论文检索

Carter Blair, Kate Larson, Edith Law

AI agents are commonly aligned with "human values" through reinforcement learning from human feedback (RLHF), where a single reward model is learned from aggregated human feedback and used to align an agent's behavior. However, human values are not homogeneous--different people hold distinct and sometimes conflicting values. Aggregating feedback into a single reward model risks disproportionately suppressing minority preferences. To address this, we present a novel reward modeling approach for learning individualized reward models. Our approach uses a language model to guide users through reflective dialogues where they critique agent behavior and construct their preferences. This personalized dialogue history, containing the user's reflections and critiqued examples, is then used as context for another language model that serves as an individualized reward function (what we call a "verbal reward model") for evaluating new trajectories. In studies with 30 participants, our method achieved a 9-12% improvement in accuracy over non-reflective verbal reward models while being more sample efficient than traditional supervised learning methods.

Tongtong Su, Chengyu Wang, Bingyan Liu, Jun Huang, Dongming Lu

Video editing is a pivotal process for customizing video content according to user needs. However, existing text-guided methods often lead to ambiguities regarding user intentions and restrict fine-grained control for editing specific aspects in videos. To overcome these limitations, this paper introduces a novel approach named \emph{AdaptEdit}, which focuses on reference-based video editing that disentangles the editing process. It achieves this by first editing a reference image and then adaptively propagating its appearance across other frames to complete the video editing. While previous propagation methods, such as optical flow and the temporal modules of recent video generative models, struggle with object deformations and large motions, we propose an adaptive correspondence strategy that accurately transfers the appearance from the reference frame to the target frames by leveraging inter-frame semantic correspondences in the original video. By implementing a proxy-editing task to optimize hyperparameters for image token-level correspondence, our method effectively balances the need to maintain the target frame's structure while preventing leakage of irrelevant appearance. To more accurately evaluate editing beyond the semantic-level consistency provided by CLIP-style models, we introduce a new dataset, PVA, which supports pixel-level evaluation. Our method outperforms the best-performing baseline with a clear PSNR improvement of 3.6 dB.

Mao Xun Huang, Brian J Chan, Hen-Hsen Huang

Stable Diffusion models have made remarkable strides in generating photorealistic images from text prompts but often falter when tasked with accurately representing complex spatial arrangements, particularly involving intricate 3D relationships. To address this limitation, we introduce SmartSpatial, an innovative approach that not only enhances the spatial arrangement capabilities of Stable Diffusion but also fosters AI-assisted creative workflows through 3D-aware conditioning and attention-guided mechanisms. SmartSpatial incorporates depth information injection and cross-attention control to ensure precise object placement, delivering notable improvements in spatial accuracy metrics. In conjunction with SmartSpatial, we present SmartSpatialEval, a comprehensive evaluation framework that bridges computational spatial accuracy with qualitative artistic assessments. Experimental results show that SmartSpatial significantly outperforms existing methods, setting new benchmarks for spatial fidelity in AI-driven art and creativity.

HsiaoYuan Hsu, Yuxin Peng

In AI-empowered poster design, content-aware layout generation is crucial for the on-image arrangement of visual-textual elements, e.g., logo, text, and underlay. To perceive the background images, existing work demanded a high parameter count that far exceeds the size of available training data, which has impeded the model's real-time performance and generalization ability. To address these challenges, we proposed a patch-level data summarization and augmentation approach, vividly named Scan-and-Print. Specifically, the scan procedure selects only the patches suitable for placing element vertices to perform fine-grained perception efficiently. Then, the print procedure mixes up the patches and vertices across two image-layout pairs to synthesize over 100% new samples in each epoch while preserving their plausibility. Besides, to facilitate the vertex-level operations, a vertex-based layout representation is introduced. Extensive experimental results on widely used benchmarks demonstrated that Scan-and-Print can generate visually appealing layouts with state-of-the-art quality while dramatically reducing computational bottleneck by 95.2%. The project page is at https://thekinsley.github.io/Scan-and-Print/.

