Central South University
AI Insights
- Retrieval-augmented generation (RAG): a technique that uses a retriever model to retrieve relevant information from a database and then generates text based on this information. [3]
- Limited domain knowledge Lack of personalization The paper discusses the work of various researchers in the field, including Patrick Lewis et al. [3]
- (2020), who introduced the concept of retrieval-augmented generation. [3]
- The paper discusses the use of large language models (LLMs) for travel planning and itinerary generation. [2]
Abstract
Addressing itinerary modification is crucial for enhancing the travel experience as it is a frequent requirement during traveling. However, existing research mainly focuses on fixed itinerary planning, leaving modification underexplored. To bridge this gap, we formally define the itinerary modification task and introduce iTIMO, a dataset specifically tailored for this purpose. We identify the lack of {\itshape need-to-modify} itinerary data as the critical bottleneck hindering research on this task and propose a general pipeline to overcome it. This pipeline frames the generation of such data as an intent-driven perturbation task. It instructs large language models to perturb real world itineraries using three atomic editing operations: REPLACE, ADD, and DELETE. Each perturbation is grounded in three intents, including disruptions of popularity, spatial distance, and category diversity. Furthermore, a hybrid evaluation metric is designed to ensure perturbation effectiveness. We conduct comprehensive experiments on iTIMO, revealing the limitations of current LLMs and lead to several valuable directions for future research. Dataset and corresponding code are available at https://github.com/zelo2/iTIMO.
Addressing itinerary modification is crucial for enhancing the travel experience as it is a frequent requirement during traveling. However, existing research mainly focuses on fixed itinerary planning, leaving modification underexplored. To bridge this gap, we formally define the itinerary modification task and introduce iTIMO, a dataset specifically tailored for this purpose. We identify the lack of {\itshape need-to-modify} itinerary data as the critical bottleneck hindering research on this task and propose a general pipeline to overcome it. This pipeline frames the generation of such data as an intent-driven perturbation task. It instructs large language models to perturb real world itineraries using three atomic editing operations: REPLACE, ADD, and DELETE. Each perturbation is grounded in three intents, including disruptions of popularity, spatial distance, and category diversity. Furthermore, a hybrid evaluation metric is designed to ensure perturbation effectiveness. We conduct comprehensive experiments on iTIMO, revealing the limitations of current LLMs and lead to several valuable directions for future research. Dataset and corresponding code are available at https://github.com/zelo2/iTIMO.
Why we are recommending this paper?
Due to your Interest in Travel Itinerary Creation
This paper directly addresses itinerary modification, a key interest for the user. The use of LLMs for this task aligns with the userβs interest in travel personalization and recommendations, offering a novel approach to enhancing travel experiences.
Due to your Interest in Travel Itinerary Creation
This paper directly addresses itinerary modification, a key interest for the user. The use of LLMs for this task aligns with the userβs interest in travel personalization and recommendations, offering a novel approach to enhancing travel experiences.
Fudan University
AI Insights
- On objective tasks, personalized information may not always improve model performance and can even lead to factual errors or logical biases. [3]
- On subjective personalized tasks, personalized information is crucial for improving model performance. [3]
- The type of personalized information used can significantly impact model performance. [3]
- Aligned personas tend to perform better than unaligned personas on both objective and subjective tasks. [3]
- To maximize the benefits of personalized information, it is essential to carefully design and implement the personaDual framework, taking into account the specific requirements and constraints of each application domain. [3]
- Personalized information can have a double-edged effect on the performance of large language models (LLMs). [2]
Abstract
As users increasingly expect LLMs to align with their preferences, personalized information becomes valuable. However, personalized information can be a double-edged sword: it can improve interaction but may compromise objectivity and factual correctness, especially when it is misaligned with the question. To alleviate this problem, we propose PersonaDual, a framework that supports both general-purpose objective reasoning and personalized reasoning in a single model, and adaptively switches modes based on context. PersonaDual is first trained with SFT to learn two reasoning patterns, and then further optimized via reinforcement learning with our proposed DualGRPO to improve mode selection. Experiments on objective and personalized benchmarks show that PersonaDual preserves the benefits of personalization while reducing interference, achieving near interference-free performance and better leveraging helpful personalized signals to improve objective problem-solving.
