Seoul National University
AI Insights
- Vision-Language Models (VLMs): A type of artificial intelligence model that combines natural language processing and computer vision capabilities. (ML: 0.97)
- The paper discusses the concept of contextualized visual personalization in vision-language models (VLMs), which involves tailoring the model's responses to a user's specific context and preferences. (ML: 0.97)
- MCQA Accuracy: The accuracy of a VLM's ability to answer multiple-choice questions accurately. (ML: 0.97)
- Contextualized Visual Personalization: The ability of a VLM to tailor its responses to a user's specific context and preferences. (ML: 0.96)
- The paper concludes by emphasizing the need for more research on contextualized visual personalization and the development of new evaluation metrics and benchmarks to assess VLMs' performance in this area. (ML: 0.96)
- The authors highlight the importance of addressing issues such as object hallucination, where the model generates objects that are not present in the input image, and entity name inclusion, where the model fails to include relevant entities in its response. (ML: 0.93)
- The authors propose a new benchmark for evaluating VLMs' ability to personalize their responses, which includes tasks such as object hallucination, entity name inclusion, and positive MCQA accuracy. (ML: 0.93)
- The paper also discusses various techniques for improving VLMs' personalization capabilities, including retrieval-augmented personalization, knowledge-augmented large language models, and multi-concept customization of text-to-image diffusion. (ML: 0.92)
- Entity Name Inclusion: When a VLM fails to include relevant entities in its response. (ML: 0.89)
- Object Hallucination: When a VLM generates objects that are not present in the input image. (ML: 0.83)
Abstract
Despite recent progress in vision-language models (VLMs), existing approaches often fail to generate personalized responses based on the user's specific experiences, as they lack the ability to associate visual inputs with a user's accumulated visual-textual context. We newly formalize this challenge as contextualized visual personalization, which requires the visual recognition and textual retrieval of personalized visual experiences by VLMs when interpreting new images. To address this issue, we propose CoViP, a unified framework that treats personalized image captioning as a core task for contextualized visual personalization and improves this capability through reinforcement-learning-based post-training and caption-augmented generation. We further introduce diagnostic evaluations that explicitly rule out textual shortcut solutions and verify whether VLMs truly leverage visual context. Extensive experiments demonstrate that existing open-source and proprietary VLMs exhibit substantial limitations, while CoViP not only improves personalized image captioning but also yields holistic gains across downstream personalization tasks. These results highlight CoViP as a crucial stage for enabling robust and generalizable contextualized visual personalization.
Despite recent progress in vision-language models (VLMs), existing approaches often fail to generate personalized responses based on the user's specific experiences, as they lack the ability to associate visual inputs with a user's accumulated visual-textual context. We newly formalize this challenge as contextualized visual personalization, which requires the visual recognition and textual retrieval of personalized visual experiences by VLMs when interpreting new images. To address this issue, we propose CoViP, a unified framework that treats personalized image captioning as a core task for contextualized visual personalization and improves this capability through reinforcement-learning-based post-training and caption-augmented generation. We further introduce diagnostic evaluations that explicitly rule out textual shortcut solutions and verify whether VLMs truly leverage visual context. Extensive experiments demonstrate that existing open-source and proprietary VLMs exhibit substantial limitations, while CoViP not only improves personalized image captioning but also yields holistic gains across downstream personalization tasks. These results highlight CoViP as a crucial stage for enabling robust and generalizable contextualized visual personalization.
Why we are recommending this paper?
Due to your Interest in Travel Personalization
This paper directly addresses personalization, a core interest for the user, by exploring how visual information can be tailored to individual experiences. The focus on vision-language models aligns with the user's interest in leveraging diverse data sources for recommendations.
Due to your Interest in Travel Personalization
This paper directly addresses personalization, a core interest for the user, by exploring how visual information can be tailored to individual experiences. The focus on vision-language models aligns with the user's interest in leveraging diverse data sources for recommendations.
