论文检索

Jieyu Wu, Quan Zhang, Yiyuan Wang, Shiwei Pan, Jian Gao

Finding the maximum common induced subgraph (MCIS) between two graphs is a well-known NP-hard problem. While sequential MCIS algorithms have been extensively studied, parallel computing has emerged as an important direction for further performance enhancement with the advancement of computing resources. In this paper, we propose a parallel MCIS framework integrating a dynamic task decomposition method guided by search information and a novel pruning strategy based on shared information. The experimental results demonstrate that the algorithm enhanced by our framework achieves superior performance over both state-of-the-art sequential and existing parallel algorithms. Extensive results further demonstrate the wide scalability and generality of our framework, and the effectiveness of our strategies.

Chengrui Huang, Zhengliang Shi, Yuntao Wen, Xiuying Chen, Peng Han, Shen Gao, Shuo Shang

Tool learning methods have enhanced the ability of large language models (LLMs) to interact with real-world applications. Many existing works fine-tune LLMs or design prompts to enable LLMs to select appropriate tools and correctly invoke them to meet user requirements. However, it is observed in previous works that the performance of tool learning varies from tasks, datasets, training settings, and algorithms. Without understanding the impact of these factors, it can lead to inconsistent results, inefficient model deployment, and suboptimal tool utilization, ultimately hindering the practical integration and scalability of LLMs in real-world scenarios. Therefore, in this paper, we explore the impact of both internal and external factors on the performance of tool learning frameworks. Through extensive experiments on two benchmark datasets, we find several insightful conclusions for future work, including the observation that LLMs can benefit significantly from increased trial and exploration. We believe our empirical study provides a new perspective for future tool learning research.

Paul Burkhardt, David G. Harris, Kevin T. Schmitt

Model counting of Disjunctive Normal Form (DNF) formulas is a critical problem in applications such as probabilistic inference and network reliability. For example, it is often used for query evaluation in probabilistic databases. Due to the computational intractability of exact DNF counting, there has been a line of research into a variety of approximation algorithms. We develop a new Monte Carlo approach with an adaptive stopping rule and short-circuit formula evaluation. We prove it achieves Probably Approximately Correct (PAC) learning bounds and has asymptotically improved time and randomness complexity compared to previous methods. We also show experimentally that it out-performs prior algorithms by at least three orders of magnitude in running time and scalability.

Yining Lang, Zhaoxin Li, Xiujuan Chai

While deep learning has significantly enhanced robotic perception in agriculture, autonomous decision-making in dense and occluded environments remains a persistent challenge. This paper proposes a VR-based expert motion capture framework to bridge this gap by integrating high-fidelity virtual environments with human expertise. By reconstructing a realistic tomato greenhouse in Unity and utilizing 27-point motion capture suits, we captured multi-dimensional expert demonstration data encompassing trajectories, postures, and velocities. In the VR environment, ``hard cases" featuring frequent collisions can be selectively generated at a higher frequency, allowing experts to provide concentrated demonstrations of specialized postures that markedly accelerate algorithmic learning efficiency. Crucially, the virtual framework enables multiple experts to repetitively harvest identical targets to match optimal trajectories—a process precluded in reality by the destructive nature of harvesting. Moreover, it bypasses biological growth and seasonal constraints, facilitating continuous, high-frequency experimentation independent of crop maturation. These expert data were subsequently integrated into a multi-task reinforcement learning model as experience replay and reward templates. Experimental results demonstrate that our expert-driven algorithm significantly outperforms baseline methods in harvesting efficiency, collision avoidance, and stability, establishing VR-guided motion capture as a robust and scalable paradigm for advancing agricultural robotics.

Bryan Shan Guanrong, Alysa Ziying Tan, Han Yu

We present Federated Learning Playground, an interactive browser-based platform inspired by and extends TensorFlow Playground that teaches core Federated Learning (FL) concepts. Users can experiment with heterogeneous client data distributions, model hyperparameters, and aggregation algorithms directly in the browser without coding or system setup, and observe their effects on client and global models through real-time visualizations, gaining intuition for challenges such as non-IID data, local overfitting, and scalability. The playground serves as an easy to use educational tool, lowering the entry barrier for newcomers to distributed AI while also offering a sandbox for rapidly prototyping and comparing FL methods. By democratizing exploration of FL, it promotes broader understanding and adoption of this important paradigm.