As users increasingly expect LLMs to align with their preferences, personalized information becomes valuable. However, personalized information can be a double-edged sword: it can improve interaction but may compromise objectivity and factual correctness, especially when it is misaligned with the question. To alleviate this problem, we propose PersonaDual, a framework that supports both general-purpose objective reasoning and personalized reasoning in a single model, and adaptively switches modes based on context. PersonaDual is first trained with SFT to learn two reasoning patterns, and then further optimized via reinforcement learning with our proposed DualGRPO to improve mode selection. Experiments on objective and personalized benchmarks show that PersonaDual preserves the benefits of personalization while reducing interference, achieving near interference-free performance and better leveraging helpful personalized signals to improve objective problem-solving.
Why we are recommending this paper?
Due to your Interest in Travel Personalization
Given the user's interest in personalization, this paper explores how LLMs can adapt to individual preferences. The focus on balancing personalization with objectivity is particularly relevant to the user's exploration of travel recommendations.
Due to your Interest in Travel Personalization
Given the user's interest in personalization, this paper explores how LLMs can adapt to individual preferences. The focus on balancing personalization with objectivity is particularly relevant to the user's exploration of travel recommendations.
Technical University of Munich
AI Insights
- Germany leads in both national and international collaborations, followed by China and the USA. [3]
- Countries like Canada, Austria, and the Netherlands have nearly half or more of their publications as MCPs (Multiple Country Publications), demonstrating strong international collaboration. [3]
- Co-authorship network: A visual representation of collaborations between authors, showing how they work together on research projects. [3]
- Multiple Country Publications (MCP): Papers that involve authors from different countries, indicating international collaboration. [3]
- Single Country Publications (SCP): Papers that only involve authors from the same country, indicating domestic research. [3]
- The co-authorship network of OSM research is global, with varying levels of collaboration and specialization across institutions and countries. [2]
Abstract
OpenStreetMap (OSM) has transitioned from a pioneering volunteered geographic information (VGI) project into a global, multi-disciplinary research nexus. This study presents a bibliometric and systematic analysis of the OSM research landscape, examining its development trajectory and key driving forces. By evaluating 1,926 publications from the Web of Science (WoS) Core Collection and 782 State of the Map (SotM) presentations up to June 2024, we quantify publication growth, collaboration patterns, and thematic evolution. Results demonstrate simultaneous consolidation and diversification within the field. While a stable core of contributors continues to anchor OSM research, themes have shifted from initial concerns over data production and quality toward advanced analytical and applied uses. Comparative analysis of OSM-related research in WoS and SotM reveals distinct but complementary agendas between scholars and the OSM community. Building on these findings, we identify six emerging research directions and discuss how evolving partnerships among academia, the OSM community, and industry are poised to shape the future of OSM research. This study establishes a structured reference for understanding the state of OSM studies and offers strategic pathways for navigating its future trajectory.The data and code are available at https://github.com/ya0-sun/OSMbib.
OpenStreetMap (OSM) has transitioned from a pioneering volunteered geographic information (VGI) project into a global, multi-disciplinary research nexus. This study presents a bibliometric and systematic analysis of the OSM research landscape, examining its development trajectory and key driving forces. By evaluating 1,926 publications from the Web of Science (WoS) Core Collection and 782 State of the Map (SotM) presentations up to June 2024, we quantify publication growth, collaboration patterns, and thematic evolution. Results demonstrate simultaneous consolidation and diversification within the field. While a stable core of contributors continues to anchor OSM research, themes have shifted from initial concerns over data production and quality toward advanced analytical and applied uses. Comparative analysis of OSM-related research in WoS and SotM reveals distinct but complementary agendas between scholars and the OSM community. Building on these findings, we identify six emerging research directions and discuss how evolving partnerships among academia, the OSM community, and industry are poised to shape the future of OSM research. This study establishes a structured reference for understanding the state of OSM studies and offers strategic pathways for navigating its future trajectory.The data and code are available at https://github.com/ya0-sun/OSMbib.
Why we are recommending this paper?
Due to your Interest in Travel Search
This paperβs focus on OpenStreetMap, a foundational resource for travel data, aligns strongly with the userβs interest in travel and travel recommendations. Analyzing the research landscape provides valuable context for understanding travel-related data sources.