Palo Alto Networks
AI Insights
- While the RL agent learns from engagement signals, incorporating cognitive load and user satisfaction as explicit reward components could further improve adaptation quality. (ML: 0.96)
- The current framework assumes stable user behavior distributions and relies on anonymized interaction data, which may not capture all contextual factors. (ML: 0.96)
- Predictive modeling: A technique used to forecast user behavior based on past interactions and contextual factors. (ML: 0.95)
- Results indicate that AI-driven personalization increases engagement metrics by up to 30% while reducing average interaction latency. (ML: 0.95)
- Reinforcement learning: An AI approach that enables systems to learn from rewards or penalties received after taking actions in an environment. (ML: 0.94)
- A key insight from this work is the synergistic relationship between sequence prediction and reward-based optimization, which balances immediacy and sustained engagement. (ML: 0.90)
- The proposed system integrates predictive modeling and reinforcement learning within a unified personalization loop to enhance front-end adaptability. (ML: 0.90)
- The study presents a concrete step toward practical, real-time AI-driven personalization in production-scale front-end systems. (ML: 0.86)
- Unified personalization loop: A framework that combines predictive modeling, reinforcement learning, and adaptive rendering to continuously improve UI adaptation. (ML: 0.86)
- By coupling prediction, optimization, and adaptive rendering within a single feedback architecture, it establishes a foundation for next-generation user interfaces that evolve intelligently alongside their users. (ML: 0.82)
Abstract
Front-end personalization has traditionally relied on static designs or rule-based adaptations, which fail to fully capture user behavior patterns. This paper presents an AI driven approach for dynamic front-end personalization, where UI layouts, content, and features adapt in real-time based on predicted user behavior. We propose three strategies: dynamic layout adaptation using user path prediction, content prioritization through reinforcement learning, and a comparative analysis of AI-driven vs. rule-based personalization. Technical implementation details, algorithms, system architecture, and evaluation methods are provided to illustrate feasibility and performance gains.
Front-end personalization has traditionally relied on static designs or rule-based adaptations, which fail to fully capture user behavior patterns. This paper presents an AI driven approach for dynamic front-end personalization, where UI layouts, content, and features adapt in real-time based on predicted user behavior. We propose three strategies: dynamic layout adaptation using user path prediction, content prioritization through reinforcement learning, and a comparative analysis of AI-driven vs. rule-based personalization. Technical implementation details, algorithms, system architecture, and evaluation methods are provided to illustrate feasibility and performance gains.
Why we are recommending this paper?
Due to your Interest in Travel Personalization
Given the user's interest in travel recommendations and personalization, this paper’s exploration of dynamic front-end adaptation is highly relevant. The AI-driven approach suggests a system capable of tailoring the user’s experience, a key aspect of their interests.
Due to your Interest in Travel Personalization
Given the user's interest in travel recommendations and personalization, this paper’s exploration of dynamic front-end adaptation is highly relevant. The AI-driven approach suggests a system capable of tailoring the user’s experience, a key aspect of their interests.
Eindhoven University of Technology
AI Insights
- Geosocial reachability queries: These are queries that ask for the set of nodes in a graph that are reachable from a given node within a certain spatial range. (ML: 0.90)
- Experiments on four real-world datasets show that 2DReach achieves faster index construction, smaller index size, and stable query performance compared to 3DReach. (ML: 0.89)
- Interval labelling: This is a technique used in 3DReach to label each node with an interval representing its reachable set, which can be expensive and complex. (ML: 0.88)
- Persistent R-trees: This is a technique that allows R-trees to be updated incrementally, which can improve performance and reduce storage requirements. (ML: 0.86)
- 2D R-trees: These are data structures used in 2DReach to index the nodes of a graph based on their spatial coordinates, allowing for efficient querying of reachability. (ML: 0.85)
- 2DReach offers significant improvements over 3DReach in terms of index construction time, index size, and query performance. (ML: 0.85)
- The paper introduces 2DReach, a simpler and faster alternative to the state-of-the-art 3DReach for geosocial reachability queries. (ML: 0.85)
- 2DReach eliminates interval labelling and replaces 3D R-trees with per-component 2D R-trees, simplifying index construction and query execution. (ML: 0.81)
- The compressed variants of 2DReach provide further reductions in storage requirements while maintaining stable query performance. (ML: 0.80)
- Compressed variants of 2DReach further reduce storage by excluding spatial sinks and sharing R-trees between components with identical reachable sets. (ML: 0.79)
Abstract
Geosocial reachability queries (\textsc{RangeReach}) determine whether a given vertex in a geosocial network can reach any spatial vertex within a query region. The state-of-the-art 3DReach method answers such queries by encoding graph reachability through interval labelling and indexing spatial vertices in a 3D R-tree. We present 2DReach, a simpler approach that avoids interval labelling entirely. Like 3DReach, 2DReach collapses strongly connected components (SCCs) into a DAG, but instead of computing interval labels, it directly stores a 2D R-tree per component over all reachable spatial vertices. A query then reduces to a single 2D R-tree lookup. We further propose compressed variants that reduce storage by excluding spatial sinks and sharing R-trees between components with identical reachable sets. Experiments on four real-world datasets show that 2DReach achieves faster index construction than 3DReach, with the compressed variant yielding the smallest index size among all methods. 2DReach delivers competitive or superior query performance with more stable response times across varying query parameters.
