIP \cite{chu2020detection} that specifies in handling crowded scenarios. Moreover, the proposed method, robust to crowdedness, can still obtain consistent improvements on moderately and slightly crowded datasets like CityPersons \cite{zhang2017citypersons} and COCO \cite{lin2014microsoft}. Code will be made publicly available at https://github.com/megvii-model/Iter-E2EDET.

Jinyao Guo, Chengpeng Wang, Dominic Deluca et al.

Software auditing is an increasingly critical task in the era of rapid code generation. While LLM-based auditors have demonstrated strong potential, their effectiveness remains limited by misalignment with the highly complex, domain-specific nature of bug detection. In this work, we introduce BugScope, a framework that mirrors how human auditors learn specific bug patterns from representative examples and apply this knowledge during code auditing. BugScope structures auditing into three steps: seed identification, context retrieval, and bug detection, and aligns LLMs to each step by analyzing real bug reports and mutated examples, and distilling concise, reusable guidelines. On a curated dataset of 33 real-world bugs from 21 widely used open-source projects, BugScope achieves 86.05\% precision and 87.88\% recall, corresponding to an F1 score of 0.87. By comparison, leading industrial tools such as Claude Code (with Claude Opus 4.6) and Cursor BugBot achieve F1 scores of only 0.51 and 0.43, respectively. Beyond benchmarks, large-scale evaluation on real-world projects such as the Linux kernel uncovered 184 previously unknown bugs, of which 78 have already been fixed and 7 explicitly confirmed by developers. Our code is available at https://github.com/jinyaoguo/BugScope

Zhiyuan Cheng, James Liang, Guanhong Tao et al.

Monocular Depth Estimation (MDE) is a critical component in applications such as autonomous driving. There are various attacks against MDE networks. These attacks, especially the physical ones, pose a great threat to the security of such systems. Traditional adversarial training method requires ground-truth labels hence cannot be directly applied to self-supervised MDE that does not have ground-truth depth. Some self-supervised model hardening techniques (e.g., contrastive learning) ignore the domain knowledge of MDE and can hardly achieve optimal performance. In this work, we propose a novel adversarial training method for self-supervised MDE models based on view synthesis without using ground-truth depth. We improve adversarial robustness against physical-world attacks using L0-norm-bounded perturbation in training. We compare our method with supervised learning based and contrastive learning based methods that are tailored for MDE. Results on two representative MDE networks show that we achieve better robustness against various adversarial attacks with nearly no benign performance degradation.

Patrick Emami, Xiangyu Zhang, David Biagioni et al.

In multi-timescale multi-agent reinforcement learning (MARL), agents interact across different timescales. In general, policies for time-dependent behaviors, such as those induced by multiple timescales, are non-stationary. Learning non-stationary policies is challenging and typically requires sophisticated or inefficient algorithms. Motivated by the prevalence of this control problem in real-world complex systems, we introduce a simple framework for learning non-stationary policies for multi-timescale MARL. Our approach uses available information about agent timescales to define a periodic time encoding. In detail, we theoretically demonstrate that the effects of non-stationarity introduced by multiple timescales can be learned by a periodic multi-agent policy. To learn such policies, we propose a policy gradient algorithm that parameterizes the actor and critic with phase-functioned neural networks, which provide an inductive bias for periodicity. The framework's ability to effectively learn multi-timescale policies is validated on a gridworld and building energy management environment.

Yayue Deng, Guoqiang Hu, Haiyang Sun et al.

Spoken Dialogue Models (SDMs) have advanced rapidly, yet their ability to sustain genuinely interactive multi-turn conversations remains underexplored, as most benchmarks focus on single-turn exchanges. We introduce Multi-Bench, the first benchmark explicitly designed to evaluate SDMs in multi-turn interactive dialogue with an emphasis on emotional intelligence. Multi-Bench employs a hierarchical structure with a basic track for emotion understanding and reasoning and an advanced track for emotion support and application. It comprises five carefully designed tasks and about 3.2K samples, ranging from emotion recognition to complex reasoning and interactive dialogue, supported by a reproducible evaluation framework. We evaluate six representative SDMs on eight subsets of Multi-Bench. Results show that while current SDMs achieve good performance on basic understanding tasks, they still have room for improvement in advanced multi-turn interactive dialogue and reasoning-related tasks, particularly in emotion awareness and application.

Abhijeet Sahu, Truc Nguyen, Kejun Chen et al.

With the deeper penetration of inverter-based resources in power systems, false data injection attacks (FDIA) are a growing cyber-security concern. They have the potential to disrupt the system's stability like frequency stability, thereby leading to catastrophic failures. Therefore, an FDIA detection method would be valuable to protect power systems. FDIAs typically induce a discrepancy between the desired and the effective behavior of the power system dynamics. A suitable detection method can leverage power dynamics predictions to identify whether such a discrepancy was induced by an FDIA. This work investigates the efficacy of temporal and spatio-temporal state prediction models, such as Long Short-Term Memory (LSTM) and a combination of Graph Neural Networks (GNN) with LSTM, for predicting frequency dynamics in the absence of an FDIA but with noisy measurements, and thereby identify FDIA events. For demonstration purposes, the IEEE 39 New England Kron-reduced model simulated with a swing equation is considered. It is shown that the proposed state prediction models can be used as a building block for developing an effective FDIA detection method that can maintain high detection accuracy across various attack and deployment settings. It is also shown how the FDIA detection should be deployed to limit its exposure to detection inaccuracies and mitigate its computational burden.