Due to your Interest in Travel Search
This paperβs focus on OpenStreetMap, a foundational resource for travel data, aligns strongly with the userβs interest in travel and travel recommendations. Analyzing the research landscape provides valuable context for understanding travel-related data sources.
Allegro sp z oo
AI Insights
- CTR: Click-Through Rate Ranker: a model that predicts the ranking order of items based on their relevance to a user's query The proposed method, MLPlatt, demonstrates superior performance compared to other strong baseline approaches. [3]
- The paper does not provide a detailed comparison with other state-of-the-art methods. [3]
- The method's performance may degrade when dealing with large-scale datasets or complex ranking tasks. [3]
- The paper proposes a novel framework called MLPlatt for transforming uncalibrated ranker predictions into CTR probabilities while preserving the ranking order. [2]
Abstract
Ranking models are extensively used in e-commerce for relevance estimation. These models often suffer from poor interpretability and no scale calibration, particularly when trained with typical ranking loss functions. This paper addresses the problem of post-hoc calibration of ranking models. We introduce MLPlatt: a simple yet effective ranking model calibration method that preserves the item ordering and converts ranker outputs to interpretable click-through rate (CTR) probabilities usable in downstream tasks. The method is context-aware by design and achieves good calibration metrics globally, and within strata corresponding to different values of a selected categorical field (such as user country or device), which is often important from a business perspective of an E-commerce platform. We demonstrate the superiority of MLPlatt over existing approaches on two datasets, achieving an improvement of over 10\% in F-ECE (Field Expected Calibration Error) compared to other methods. Most importantly, we show that high-quality calibration can be achieved without compromising the ranking quality.
Ranking models are extensively used in e-commerce for relevance estimation. These models often suffer from poor interpretability and no scale calibration, particularly when trained with typical ranking loss functions. This paper addresses the problem of post-hoc calibration of ranking models. We introduce MLPlatt: a simple yet effective ranking model calibration method that preserves the item ordering and converts ranker outputs to interpretable click-through rate (CTR) probabilities usable in downstream tasks. The method is context-aware by design and achieves good calibration metrics globally, and within strata corresponding to different values of a selected categorical field (such as user country or device), which is often important from a business perspective of an E-commerce platform. We demonstrate the superiority of MLPlatt over existing approaches on two datasets, achieving an improvement of over 10\% in F-ECE (Field Expected Calibration Error) compared to other methods. Most importantly, we show that high-quality calibration can be achieved without compromising the ranking quality.
Why we are recommending this paper?
Due to your Interest in Travel Ranking
The paperβs exploration of ranking models, frequently used in travel search and recommendation systems, is directly relevant to the userβs interest in travel ranking and search. Understanding model calibration is crucial for effective travel planning.
Due to your Interest in Travel Ranking
The paperβs exploration of ranking models, frequently used in travel search and recommendation systems, is directly relevant to the userβs interest in travel ranking and search. Understanding model calibration is crucial for effective travel planning.
Clemson University
AI Insights
- The paper discusses the problem of finding a strict improvement via the framework of Theorem 3 for non-defective cases. [3]
- The authors conduct an exhaustive search and find no counterexamples in every non-defective case with r β€ 10, suggesting a positive answer to the question. [3]
- However, verifying this requires improvements in numerical techniques since the degree alone does not directly determine q in higher codimensions. [3]
- Non-defective case: A case where the secant variety Οr(V) is non-defective, meaning it has no singularities and its dimension equals the expected value. [3]
- Theorem 3: A framework for finding a strict improvement via the degree of the secant variety Οr(V). [3]
- The authors' exhaustive search suggests that every non-defective case admits a strict improvement via the framework of Theorem 3. [3]
- However, verifying this requires improvements in numerical techniques since the degree alone does not directly determine q in higher codimensions. [3]
- Improved bound: A bound that is stricter than the geometric bounds provided by Theorem 3. [2]
- The authors rely on numerical techniques, which may not be accurate or reliable in higher codimensions. [0]
Abstract
We systematically compute improved asymptotic rank bounds for tensors. Using numerical implicitization, we implement the geometric framework of Kaski and MichaΕek across all computationally feasible cases. By detecting the absence of low-degree vanishing polynomials on secant varieties, we obtain new asymptotic rank bounds that improve upon the generic border rank bounds. The results provide numerical data supporting Strassen's asymptotic rank conjecture and clarify the computational barriers posed by current numerical methods.