Geosocial reachability queries (\textsc{RangeReach}) determine whether a given vertex in a geosocial network can reach any spatial vertex within a query region. The state-of-the-art 3DReach method answers such queries by encoding graph reachability through interval labelling and indexing spatial vertices in a 3D R-tree. We present 2DReach, a simpler approach that avoids interval labelling entirely. Like 3DReach, 2DReach collapses strongly connected components (SCCs) into a DAG, but instead of computing interval labels, it directly stores a 2D R-tree per component over all reachable spatial vertices. A query then reduces to a single 2D R-tree lookup. We further propose compressed variants that reduce storage by excluding spatial sinks and sharing R-trees between components with identical reachable sets. Experiments on four real-world datasets show that 2DReach achieves faster index construction than 3DReach, with the compressed variant yielding the smallest index size among all methods. 2DReach delivers competitive or superior query performance with more stable response times across varying query parameters.
Why we are recommending this paper?
Due to your Interest in Travel Search
The focus on geospatial reachability aligns strongly with the user's interest in travel and travel search. Understanding location-based queries is fundamental to building effective travel recommendations and search capabilities.
Due to your Interest in Travel Search
The focus on geospatial reachability aligns strongly with the user's interest in travel and travel search. Understanding location-based queries is fundamental to building effective travel recommendations and search capabilities.
Northwestern University
AI Insights
- Gradual resolution of uncertainty: the process by which consumers gradually learn about the quality and prices of products over time. (ML: 0.98)
- Benchmark model: a model without hidden fees used for comparison purposes. (ML: 0.95)
- The paper concludes that gradual resolution of uncertainty leads to higher prices and lower consumer welfare, but regulation can mitigate these effects. (ML: 0.95)
- It also highlights the importance of considering the impact of regulatory policies on equilibrium prices and consumer welfare in markets with hidden fees. (ML: 0.94)
- It finds that gradual resolution of uncertainty leads to higher prices and lower consumer welfare compared to a benchmark model without hidden fees. (ML: 0.94)
- However, regulation that prohibits hidden fees can lead to lower prices and higher consumer welfare. (ML: 0.93)
- The paper studies the effect of gradual resolution of uncertainty on prices and consumer welfare in a monopolistic competition model with hidden fees. (ML: 0.91)
- Hidden fees: fees charged by firms to consumers that are not explicitly disclosed. (ML: 0.91)
- Monopolistic competition: a market structure where firms compete with each other but also have some degree of market power. (ML: 0.88)
- The paper also examines the effect of regulation on equilibrium prices in unregulated and regulated markets and finds that it increases consumer surplus. (ML: 0.83)
Abstract
I introduce and study a nested search problem modeled as a tree structure that generalizes Weitzman (1979) in two ways: (1) search progresses incrementally, reflecting real-life scenarios where agents gradually acquire information about the prizes; and (2) the realization of prizes can be correlated, capturing similarities among them. I derive the optimal policy, which takes the form of an index solution. I apply this result to study monopolistic competition in a market with two stages of product inspection. My application illustrates that regulations on drip pricing lower equilibrium price and raise consumer surplus.