Romesh Prasad, Malik Hassanaly, Xiangyu Zhang et al.

While inverter-based distributed energy resources (DERs) play a crucial role in integrating renewable energy into the power system, they concurrently diminish the grid's system inertia, elevating the risk of frequency instabilities. Furthermore, smart inverters, interfaced via communication networks, pose a potential vulnerability to cyber threats if not diligently managed. To proactively fortify the power grid against sophisticated cyber attacks, we propose to employ reinforcement learning (RL) to identify potential threats and system vulnerabilities. This study concentrates on analyzing adversarial strategies for false data injection, specifically targeting smart inverters involved in primary frequency control. Our findings demonstrate that an RL agent can adeptly discern optimal false data injection methods to manipulate inverter settings, potentially causing catastrophic consequences.

David Biagioni, Xiangyu Zhang, Dylan Wald et al.

We present the PowerGridworld software package to provide users with a lightweight, modular, and customizable framework for creating power-systems-focused, multi-agent Gym environments that readily integrate with existing training frameworks for reinforcement learning (RL). Although many frameworks exist for training multi-agent RL (MARL) policies, none can rapidly prototype and develop the environments themselves, especially in the context of heterogeneous (composite, multi-device) power systems where power flow solutions are required to define grid-level variables and costs. PowerGridworld is an open-source software package that helps to fill this gap. To highlight PowerGridworld's key features, we present two case studies and demonstrate learning MARL policies using both OpenAI's multi-agent deep deterministic policy gradient (MADDPG) and RLLib's proximal policy optimization (PPO) algorithms. In both cases, at least some subset of agents incorporates elements of the power flow solution at each time step as part of their reward (negative cost) structures.

Deyu Zhou, Quan Sun, Yuang Peng et al. · tsinghua

We introduce MAGI, a hybrid video generation framework that combines masked modeling for intra-frame generation with causal modeling for next-frame generation. Our key innovation, Complete Teacher Forcing (CTF), conditions masked frames on complete observation frames rather than masked ones (namely Masked Teacher Forcing, MTF), enabling a smooth transition from token-level (patch-level) to frame-level autoregressive generation. CTF significantly outperforms MTF, achieving a +23% improvement in FVD scores on first-frame conditioned video prediction. To address issues like exposure bias, we employ targeted training strategies, setting a new benchmark in autoregressive video generation. Experiments show that MAGI can generate long, coherent video sequences exceeding 100 frames, even when trained on as few as 16 frames, highlighting its potential for scalable, high-quality video generation.

Xiangyu Zhang, Peter I. Frazier

Restless bandits are an important class of problems with applications in recommender systems, active learning, revenue management and other areas. We consider infinite-horizon discounted restless bandits with many arms where a fixed proportion of arms may be pulled in each period and where arms share a finite state space. Although an average-case-optimal policy can be computed via stochastic dynamic programming, the computation required grows exponentially with the number of arms $N$. Thus, it is important to find scalable policies that can be computed efficiently for large $N$ and that are near optimal in this regime, in the sense that the optimality gap (i.e. the loss of expected performance against an optimal policy) per arm vanishes for large $N$. However, the most popular approach, the Whittle index, requires a hard-to-verify indexability condition to be well-defined and another hard-to-verify condition to guarantee a $o(N)$ optimality gap. We present a method resolving these difficulties. By replacing a global Lagrange multiplier used by the Whittle index with a sequence of Lagrangian multipliers, one per time period up to a finite truncation point, we derive a class of policies, called fluid-balance policies, that have a $O(\sqrt{N})$ optimality gap. Unlike the Whittle index, fluid-balance policies do not require indexability to be well-defined and their $O(\sqrt{N})$ optimality gap bound holds universally without sufficient conditions. We also demonstrate empirically that fluid-balance policies provide state-of-the-art performance on specific problems.