Egor Suraveikin, Dastan Omirzak, Roman Sultimov, Yury Maximov

The contextual multi-armed bandit problem underlies applications in recommendations, e-commerce, finance, and healthcare, where balancing exploration and exploitation is critical. While algorithms such as Upper Confidence Bound (UCB) and Thompson Sampling (TS) achieve strong theoretical guarantees, they often incur heavy computational cost from high-dimensional parameter estimation. We propose a new approach that combines reward sampling with online stochastic optimization. At each round, the algorithm samples hypothetical rewards for all actions and selects the action with the largest draw; the observed reward then updates the model via stochastic optimization. This design is both simple and efficient, preserving exploration while avoiding the pitfalls of greedy behavior on near-duplicate arms. Across synthetic and real-world datasets, our method attains near-optimal reward more quickly and with substantially lower computation than TS and UCB, demonstrating that sampling directly in reward space can improve both statistical efficiency and scalability.

Zifeng Liu, Hai Li, Jie Chao, Wanli Xing

Multiple-choice questions (MCQs) are central to instruction and assessment, with distractors revealing student understanding and misconceptions. However, creating high-quality distractors is time-consuming, especially for emerging domains like K–12 AI education. This study explores using generative AI to support distractor creation in a self-paced online module integrating AI and Algebra 1. Five MCQs were selected to compare distractors written by human developers and ChatGPT, using expert reviews and log data from 80 students. Experts rated human distractors higher overall, though AI ones consistently ranked second. Log analysis showed human distractors drew more initial selections, while students who chose AI distractors spent more time engaging without differences in hint use or revisits. Transition patterns across attempts suggest AI-generated distractors can effectively guide students toward correct answers, highlighting their potential for scalable MCQ design.

Julian Zhong-Nan Zhang, Yang Yu

The reliable deployment of reinforcement learning (RL) for real-world algorithmic trading is critically hindered by the ``simulation-to-reality gap.'' Standard industry backtesting on static historical data ignores market impact—the feedback loop where an agent's trades influence price dynamics—leading to strategies that are fragile and untrustworthy in live markets. To solve this significant problem, we present a novel and emerging application of AI: a framework for building an interactive, responsive market simulator. Our system first uses imitation learning (IL) to automatically train an ensemble of agents, each learning a distinct trading strategy from a different historical market regime (e.g., bull, bear). This creates a data-driven proxy for a diverse population of real-world traders. We then deploy an innovative Action Synthesis Network to synthesize the actions of this ensemble, generating a realistic, synthetic price trajectory that endogenously models the market's reaction to trades. This interactive environment is then used to train a final RL policy. We evaluate our system on NASDAQ-100 (QQQ) data, and the results demonstrate strong potential for deployment. The RL policy trained in our responsive simulator achieves significantly more robust performance, exhibiting superior downside protection during market downturns compared to various traditional baselines. This application provides a scalable and technically sound methodology for building more realistic training environments, presenting a clear path toward the development and eventual deployment of more resilient and effective algorithmic trading strategies.

Benedikt Schlereth-Groh, Sakir Furkan Yöndem, Ramin Tavakoli Kolagari

Reinforcement Learning (RL) has shown significant promise in developing autonomous navigation algorithms for complex environments. However, the direct application of RL policies trained in simulation to real-world scenarios often faces challenges due to the reality gap. This paper proposes a two-stage system incorporating a segmentation strategy and a bird’s-eye-view (BEV) representation to mitigate the domain gap between simulation and reality. In the first stage, the segmentation transforms sensor data into a simplified and interpretable representation of the surrounding area, facilitating transferability across different deployments. In the second stage, the agent navigates through the BEV map, which can be trained using a vectorized simulation environment---a setup that runs multiple parallel instances of the environment to provide a wide range of training scenarios. This vectorization enables rapid exposure to varied environmental conditions, thereby accelerating and diversifying the training of a deep RL agent to achieve optimal navigation behaviors while maintaining high-speed, in-bound trajectories. The segmentation is crucial because it supports generalization of the learned policy across different robotic platforms. The contribution of this paper lies in combining real-time semantic segmentation with a bird’s-eye-view navigation policy, resulting in a transferable and scalable framework for real-world deployment of RL-based navigation agents. Experimental results demonstrate that agents trained with this methodology exhibit robust navigation performance and adaptability in both simulated and real-world environments, validating the efficacy of combining vectorized simulation with real-world segmentation for practical robotic navigation.