I introduce and study a nested search problem modeled as a tree structure that generalizes Weitzman (1979) in two ways: (1) search progresses incrementally, reflecting real-life scenarios where agents gradually acquire information about the prizes; and (2) the realization of prizes can be correlated, capturing similarities among them. I derive the optimal policy, which takes the form of an index solution. I apply this result to study monopolistic competition in a market with two stages of product inspection. My application illustrates that regulations on drip pricing lower equilibrium price and raise consumer surplus.
Why we are recommending this paper?
Due to your Interest in Travel Search
This paper's exploration of incremental information acquisition, modeled as a tree structure, resonates with the user’s interest in travel planning. The concept of gradually refining search criteria mirrors the process of building a travel itinerary.
Due to your Interest in Travel Search
This paper's exploration of incremental information acquisition, modeled as a tree structure, resonates with the user’s interest in travel planning. The concept of gradually refining search criteria mirrors the process of building a travel itinerary.
Alibaba Group
AI Insights
- The authors use a large-scale dataset with 10 million users and 100 million routes to train and evaluate their model. (ML: 0.96)
- The results show that the proposed method outperforms state-of-the-art methods in terms of precision, recall, and F1-score. (ML: 0.93)
- The proposed method incorporates context-aware features, user history sequences, link static features, dynamic characteristics of the dual network, and route sets to make recommendations. (ML: 0.91)
- Context-aware feature (𝑥𝑠): A vector describing the currently requested scene information. (ML: 0.91)
- User history sequence (𝑥ℎ): A vector containing user selection strategy and route characteristics for the last 100 times. (ML: 0.90)
- The paper discusses a novel approach to personalized route recommendation using graph attention networks (GATs) and reinforcement learning. (ML: 0.89)
- Coverage (𝐶𝑜𝑣): A vector recording the coverage of each route compared to the user's actual route. (ML: 0.84)
- Route set (𝑅): A matrix with routes and their corresponding links. (ML: 0.73)
- Link static feature (𝑥𝑙𝑖𝑛𝑘): A matrix with static information about each link in the dual network. (ML: 0.72)
- Dynamic characteristics of dual network: Frequency features (𝑥𝑓𝑟𝑒𝑞) and OD heat data (𝑥ℎ𝑒𝑎𝑡). (ML: 0.60)
Abstract
Existing industrial-scale navigation applications contend with massive road networks, typically employing two main categories of approaches for route planning. The first relies on precomputed road costs for optimal routing and heuristic algorithms for generating alternatives, while the second, generative methods, has recently gained significant attention. However, the former struggles with personalization and route diversity, while the latter fails to meet the efficiency requirements of large-scale real-time scenarios. To address these limitations, we propose GenMRP, a generative framework for multi-route planning. To ensure generation efficiency, GenMRP first introduces a skeleton-to-capillary approach that dynamically constructs a relevant sub-network significantly smaller than the full road network. Within this sub-network, routes are generated iteratively. The first iteration identifies the optimal route, while the subsequent ones generate alternatives that balance quality and diversity using the newly proposed correctional boosting approach. Each iteration incorporates road features, user historical sequences, and previously generated routes into a Link Cost Model to update road costs, followed by route generation using the Dijkstra algorithm. Extensive experiments show that GenMRP achieves state-of-the-art performance with high efficiency in both offline and online environments. To facilitate further research, we have publicly released the training and evaluation dataset. GenMRP has been fully deployed in a real-world navigation app, demonstrating its effectiveness and benefits.
Existing industrial-scale navigation applications contend with massive road networks, typically employing two main categories of approaches for route planning. The first relies on precomputed road costs for optimal routing and heuristic algorithms for generating alternatives, while the second, generative methods, has recently gained significant attention. However, the former struggles with personalization and route diversity, while the latter fails to meet the efficiency requirements of large-scale real-time scenarios. To address these limitations, we propose GenMRP, a generative framework for multi-route planning. To ensure generation efficiency, GenMRP first introduces a skeleton-to-capillary approach that dynamically constructs a relevant sub-network significantly smaller than the full road network. Within this sub-network, routes are generated iteratively. The first iteration identifies the optimal route, while the subsequent ones generate alternatives that balance quality and diversity using the newly proposed correctional boosting approach. Each iteration incorporates road features, user historical sequences, and previously generated routes into a Link Cost Model to update road costs, followed by route generation using the Dijkstra algorithm. Extensive experiments show that GenMRP achieves state-of-the-art performance with high efficiency in both offline and online environments. To facilitate further research, we have publicly released the training and evaluation dataset. GenMRP has been fully deployed in a real-world navigation app, demonstrating its effectiveness and benefits.