Yixuan Zhao, Hongkai Wen, Xingchen Zhang, Man Luo

Accurate demand prediction is crucial for the equitable and sustainable expansion of bike-sharing systems, which help reduce urban congestion, promote low-carbon mobility, and improve transportation access in underserved areas. However, expanding these systems presents societal challenges, particularly in ensuring fair resource distribution and operational efficiency. A major hurdle is the difficulty of demand prediction at new stations, which lack historical usage data and are heavily influenced by the existing network. Additionally, new stations dynamically reshape demand patterns across time and space, complicating efforts to balance supply and accessibility in evolving urban environments. Existing methods model relationships between new and existing stations but often assume static patterns, overlooking how new stations reshape demand dynamics over time and space. To tackle these challenges, we propose a novel demand prediction framework for expanding bike-sharing systems, namely BGM, which leverages dynamic graph modeling to capture the evolving inter-station correlations while accounting for spatial and temporal heterogeneity. Specifically, we develop a knowledge transfer approach that studies the embeddings transformation across existing and new stations through a learnable orthogonal mapping matrix. We further design a gated selecting vector-based feature fusion mechanism to integrate the transferred embeddings and the intrinsic features of stations for precise predictions. Experiments on real-world bike-sharing data demonstrate that BGM outperforms existing methods.

Jinwei Zeng, Yu Liu, Guozhen Zhang, Jingtao Ding, Yuming Lin, Jian Yuan, Yong Li

Accurately estimating high-resolution carbon emissions is crucial for effective emission governance and mitigation planning. While conventional methods for precise carbon accounting are hindered by substantial data collection efforts, the rise of open data and advanced learning techniques offers a promising solution. Once an open data-based prediction model is developed and trained, it can easily infer emissions for new areas based on available open data. To address this, we incorporate two modalities of open data, satellite images and point-of-interest (POI) data, to predict high-resolution urban carbon emissions, with satellite images providing macroscopic and static and POI data offering fine-grained and relatively dynamic functionality information. However, estimating high-resolution carbon emissions presents two significant challenges: the intertwined and implicit effects of various functionalities on carbon emissions, and the complex spatial contiguity correlations that give rise to the agglomeration effect. Our model, OpenCarbon, features two major designs that target the challenges: a cross-modality information extraction and fusion module to extract complementary functionality information from two modules and model their interactions, and a neighborhood-informed aggregation module to capture the spatial contiguity correlations. Extensive experiments demonstrate our model's superiority, with a significant performance gain of 26.6% on R2. Further generalizability tests and case studies also show OpenCarbon's capacity to capture the intrinsic relation between urban functionalities and carbon emissions, validating its potential to empower efficient carbon governance and targeted carbon mitigation planning. Codes and data are available: https://github.com/JinweiZzz/OpenCarbon.

Benedetta Muscato, Lucia Passaro, Gizem Gezici, Fosca Giannotti

In the realm of Natural Language Processing (NLP), common approaches for handling human disagreement consist of aggregating annotators' viewpoints to establish a single ground truth. However, prior studies show that disregarding individual opinions can lead to the side-effect of under-representing minority perspectives, especially in subjective tasks, where annotators may systematically disagree because of their preferences. Recognizing that labels reflect the diverse backgrounds, life experiences, and values of individuals, this study proposes a new multi-perspective approach using soft labels to encourage the development of the next generation of perspective-aware models—more inclusive and pluralistic. We conduct an extensive analysis across diverse subjective text classification tasks including hate speech, irony, abusive language, and stance detection, to highlight the importance of capturing human disagreements, often overlooked by traditional aggregation methods. Results show that the multi-perspective approach not only better approximates human label distributions, as measured by Jensen-Shannon Divergence (JSD), but also achieves superior classification performance (higher F1-scores), outperforming traditional approaches. However, our approach exhibits lower confidence in tasks like irony and stance detection, likely due to the inherent subjectivity present in the texts. Lastly, leveraging Explainable AI (XAI), we explore model uncertainty and uncover meaningful insights into model predictions. All implementation details are available at our github repo.

Yue Mao, Zhongdi Qu, Imanol Miqueleiz, Aaron Ferber, Sami Wolf, Marc Grimson, Sebastian Heilpern, Felipe S. Pacheco, Alexander S. Flecker, Peter B. McIntyre 等

Climate change and biodiversity loss are among humanity’s most pressing challenges. In 2022, under the auspices of the United Nations, over 190 countries reached a historic agreement to address the alarming loss of biodiversity and restore natural ecosystems. Target 3, often referred to as ``30x30'', seeks to effectively protect and manage 30% of the world’s terrestrial, inland water, coastal, and marine areas by 2030. In this work, we address the UN 30x30 target in the context of global freshwater fish conservation. Freshwater ecosystems are disproportionately unprotected, and their biota are declining at an alarming rate. Our goal is to select new protected areas that protect freshwater fish species as much as possible without exceeding total coverage of 30% of land area. To support this goal, we introduce the Expansion of Connected Components from Alternative Terminals Problem, a graph-based optimization problem that captures ecological priorities and connectivity constraints. We analyze its computational complexity, propose novel integer programming formulations, and develop scalable solution methods. We further evaluate its typical-case complexity under diverse settings and demonstrate that our approach scales to a global real-world scope, encompassing approximately 200,000 freshwater basins and 13,000 species, paving the way for implementing the 30x30 target on a worldwide scale.