Gaowei Zhang, Wei Wang, Tiong Lee Kong, Kai Xing, Huan Li, Yi Wang

Ensuring safety in power grid construction remains a critical yet challenging task, as existing monitoring approaches often lack scalability, timeliness, and adaptability to diverse on-site conditions. To address these limitations, we present ConstructAI, a deployed AI-driven safety management system that integrates multi-source image and video acquisition devices with advanced multimodal large model reasoning. The system combines text, image, and video prompts through an efficient workflow powered by LLaMA3 and Meta SAM2 backbones, enhanced with LoRA and adaptor modules for multimodal fusion. Once deployed, ConstructAI continuously processes real-time construction footage to identify violations, assess risk levels, and generate standardized rectification requirements. The deployment has demonstrated measurable benefits across multiple sites, including a >70% increase in violation rectification rates, reduction of average rectification delays from hours to minutes, and a 45% decline in repeat violations. Beyond technical gains, ConstructAI has delivered significant business impacts, such as reduced safety incidents, improved compliance with national regulations, and higher operational efficiency. By enabling proactive risk management and structured safety feedback loops, our system exemplifies how innovative use of AI can translate into tangible improvements for industrial safety. The lessons learned from deployment highlight the importance of balancing algorithmic advances with practical integration into organizational workflows.

Yang Xi, Orelia Pi, Miaomiao Zhang, Rebecca Xiong, Jacqueline Lane, Nihar B Shah

There is growing interest in applying artificial intelligence (AI) to automate and support complex decision-making tasks. However, it remains unclear how algorithms compare to human judgment in contexts requiring semantic understanding and domain expertise. We examine this in the context of the judge assignment problem, matching submissions to suitably qualified judges. Specifically, we tackled this problem at the Harvard President’s Innovation Challenge, the university’s premier venture competition awarding over $500,000 to student and alumni startups. This setting represents a real-world environment where high-quality judge assignment is essential. We developed an AI-based judge assignment algorithm, the Hybrid Lexical-Semantic Similarity Ensemble (HLSE), and deployed it at the competition. We then evaluated its performance against human expert assignments using blinded match-quality scores from judges on 309 judge-venture pairs. Using a Mann-Whitney U statistic-based test, we found no statistically significant difference in assignment quality between the two approaches (AUC=0.48, p=0.40); on average, algorithmic matches were rated 3.90 and manual matches 3.94 on a 5-point scale, where 5 indicates an excellent match. Furthermore, manual assignments that previously required a full week could be automated in several hours by the algorithm during deployment. These results demonstrate that HLSE achieves human-expert-level matching quality while offering greater scalability and efficiency, underscoring the potential of AI-driven solutions to support and enhance human decision-making for judge assignment in high-stakes settings.

Stylianos Loukas Vasileiou, William Yeoh, Alessandro Previti, Tran Cao Son

Explanation generation frameworks aim to make AI systems’ decisions transparent and understandable to human users. However, generating explanations in uncertain environments characterized by incomplete information and probabilistic models remains a significant challenge. In this paper, we propose a novel framework for generating probabilistic monolithic explanations and model reconciling explanations. Monolithic explanations provide self-contained reasons for an explanandum without considering the agent receiving the explanation, while model reconciling explanations account for the knowledge of the agent receiving the explanation. For monolithic explanations, our approach integrates uncertainty by utilizing probabilistic logic to increase the probability of the explanandum. For model reconciling explanations, we propose a framework that extends the logic-based variant of the model reconciliation problem to account for probabilistic human models, where the goal is to find explanations that increase the probability of the explanandum while minimizing conflicts between the explanation and the probabilistic human model. We introduce explanatory gain and explanatory power as quantitative metrics to assess the quality of these explanations. Further, we present algorithms that exploit the duality between minimal correction sets and minimal unsatisfiable sets to efficiently compute both types of explanations in probabilistic contexts. Extensive experimental evaluations on various benchmarks demonstrate the effectiveness and scalability of our approach in generating explanations under uncertainty.