Why we are recommending this paper?
Due to your Interest in Travel Planning
This paper’s focus on efficient and personalized route planning, particularly within an industrial context, aligns with the user’s interest in travel planning and optimization. The framework’s potential for real-time adaptation is a valuable asset for creating tailored travel experiences.
Due to your Interest in Travel Planning
This paper’s focus on efficient and personalized route planning, particularly within an industrial context, aligns with the user’s interest in travel planning and optimization. The framework’s potential for real-time adaptation is a valuable asset for creating tailored travel experiences.
University of Oxford
AI Insights
- They're looking at different ways to design systems that work for everyone, but they're also finding that it's really hard to balance fairness with efficiency. (ML: 0.98)
- The paper discusses the computational challenges of designing equitable public transportation systems. (ML: 0.95)
- The authors of this paper are trying to figure out how to make public transportation more fair and efficient. (ML: 0.93)
- It presents a bus stop model and a network transit problem, highlighting the trade-offs between fairness, efficiency, and complexity. (ML: 0.92)
- The paper does not provide a clear solution to the problems it identifies. (ML: 0.92)
Abstract
We study two stylized, multi-agent models aimed at investing a limited, indivisible resource in public transportation. In the first model, we face the decision of which potential stops to open along a (e.g., bus) path, given agents' travel demands. While it is known that utilitarian optimal solutions can be identified in polynomial time, we find that computing approximately optimal solutions with respect to egalitarian welfare is NP-complete. This is surprising as we operate on the simple topology of a line graph. In the second model, agents navigate a more complex network modeled by a weighted graph where edge weights represent distances. We face the decision of improving travel time along a fixed number of edges. We provide a polynomial-time algorithm that combines Dijkstra's algorithm with a dynamical program to find the optimal decision for one or two agents. By contrast, if the number of agents is variable, we find \np-completeness and inapproximability results for utilitarian and egalitarian welfare. Moreover, we demonstrate implications of our results for a related model of railway network design.
We study two stylized, multi-agent models aimed at investing a limited, indivisible resource in public transportation. In the first model, we face the decision of which potential stops to open along a (e.g., bus) path, given agents' travel demands. While it is known that utilitarian optimal solutions can be identified in polynomial time, we find that computing approximately optimal solutions with respect to egalitarian welfare is NP-complete. This is surprising as we operate on the simple topology of a line graph. In the second model, agents navigate a more complex network modeled by a weighted graph where edge weights represent distances. We face the decision of improving travel time along a fixed number of edges. We provide a polynomial-time algorithm that combines Dijkstra's algorithm with a dynamical program to find the optimal decision for one or two agents. By contrast, if the number of agents is variable, we find \np-completeness and inapproximability results for utilitarian and egalitarian welfare. Moreover, we demonstrate implications of our results for a related model of railway network design.
Why we are recommending this paper?