Yunxiang Zhang, Xiangyu Zhang, Peter I. Frazier

Recent advances in computationally efficient non-myopic Bayesian optimization (BO) improve query efficiency over traditional myopic methods like expected improvement while only modestly increasing computational cost. These advances have been largely limited, however, to unconstrained optimization. For constrained optimization, the few existing non-myopic BO methods require heavy computation. For instance, one existing non-myopic constrained BO method [Lam and Willcox, 2017] relies on computationally expensive unreliable brute-force derivative-free optimization of a Monte Carlo rollout acquisition function. Methods that use the reparameterization trick for more efficient derivative-based optimization of non-myopic acquisition functions in the unconstrained setting, like sample average approximation and infinitesimal perturbation analysis, do not extend: constraints introduce discontinuities in the sampled acquisition function surface that hinder its optimization. Moreover, we argue here that being non-myopic is even more important in constrained problems because fear of violating constraints pushes myopic methods away from sampling the boundary between feasible and infeasible regions, slowing the discovery of optimal solutions with tight constraints. In this paper, we propose a computationally efficient two-step lookahead constrained Bayesian optimization acquisition function (2-OPT-C) supporting both sequential and batch settings. To enable fast acquisition function optimization, we develop a novel likelihood-ratio-based unbiased estimator of the gradient of the two-step optimal acquisition function that does not use the reparameterization trick. In numerical experiments, 2-OPT-C typically improves query efficiency by 2x or more over previous methods, and in some cases by 10x or more.

David J. Biagioni, Xiangyu Zhang, Peter Graf et al.

We present a careful comparison of two model-free control algorithms, Evolution Strategies (ES) and Proximal Policy Optimization (PPO), with receding horizon model predictive control (MPC) for operating simulated, price responsive water heaters. Four MPC variants are considered: a one-shot controller with perfect forecasting yielding optimal control; a limited-horizon controller with perfect forecasting; a mean forecasting-based controller; and a two-stage stochastic programming controller using historical scenarios. In all cases, the MPC model for water temperature and electricity price are exact; only water demand is uncertain. For comparison, both ES and PPO learn neural network-based policies by directly interacting with the simulated environment under the same scenarios used by MPC. All methods are then evaluated on a separate one-week continuation of the demand time series. We demonstrate that optimal control for this problem is challenging, requiring more than 8-hour lookahead for MPC with perfect forecasting to attain the minimum cost. Despite this challenge, both ES and PPO learn good general purpose policies that outperform mean forecast and two-stage stochastic MPC controllers in terms of average cost and are more than two orders of magnitude faster at computing actions. We show that ES in particular can leverage parallelism to learn a policy in under 90 seconds using 1150 CPU cores.

Xiangyu Zhang, Peter I. Frazier

We consider finite-horizon restless bandits with multiple pulls per period, which play an important role in recommender systems, active learning, revenue management, and many other areas. While an optimal policy can be computed, in principle, using dynamic programming, the computation required scales exponentially in the number of arms $N$. Thus, there is substantial value in understanding the performance of index policies and other policies that can be computed efficiently for large $N$. We study the growth of the optimality gap, i.e., the loss in expected performance compared to an optimal policy, for such policies in a classical asymptotic regime proposed by Whittle in which $N$ grows while holding constant the fraction of arms that can be pulled per period. Intuition from the Central Limit Theorem and the tightest previous theoretical bounds suggest that this optimality gap should grow like $O(\sqrt{N})$. Surprisingly, we show that it is possible to outperform this bound. We characterize a non-degeneracy condition and a wide class of novel practically-computable policies, called fluid-priority policies, in which the optimality gap is $O(1)$. These include most widely-used index policies. When this non-degeneracy condition does not hold, we show that fluid-priority policies nevertheless have an optimality gap that is $O(\sqrt{N})$, significantly generalizing the class of policies for which convergence rates are known. We demonstrate that fluid-priority policies offer state-of-the-art performance on a collection of restless bandit problems in numerical experiments.

David Biagioni, Peter Graf, Xiangyu Zhang et al.

We propose a novel data-driven method to accelerate the convergence of Alternating Direction Method of Multipliers (ADMM) for solving distributed DC optimal power flow (DC-OPF) where lines are shared between independent network partitions. Using previous observations of ADMM trajectories for a given system under varying load, the method trains a recurrent neural network (RNN) to predict the converged values of dual and consensus variables. Given a new realization of system load, a small number of initial ADMM iterations is taken as input to infer the converged values and directly inject them into the iteration. We empirically demonstrate that the online injection of these values into the ADMM iteration accelerates convergence by a significant factor for partitioned 14-, 118- and 2848-bus test systems under differing load scenarios. The proposed method has several advantages: it maintains the security of private decision variables inherent in consensus ADMM; inference is fast and so may be used in online settings; RNN-generated predictions can dramatically improve time to convergence but, by construction, can never result in infeasible ADMM subproblems; it can be easily integrated into existing software implementations. While we focus on the ADMM formulation of distributed DC-OPF in this paper, the ideas presented are naturally extended to other distributed optimization problems.

Hanchen Xu, Xiao Li, Xiangyu Zhang et al.

In this letter, we address the problem of controlling energy storage systems (ESSs) for arbitrage in real-time electricity markets under price uncertainty. We first formulate this problem as a Markov decision process, and then develop a deep reinforcement learning based algorithm to learn a stochastic control policy that maps a set of available information processed by a recurrent neural network to ESSs' charging/discharging actions. Finally, we verify the effectiveness of our algorithm using real-time electricity prices from PJM.