Chengyang He, Tanishq Duhan, Parth Tulsyan, Patrick Kim, Guillaume Sartoretti

The Multi-agent Path Finding (MAPF) problem involves finding collision-free paths for a team of agents in a known, static environment, with important applications in warehouse automation, logistics, or last-mile delivery. To meet the needs of these large-scale applications, current learning-based methods often deploy the same fully trained, decentralized network to all agents to improve scalability. However, such parameter sharing typically results in homogeneous behaviors among agents, which may prevent agents from breaking ties around symmetric conflict (e.g., bottlenecks) and might lead to live-/deadlocks. In this paper, we propose SYLPH, a novel learning-based MAPF framework aimed to mitigate the adverse effects of homogeneity by allowing agents to learn and dynamically select different social behaviors (akin to individual, dynamic roles), without affecting the scalability offered by parameter sharing. Specifically, SYLPH offers a novel hierarchical mechanism by introducing Social Value Orientation (SVO) as a temporally extended latent variable that plays a central role in both policy generation and reward assignment. To support this hierarchical decision-making process, we introduce Social-aware Multi-Policy PPO (SMP3O), a reinforcement learning method that ensures stable and effective training through a mechanism for the cross-utilization of advantages. Moreover, we design an SVO-based learning tie-breaking algorithm, allowing agents to proactively avoid collisions, rather than relying solely on post-processing techniques. As a result of this hierarchical decision-making and exchange of social preferences, SYLPH endows agents with the ability to reason about the MAPF task through more latent spaces and nuanced contexts, leading to varied responses that can help break ties around symmetric conflicts. Our comparative experiments show that SYLPH achieves state-of-the-art performance, surpassing other learning-based MAPF planners in random, room-like, and maze-like maps, while our ablation studies demonstrate the advantages of each component in SYLPH. We finally experimentally validate our trained policies on hardware in three types of maps, showing how SYLPH allows agents to find high-quality paths under real-life conditions. Our code and videos are available at: marmotlab.github.io/mapf_sylph.

Hosein Hasanbeig, Natasha Yogananda Jeppu, Alessandro Abate, Tom Melham, Daniel Kroening

This paper proposes DeepSynth, a method for effective training of deep reinforcement learning agents when the reward is sparse or non-Markovian, but at the same time progress towards the reward requires achieving an unknown sequence of high-level objectives. Our method employs a novel algorithm for synthesis of compact finite state automata to uncover this sequential structure automatically. We synthesise a human-interpretable automaton from trace data collected by exploring the environment. The state space of the environment is then enriched with the synthesised automaton, so that the generation of a control policy by deep reinforcement learning is guided by the discovered structure encoded in the automaton. The proposed approach is able to cope with both high-dimensional, low-level features and unknown sparse or non-Markovian rewards. We have evaluated DeepSynth’s performance in a set of experiments that includes the Atari game Montezuma’s Revenge, known to be challenging. Compared to approaches that rely solely on deep reinforcement learning, we obtain a reduction of two orders of magnitude in the iterations required for policy synthesis, and a significant improvement in scalability.

Kai Wang

The Knowledge of Optimization And Learning Algorithms (KOALA) group studies how to integrate optimization, machine learning, and generative modeling to enable data-driven decision-making under uncertainty. We study decision-focused learning, embedding optimization as a differentiable layer to train models end-to-end for decision quality. We design scalable reinforcement learning algorithms for population and personalized healthcare, and develop efficient bilevel optimization methods for nested and multi-agent decision-making. These directions form a unified framework linking optimization and learning for impactful AI in healthcare. Through collaborations with hospitals and NGOs, our group designs and deploys algorithms for pediatric, diabetes, maternal, and mental health applications. Looking ahead, we aim to unite these foundations with generative AI to build theoretically grounded and socially responsible algorithms that advance trustworthy, real-world AI for health and beyond.

Xuefeng Du

This talk surveys my research journey toward building reliable machine learning systems that behave safely and predictably in the open world. While modern machine learning models—including foundation models (FMs)—have demonstrated unprecedented capabilities, they often suffer from reliability failures under distribution shift, leading to overconfident mispredictions, hallucinated generations, or susceptibility to adversarial prompts. My research rethinks reliability not as an afterthought, but as a first-class algorithmic principle, to be optimized alongside accuracy with minimal human supervision. The talk is organized around three key threads. To respect the allotted 20-30 minutes, the first and second parts will be briefly discussed. 1. Unknown-Aware Learning via Outlier Synthesis. I introduce a class of learning algorithms that synthesize “virtual outliers” in representation or pixel space to explicitly teach models what they don’t know. This includes the VOS, NPOS, and Dream-OOD frameworks, which shape the energy landscape around in-distribution data to avoid overconfidence on OOD. 2. Learning in the Wild with Unlabeled Data. I present theoretical insights and practical algorithms for leveraging unlabeled in-the-wild data to improve reliability. This includes SAL framework, which uses a gradient-based spectral method to separate potential outliers, and SCONE, which handles semantic and covariate shifts via constrained optimization. These results turn unlabeled data contamination into a learning signal. 3. Reliable Foundation Models. I explore reliability failures in LLMs and multimodal systems. I introduce HaloScope for hallucination detection via subspace separation on LLM representations, and TSV that performs LLM latent steering for improved hallucination detection. I will also briefly cover the LLM security and alignment, which includes VLMGuard for detecting malicious prompts in vision-language models and a data-centric paradigm for AI alignment through source-aware feedback cleaning. Throughout the talk, I highlight how representation learning, data generation, and theoretical guarantees intersect to produce scalable, label-efficient reliability methods. I will also reflect on my broader vision: designing proactive and collaborative AI systems that anticipate uncertainty and support rich human-AI interaction—especially for underrepresented communities and emerging scientific domains. This talk will be accessible to a broad AAAI audience, combining foundational algorithmic insights with real-world applications and forward-looking perspectives on the future of responsible AI.