Due to your Interest in Travel Industry
Due to your Interest in Travel Industry
Leiden University
AI Insights
- It characterizes ranking behavior through three steerable directions – decision, evidence, and role – and shows that ranking performance can be effectively calibrated at inference time through simple projection-based interventions. (ML: 0.99)
- The method can be applied to other ranking paradigms and retrieval settings, making it a promising area of research. (ML: 0.96)
- Steerable directions: The three dimensions through which the activation steering is performed – decision, evidence, and role. (ML: 0.95)
- The method outperforms state-of-the-art pointwise LLM ranking methods on TREC-DL 2020 and the BEIR benchmarks with three backbone LLMs. (ML: 0.93)
- RankSteer is a post-hoc activation steering method for pointwise Large Language Model (LLM) rankers. (ML: 0.90)
- RankSteer preserves the inference complexity of standard pointwise ranking, making it a computationally efficient post-hoc calibration mechanism for pointwise LLM rankers. (ML: 0.90)
- Activation steering: A method that directly manipulates the activation geometry of an LLM to improve its performance on specific tasks. (ML: 0.90)
- RankSteer provides an efficient post-hoc calibration mechanism for pointwise LLM rankers, recovering under-utilized ranking capacity with far fewer labeled queries than fine-tuning. (ML: 0.89)
- The method requires a large amount of labeled data to train the anchor queries. (ML: 0.85)
- Pointwise LLM ranker: An LLM-based ranking system that generates a ranked list of documents based on their relevance to a given query. (ML: 0.83)
Abstract
Large language models (LLMs) have recently shown strong performance as zero-shot rankers, yet their effectiveness is highly sensitive to prompt formulation, particularly role-play instructions. Prior analyses suggest that role-related signals are encoded along activation channels that are largely separate from query-document representations, raising the possibility of steering ranking behavior directly at the activation level rather than through brittle prompt engineering. In this work, we propose RankSteer, a post-hoc activation steering framework for zero-shot pointwise LLM ranking. We characterize ranking behavior through three disentangled and steerable directions in representation space: a \textbf{decision direction} that maps hidden states to relevance scores, an \textbf{evidence direction} that captures relevance signals not directly exploited by the decision head, and a \textbf{role direction} that modulates model behavior without injecting relevance information. Using projection-based interventions at inference time, RankSteer jointly controls these directions to calibrate ranking behavior without modifying model weights or introducing explicit cross-document comparisons. Experiments on TREC DL 20 and multiple BEIR benchmarks show that RankSteer consistently improves ranking quality using only a small number of anchor queries, demonstrating that substantial ranking capacity remains under-utilized in pointwise LLM rankers. We further provide a geometric analysis revealing that steering improves ranking by stabilizing ranking geometry and reducing dispersion, offering new insight into how LLMs internally represent and calibrate relevance judgments.
Large language models (LLMs) have recently shown strong performance as zero-shot rankers, yet their effectiveness is highly sensitive to prompt formulation, particularly role-play instructions. Prior analyses suggest that role-related signals are encoded along activation channels that are largely separate from query-document representations, raising the possibility of steering ranking behavior directly at the activation level rather than through brittle prompt engineering. In this work, we propose RankSteer, a post-hoc activation steering framework for zero-shot pointwise LLM ranking. We characterize ranking behavior through three disentangled and steerable directions in representation space: a \textbf{decision direction} that maps hidden states to relevance scores, an \textbf{evidence direction} that captures relevance signals not directly exploited by the decision head, and a \textbf{role direction} that modulates model behavior without injecting relevance information. Using projection-based interventions at inference time, RankSteer jointly controls these directions to calibrate ranking behavior without modifying model weights or introducing explicit cross-document comparisons. Experiments on TREC DL 20 and multiple BEIR benchmarks show that RankSteer consistently improves ranking quality using only a small number of anchor queries, demonstrating that substantial ranking capacity remains under-utilized in pointwise LLM rankers. We further provide a geometric analysis revealing that steering improves ranking by stabilizing ranking geometry and reducing dispersion, offering new insight into how LLMs internally represent and calibrate relevance judgments.
Why we are recommending this paper?