Sulian Le Bozec-Chiffoleau, Dimitri Justeau-Allaire, Xavier Lorca, Charles Prud'homme, Gilles Simonin, Philippe Vismara, Philippe Birnbaum, Nicolas Rinck, Nicolas Beldiceanu

The Kunming-Montreal Global Biodiversity Framework aims to protect 30% of terrestrial, inland water, marine, and coastal ecosystems worldwide, and ensuring that at least 30% of these areas are under effective restoration by 2030. Maintaining and restoring ecological connectivity between natural habitats and protected areas is a key feature of this target. Achieving it will require effective and inclusive spatial planning supported by appropriate decision-support tools. Most spatial planning models address budget as an objective and connectivity as a constraint, formulating problems with Steiner trees. In many real-world cases, such as landscape-scale restoration planning, this formulation is inappropriate when environmental managers seek to optimise connectivity under a budget constraint. This problem was previously addressed with Constraint Programming (CP) and graph variables, but the current approach is severely limited in terms of spatial resolution. In this article, we formalise this problem as the budget-constrained graph connectivity optimisation problem. Based on a real case study: the restoration of forest connectivity in New Caledonia, we illustrate why ``naive'' CP approaches are inefficient. In response, we provide a preprocessing method based on Hanan grids which preserves the existence of at least one optimal solution. Finally, we assess the efficiency of our approach in the New Caledonian case study.

Wenjing Li, Zhao Li, Xuanwu Liu, Ruihao Zhu, Zhenzhe Zheng, Fan Wu

E-bikes (EBs) are a key transportation mode in urban area, especially for couriers of delivery platforms, but underdeveloped EB systems can hinder courier's productivity due to limited battery capacity. Battery-swapping stations address this issue by enabling riders to exchange depleted batteries for fully charged ones. However, managing supply and demand (SnD) imbalances at these stations has become increasingly complex. To address this, we introduce a new approach that formulates the Battery-Swapping Problem (BSP) as a discrete-time Markov Decision Process (MDP) to capture the dynamics of SnD imbalances. Building on it, we propose a Wasserstein-enhanced Proximal Policy Optimization (W-PPO) algorithm, which integrates Wasserstein distance with reinforcement learning to improve the robustness against uncertainty in forecasting SnD. W-PPO provides a BSP-specific, accurate loss function that reflects reward variations between two policies under real-world simulation. The algorithm’s effectiveness is assessed using key metrics: Shared Battery Utilization Ratio (SBUR) and Battery Supply Ratio (BSR). Simulations on real-world datasets show that W-PPO achieves a 30.59% improvement in SBUR and a 16.09% increase in BSR ensures practical applicability. By optimizing battery utilization and improving EB delivery systems, this work highlights the potential of AI for creating efficient and sustainable urban transportation solutions.

Jisheng Dang, Shengjun Deng, Haochen Chang, Teng Wang, Bimei Wang, Shude Wang, Nannan Zhu, Guo Niu, Jingwen Zhao, Jizhao Liu

The rapid advancement of large language models (LLMs) has led to the widespread adoption of video-language models (VLMs) across various domains. However, VLMs are often hindered by their limited semantic discrimination capability, exacerbated by the limited diversity and biased sample distribution of most video-language datasets. This limitation results in a biased understanding of the semantics between visual concepts, leading to hallucinations. To address this challenge, we propose a Multi-level Multimodal Alignment (MMA) framework that leverages a text encoder and semantic discriminative loss to achieve multi-level alignment. This enables the model to capture both low-level and high-level semantic relationships, thereby reducing hallucinations. By incorporating language-level alignment into the training process, our approach ensures stronger semantic consistency between video and textual modalities. Furthermore, we introduce a two-stage progressive training strategy that exploits larger and more diverse datasets to enhance semantic alignment and better capture general semantic relationships between visual and textual modalities. Our comprehensive experiments demonstrate that the proposed MMA method significantly mitigates hallucinations and achieves state-of-the-art performance across multiple video-language tasks, establishing a new benchmark in the field.