Grigorios Chrysos

As large language models (LLMs) scale, ensuring interpretability and privacy becomes critical. This talk addresses these interconnected challenges with novel approaches to model specialization and safety. First, we tackle the dense, distributed nature of LLM representations by casting Mixture-of-Experts (MoE) as a tensor decomposition, enabling specialized experts in a factorized space. Second, we argue that current neuron-level sparsity methods create a severe accuracy-sparsity trade-off, and we propose a paradigm shift to layer-level sparsity with the Mixture of Decoders (MxD). We explain how MxD uses tensor factorization to expand dense layers into thousands of specialized, full-rank sublayers, demonstrating how it significantly outperforms alternatives in preserving model faithfulness and performance across LLMs up to 3B parameters. Finally, we address privacy in open-weight models by proposing a scalable and certifiable algorithm that induces maximal uncertainty on protected instances, proving tight bounds that characterize the resulting privacy-utility tradeoff.

XuWen Zhang, Xiao Xue, Xia Xie, Qun Ma

Crowdsourced delivery platforms (e.g., Meituan, Uber Eats, DoorDash) have become vital infrastructure in urban logistics, yet their competitive order-grabbing mechanisms often lead to strategy homogenization, inefficiency, and income inequality. This paper presents ARDE (Adaptive Regulation via Dual-layer Evolution), an evolutionary governance framework that integrates individual reinforcement learning with adaptive platform-level regulation. The outer agent dynamically generates governance signals based on system diagnostics (strategy entropy, Gini coefficient, completion rate), while inner agents employ Diffusion Q-Learning guided by a language-model-driven reward shaping module to promote fairness and strategy diversity. Experiments on real-world datasets show that ARDE achieves stable diversity (0.997 ± 0.184), reduces inequality (Gini change 1.3%), and maintains high efficiency. Further comparison (ARDE-PPO vs. MAPPO) confirms that its advantages stem from explicit hierarchical governance rather than algorithmic coincidence. Overall, ARDE offers a scalable and interpretable paradigm for reconciling individual rationality with collective welfare in gig economies and other multi-agent socio-technical systems.

Aran Nayebi

We formalize AI alignment as a multi-objective optimization problem called -agreement, in which a set of N agents (including humans) must reach approximate (ε) agreement across M candidate objectives, with probability at least 1-δ. Analyzing communication complexity, we prove an information-theoretic lower bound showing that once either M or N is large enough, no amount of computational power or rationality can avoid intrinsic alignment overheads. This establishes rigorous limits to alignment *itself*, not merely to particular methods, clarifying a "No-Free-Lunch" principle: encoding "all human values" is inherently intractable and must be managed through consensus-driven reduction or prioritization of objectives. Complementing this impossibility result, we construct explicit algorithms as achievability certificates for alignment under both unbounded and bounded rationality with noisy communication. Even in these best-case regimes, our bounded-agent and sampling analysis shows that with large task spaces (D) and finite samples, *reward hacking is globally inevitable*: rare high-loss states are systematically under-covered, implying scalable oversight must target safety-critical slices rather than uniform coverage. Together, these results identify fundamental complexity barriers---tasks (M), agents (N), and state-space size (D)---and offer principles for more scalable human-AI collaboration.

Fares Fourati, Mohamed-Slim Alouini, Vaneet Aggarwal

We propose ECPv2, a scalable and theoretically grounded algorithm for global optimization of Lipschitz continuous functions with unknown Lipschitz constants. Building on the Every Call is Precious (ECP) framework, which ensures that each accepted function evaluation is potentially informative, ECPv2 addresses key limitations of ECP, including high computational cost and overly conservative early behavior. ECPv2 introduces three innovations: (i) an adaptive lower bound that prevents vacuous acceptance regions, (ii) a memory mechanism that restricts comparisons to a fixed-size subset of past evaluations, and (iii) a fixed random projection that accelerates distance computations in high dimensions. We theoretically show that ECPv2 retains ECP’s regret guarantees and expands the acceptance region with high probability. Extensive experiments and ablation studies empirically validate these findings. Using principled hyperparameter settings, we evaluate ECPv2 across a wide range of nonconvex optimization problems and find that it consistently matches or outperforms leading optimizers while significantly reducing wall clock time.