Due to your Interest in Travel Ranking
Due to your Interest in Travel Ranking
Karlsruhe Institute of Technology
AI Insights
- Arithmetic encoding: This is a method for compressing binary data by representing it as a single number. (ML: 0.92)
- Compact representation: This refers to a data structure that uses less memory than the original data. (ML: 0.89)
- Rank/select queries: These are operations that count the number of 1s (or 0s) before a given position in a bit vector, or select the first 1 (or 0) after a given position. (ML: 0.86)
- The proposed method is compared with existing methods, including Spider, Sux, and Movi, in terms of memory usage and query performance. (ML: 0.85)
- Bit vectors: These are arrays of bits used to represent binary data. (ML: 0.84)
- The paper discusses the development of a new data structure for rank/select queries on bit vectors. (ML: 0.79)
- The proposed method is suitable for applications where memory usage is limited, such as in embedded systems or mobile devices. (ML: 0.72)
- The authors propose a compact representation of the data structure using a combination of bitwise operations and arithmetic encoding. (ML: 0.72)
- The results show that the new data structure achieves better memory efficiency and faster query times than the existing methods. (ML: 0.72)
- The new data structure achieves better memory efficiency and faster query times than existing methods. (ML: 0.72)
Abstract
Given a text, a query $\mathsf{rank}(q, c)$ counts the number of occurrences of character $c$ among the first $q$ characters of the text. Space-efficient methods to answer these rank queries form an important building block in many succinct data structures. For example, the FM-index is a widely used data structure that uses rank queries to locate all occurrences of a pattern in a text. In bioinformatics applications, the goal is usually to process a given input as fast as possible. Thus, data structures should have high throughput when used with many threads. Contributions. For the binary alphabet, we develop BiRank with 3.28% space overhead. It merges the central ideas of two recent papers: (1) we interleave (inline) offsets in each cache line of the underlying bit vector [Laws et al., 2024], reducing cache-misses, and (2) these offsets are to the middle of each block so that only half of them need popcounting [Gottlieb and Reinert, 2025]. In QuadRank (14.4% space overhead), we extend these techniques to the $σ=4$ (DNA) alphabet. Both data structures require only a single cache miss per query, making them highly suitable for high-throughput and memory-bound settings. To enable efficient batch-processing, we support prefetching the cache lines required to answer upcoming queries. Results. BiRank and QuadRank are around $1.5\times$ and $2\times$ faster than similar-overhead methods that do not use inlining. Prefetching gives an additional $2\times$ speedup, at which point the dual-channel DDR4 RAM bandwidth becomes a hard limit on the total throughput. With prefetching, both methods outperform all other methods apart from SPIDER [Laws et al., 2024] by $2\times$. When using QuadRank with prefetching in a toy count-only FM-index, QuadFm, this results in a smaller size and up to $4\times$ speedup over Genedex, a state-of-the-art batching FM-index implementation.
Given a text, a query $\mathsf{rank}(q, c)$ counts the number of occurrences of character $c$ among the first $q$ characters of the text. Space-efficient methods to answer these rank queries form an important building block in many succinct data structures. For example, the FM-index is a widely used data structure that uses rank queries to locate all occurrences of a pattern in a text. In bioinformatics applications, the goal is usually to process a given input as fast as possible. Thus, data structures should have high throughput when used with many threads. Contributions. For the binary alphabet, we develop BiRank with 3.28% space overhead. It merges the central ideas of two recent papers: (1) we interleave (inline) offsets in each cache line of the underlying bit vector [Laws et al., 2024], reducing cache-misses, and (2) these offsets are to the middle of each block so that only half of them need popcounting [Gottlieb and Reinert, 2025]. In QuadRank (14.4% space overhead), we extend these techniques to the $σ=4$ (DNA) alphabet. Both data structures require only a single cache miss per query, making them highly suitable for high-throughput and memory-bound settings. To enable efficient batch-processing, we support prefetching the cache lines required to answer upcoming queries. Results. BiRank and QuadRank are around $1.5\times$ and $2\times$ faster than similar-overhead methods that do not use inlining. Prefetching gives an additional $2\times$ speedup, at which point the dual-channel DDR4 RAM bandwidth becomes a hard limit on the total throughput. With prefetching, both methods outperform all other methods apart from SPIDER [Laws et al., 2024] by $2\times$. When using QuadRank with prefetching in a toy count-only FM-index, QuadFm, this results in a smaller size and up to $4\times$ speedup over Genedex, a state-of-the-art batching FM-index implementation.
Why we are recommending this paper?