Libo Zhang, Yang Chen, Toru Takisaka, Kaiqi Zhao, Weidong Li, Jiamou Liu

Sequential Resource Allocation with situational constraints presents a significant challenge in real-world applications, where resource demands and priorities are context-dependent. This paper introduces a novel framework, SCRL, to address this problem. We formalize situational constraints as logic implications and develop a new algorithm that dynamically penalizes constraint violations. To handle situational constraints effectively, we propose a probabilistic selection mechanism to overcome limitations of traditional constraint reinforcement learning (CRL) approaches. We evaluate SCRL across two scenarios: medical resource allocation during a pandemic and pesticide distribution in agriculture. Experiments demonstrate that SCRL outperforms existing baselines in satisfying constraints while maintaining high resource efficiency, showcasing its potential for real-world, context-sensitive decision-making tasks.

Isaac Stone, Nathan R. Sturtevant, Jonathan Schaeffer

Among the most popular games played worldwide, Bridge stands out for having had little AI progress for over 25 years. Ginsberg's Partition Search algorithm (1996) was a breakthrough for double-dummy Bridge play, allowing a program to reason about sets of states rather than individual states. Partition Search supports the current state of the art for both bidding and cardplay. In the time since, virtually no progress has been made in Bridge bidding. Inspired by Ginsberg's idea, this paper presents Setrograde Analysis, a new set-based algorithm for perfectly solving Bridge hands. Using this approach, we have solved all 7-trick (28-card) hands — 10^30 states, which can be reduced to 10^17 unique states using preexisting techniques. This was done by considering five orders of magnitude fewer sets than the traditional state-based Retrograde Analysis algorithm. This work suggests that the entire 13-trick (52-card) state space can be solved with modern technology using this new approach. The 7-trick computation represents the largest endgame database to date in any game.

Jiyuan Pei, Yi Mei, Jialin Liu, Mengjie Zhang

Meta-Black-Box Optimization (MetaBBO) garners attention due to its success in automating the configuration and generation of black-box optimizers, significantly reducing the human effort required for optimizer design and discovering optimizers with higher performance than classic human-designed optimizers. However, existing MetaBBO methods conduct one-off training under the assumption that a stationary problem distribution with extensive and representative training problem samples is pre-available. This assumption is often impractical in real-world scenarios, where diverse problems following shifting distribution continually arise. Consequently, there is a pressing need for methods that can continuously learn from new problems encountered on-the-fly and progressively enhance their capabilities. In this work, we explore a novel paradigm of lifelong learning in MetaBBO and introduce LiBOG, a novel approach designed to learn from sequentially encountered problems and generate high-performance optimizers for Black-Box Optimization (BBO). LiBOG consolidates knowledge both across tasks and within tasks to mitigate catastrophic forgetting. Extensive experiments demonstrate LiBOG's effectiveness in learning to generate high-performance optimizers in a lifelong learning manner, addressing catastrophic forgetting while maintaining plasticity to learn new tasks.

Siyang Zhang, Bin Li, Jingtao Qi, Xueying Wang, Fu Li, Jianan Wang, En Zhu, Jinjing Sun

Behavior trees(BTs) provide a systematic and structured control architecture extensively employed in game AI and robotic behavior control, owing to their modularity, reactivity, and reusability. Nonetheless, manual BTs design requires significant expertise and becomes inefficient as task complexity increases. Recent automation technologies have avoided manual work, but often have high application barriers and face challenges in adapting to new tasks, making it difficult to easily configure them to specific requirements. Code-BT introduces a novel approach that utilizes large language models(LLMs) to automatically generate BTs, representing the task planning process as the process of coding and organizing sequences. By retrieving control flow information from the generated code, BTs can be efficiently constructed to address the complexity and diversity of task planning challenges. Rather than relying on manual design, Code-BT uses task instructions to guide the selection of relevant APIs, and then systematically assembles these APIs into modular code to align with the BTs structure. Finally, action sequences and control logic are extracted from the generated code to construct the BTs. Our approach not only ensures the automation of BTs generation but also guarantees the scalability and adaptability for long-term tasks. Experimental results demonstrate that Code-BT substantially improves LLM performance in BTs generation, achieving improvements ranging from16.67% to 29.17%.