We systematically compute improved asymptotic rank bounds for tensors. Using numerical implicitization, we implement the geometric framework of Kaski and MichaΕek across all computationally feasible cases. By detecting the absence of low-degree vanishing polynomials on secant varieties, we obtain new asymptotic rank bounds that improve upon the generic border rank bounds. The results provide numerical data supporting Strassen's asymptotic rank conjecture and clarify the computational barriers posed by current numerical methods.
Why we are recommending this paper?
Due to your Interest in Travel Ranking
While more mathematically focused, this paper addresses fundamental ranking model properties. The insights gained could be valuable for improving the accuracy and efficiency of travel ranking algorithms, aligning with the userβs interest in travel ranking.
Due to your Interest in Travel Ranking
While more mathematically focused, this paper addresses fundamental ranking model properties. The insights gained could be valuable for improving the accuracy and efficiency of travel ranking algorithms, aligning with the userβs interest in travel ranking.
Universidad de Zaragoza
AI Insights
- The paper does not provide any new or original contributions to the field. [3]
- It only presents a review of existing work. [3]
- The paper discusses the use of heterogeneous multi-agent systems for various tasks such as exploration, inspection, and reconstruction. [2]
Abstract
Monitoring large, unknown, and complex environments with autonomous robots poses significant navigation challenges, where deploying teams of heterogeneous robots with complementary capabilities can substantially improve both mission performance and feasibility. However, effectively modeling how different robotic platforms interact with the environment requires rich, semantic scene understanding. Despite this, existing approaches often assume homogeneous robot teams or focus on discrete task compatibility rather than continuous routing. Consequently, scene understanding is not fully integrated into routing decisions, limiting their ability to adapt to the environment and to leverage each robot's strengths. In this paper, we propose an integrated semantic-aware framework for coordinating heterogeneous robots. Starting from a reconnaissance flight, we build a metric-semantic map using open-vocabulary vision models and use it to identify regions requiring closer inspection and capability-aware paths for each platform to reach them. These are then incorporated into a heterogeneous vehicle routing formulation that jointly assigns inspection tasks and computes robot trajectories. Experiments in simulation and in a real inspection mission with three robotic platforms demonstrate the effectiveness of our approach in planning safer and more efficient routes by explicitly accounting for each platform's navigation capabilities. We release our framework, CHORAL, as open source to support reproducibility and deployment of diverse robot teams.
Monitoring large, unknown, and complex environments with autonomous robots poses significant navigation challenges, where deploying teams of heterogeneous robots with complementary capabilities can substantially improve both mission performance and feasibility. However, effectively modeling how different robotic platforms interact with the environment requires rich, semantic scene understanding. Despite this, existing approaches often assume homogeneous robot teams or focus on discrete task compatibility rather than continuous routing. Consequently, scene understanding is not fully integrated into routing decisions, limiting their ability to adapt to the environment and to leverage each robot's strengths. In this paper, we propose an integrated semantic-aware framework for coordinating heterogeneous robots. Starting from a reconnaissance flight, we build a metric-semantic map using open-vocabulary vision models and use it to identify regions requiring closer inspection and capability-aware paths for each platform to reach them. These are then incorporated into a heterogeneous vehicle routing formulation that jointly assigns inspection tasks and computes robot trajectories. Experiments in simulation and in a real inspection mission with three robotic platforms demonstrate the effectiveness of our approach in planning safer and more efficient routes by explicitly accounting for each platform's navigation capabilities. We release our framework, CHORAL, as open source to support reproducibility and deployment of diverse robot teams.
Why we are recommending this paper?
Due to your Interest in Travel Planning
Due to your Interest in Travel Planning
Interests not found
We did not find any papers that match the below interests.
Try other terms also consider if the content exists in arxiv.org.
- Travel Industry
- Travel
- Travel Recommendations
You can edit or add more interests any time.
π¬ Help Shape Our Pricing
We're exploring pricing options to make this project sustainable. Take 3 minutes to share what you'd be willing to pay (if anything). Your input guides our future investment.
Help us improve your experience!
This project is on its early stages your feedback can be pivotal on the future of the project.
Let us know what you think about this week's papers and suggestions!
Give Feedback