Due to your Interest in Travel Ranking
Due to your Interest in Travel Ranking
North Carolina State University
AI Insights
- Gaussian process regression: A probabilistic approach to regression that models the relationship between input variables and output variables using a Gaussian distribution. (ML: 0.98)
- Posterior variance: The variance of the predicted values in a Bayesian model, which represents the uncertainty in the predictions. (ML: 0.91)
- The algorithms are designed to work with Gaussian process regression models, where they use a probabilistic approach to estimate the posterior variance at evaluation points. (ML: 0.88)
- The algorithms use a binary coverage map construction method, where they evaluate whether a single candidate sensing location can reduce the posterior variance at an evaluation point below a target threshold. (ML: 0.86)
- The paper also discusses related work in the field of informative path planning, including previous approaches and their limitations. (ML: 0.84)
- Informative path planning: The problem of finding an optimal path for a robot or sensor to collect information about its environment. (ML: 0.84)
- The paper presents two new algorithms for informative path planning that are designed to efficiently reduce the posterior variance at evaluation points. (ML: 0.81)
- The paper provides theoretical support for these approaches, including Theorem 1, which gives an explicit covariance threshold for the single-location condition, and Theorem 2, which shows that this condition is conservative but safe. (ML: 0.79)
- Prior covariance: The covariance matrix of the prior distribution in a Gaussian process regression model, which represents the uncertainty in the parameters before observing any data. (ML: 0.77)
- The paper presents two new algorithms for informative path planning, GREEDYCOVER and GCBCOVER, which are designed to efficiently reduce the posterior variance at evaluation points. (ML: 0.77)
Abstract
Environmental monitoring robots often need to reconstruct spatial fields (e.g., salinity, temperature, bathymetry) under tight distance and energy constraints. Classical boustrophedon lawnmower surveys provide geometric coverage guarantees but can waste effort by oversampling predictable regions. In contrast, informative path planning (IPP) methods leverage spatial correlations to reduce oversampling, yet typically offer no guarantees on reconstruction quality. This paper bridges these approaches by addressing informative path planning with guaranteed estimation uncertainty: computing the shortest path whose measurements ensure that the Gaussian-process (GP) posterior variance -- an intrinsic uncertainty measure that lower-bounds the mean-squared prediction error under the GP model -- falls below a user-specified threshold over the monitoring region. We propose a three-stage approach: (i) learn a GP model from available prior information; (ii) transform the learned GP kernel into binary coverage maps for each candidate sensing location, indicating which locations' uncertainty can be reduced below a specified target; and (iii) plan a near-shortest route whose combined coverage satisfies the global uncertainty constraint. To address heterogeneous phenomena, we incorporate a nonstationary kernel that captures spatially varying correlation structure, and we accommodate non-convex environments with obstacles. Algorithmically, we present methods with provable approximation guarantees for sensing-location selection and for the joint selection-and-routing problem under a travel budget. Experiments on real-world topographic data show that our planners meet the uncertainty target using fewer sensing locations and shorter travel distances than a recent baseline, and field experiments with bathymetry-mapping autonomous surface and underwater vehicles demonstrate real-world feasibility.
Environmental monitoring robots often need to reconstruct spatial fields (e.g., salinity, temperature, bathymetry) under tight distance and energy constraints. Classical boustrophedon lawnmower surveys provide geometric coverage guarantees but can waste effort by oversampling predictable regions. In contrast, informative path planning (IPP) methods leverage spatial correlations to reduce oversampling, yet typically offer no guarantees on reconstruction quality. This paper bridges these approaches by addressing informative path planning with guaranteed estimation uncertainty: computing the shortest path whose measurements ensure that the Gaussian-process (GP) posterior variance -- an intrinsic uncertainty measure that lower-bounds the mean-squared prediction error under the GP model -- falls below a user-specified threshold over the monitoring region. We propose a three-stage approach: (i) learn a GP model from available prior information; (ii) transform the learned GP kernel into binary coverage maps for each candidate sensing location, indicating which locations' uncertainty can be reduced below a specified target; and (iii) plan a near-shortest route whose combined coverage satisfies the global uncertainty constraint. To address heterogeneous phenomena, we incorporate a nonstationary kernel that captures spatially varying correlation structure, and we accommodate non-convex environments with obstacles. Algorithmically, we present methods with provable approximation guarantees for sensing-location selection and for the joint selection-and-routing problem under a travel budget. Experiments on real-world topographic data show that our planners meet the uncertainty target using fewer sensing locations and shorter travel distances than a recent baseline, and field experiments with bathymetry-mapping autonomous surface and underwater vehicles demonstrate real-world feasibility.
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 Itinerary Creation
- Travel
- Travel Recommendations
You can edit or add more interests any time.
💬 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