Monu Nagar, Debasis Das

Vision-based motion planning is a crucial task in Autonomous Driving (AD). Recent advancements in urban AD show that integrating Imitation Learning (IL) with Deep Reinforcement Learning (DRL) improves decision-making to be more like humans. However, IL methods depend on expert demonstrations to learn the optimal policy. The main drawback of this approach is the assumption that expert demonstrations are always optimal, which is not always true in real-world settings. This creates challenges in adapting to diverse weather conditions and dynamic traffic scenarios, often resulting in higher collision rates and increased risks to pedestrian safety. To address these challenges, we propose a Diffusion-Guided Deep Reinforcement Learning (DGDRL) framework that integrates a diffusion model with a Soft Actor-Critic DRL method to effectively mitigate environmental uncertainties and enable self-learning beyond the training maps for new tasks. This framework follows a novel modified partially observable Markov decision process (mPOMDP) to choose optimal action from original and diffusion-generated observations, ensuring that the policy behavior remains consistent with the current action. We use the CARLA NoCrash benchmark to train and evaluate the proposed framework. The method is validated in diverse urban environments (e.g., empty, regular, and dense) across multiple towns. Additionally, we compare our model against state-of-the-art techniques to ensure robustness and generalizability to new environments. The project page and code are available at the link https://autovisionproject.github.io/project/.

Alexander Tuisov, Evgeny Mishlyakov, Alexander Shleyfman, Erez Karpas

Multiple agents operating in a shared environment can interfere with each other’s ability to reach their goals. One of the approaches to address this issue is enacting a social law – a set of rules that restricts some possible behaviors of the agents. A social law is considered robust if it guarantees that each agent can achieve its goal independently of the actions of other agents. Recent work has shown how to verify that a given social law, encoded in an MA-STRIPS formalism, is robust by compilation to classical planning. Follow-up work presented an extended compilation which can handle numeric multi-agent planning. In this paper, we present a new compilation, which can handle both classical and numeric multi-agent planning formalisms, as well as any other multi-agent planning formalism with instantaneous actions, in which action preconditions can be negated using first-order logic with equality. This opens the door to using social laws in even richer planning formalisms. Our empirical evaluation shows that the added expressivity of the new compilation does not hurt its performance, and it achieves comparable performance to the previous state-of-the-art compilations.

Matan Shamir, Reuth Mirsky

Goal Recognition (GR) is the problem of recognizing an agent's objectives based on observed actions. Recent data-driven approaches for GR alleviate the need for costly, manually crafted domain models. However, these approaches can only reason about a pre-defined set of goals, and time-consuming training is needed for new emerging goals. To keep this model-learning automated while enabling quick adaptation to new goals, this paper introduces GRAML: Goal Recognition As Metric Learning. GRAML frames GR as a deep metric learning problem, using a Siamese network composed of recurrent units to learn an embedding space where traces leading to the same goal are close, and those leading to different goals are distant. This metric is particularly effective for adapting to new goals, even when only a single example trace is available per goal. Evaluated on a versatile set of environments, GRAML shows speed, flexibility, and runtime improvements over the state-of-the-art GR while maintaining accurate recognition.

Tal Berman, Ronen I. Brafman, Erez Karpas

Stochastic planning problems are typically modeled as Markov Decision Processes, in which actions are assumed to be instantaneous and applied sequentially. Yet, real-world actions often have durations and are applied concurrently. This paper presents an online planning approach that can deal with durative actions with stochastic outcomes. Our approach relies on Monte Carlo Tree Search with a new backpropagation procedure and temporal reasoning techniques that address the need to not only choose which action to execute, but also when to execute it. We also introduce a novel heuristic that combines reasoning about time and probabilities. Overall, we present the first online planner for stochastic temporal planning, solving a richer problem representation than previous work while achieving state-of-the-art empirical results.

Huangming Xu, Fu Zhang, Jingwei Cheng, Xin Li

The goal of document-level relation extraction (DocRE) is to identify relations between entities from multiple sentences. As a multi-label classification task, a common approach is to determine whether there are relations for an entity pair by selecting a multi-label classification threshold, with scores of relations above the threshold predicted as positive and the rest as negative. However, we find that predicting multiple relations for entity pairs causes the decrease of predicted scores in positive classes. This could lead to many positive classes being incorrectly predicted as negative. Additionally, our analysis suggests that fitting the distribution of predicted relations to the prior distribution of relations can help improve prediction performance. However, previous studies have not explored or leveraged the prior distribution of relations. To address these issues and findings, we for the first time propose the idea of incorporating the relational prior distribution into the loss calculation in DocRE tasks. We innovatively propose an Adaptive Relational Prior Distribution Loss (ARPDL), which can adaptively adjust relation prediction scores based on the relational prior distribution. Our designed relational prior distribution component can also be integrated as an adapter into other threshold-based losses to improve prediction performance. Experimental results demonstrate that ARPDL consistently improves the performance of existing DocRE models, achieving new state-of-the-art results. Furthermore, integrating our relational prior distribution adapter into other losses significantly enhances their performance in DocRE tasks, validating the effectiveness and generality of our approach. Code is available at https://github.com/xhm-code/ARPDL.