🎯 Top Personalized Recommendations
Hanyang University
AI Summary
- The use of large-scale knowledge graphs and subgraph-aware training has been explored as a means to improve the performance of RLMs on knowledge graph completion tasks. [3]
- Knowledge Graph Completion: The task of predicting missing links between entities in a knowledge graph based on their attributes and relationships. [3]
- Retrieval-Augmented Language Models (RLMs) have shown significant improvements over traditional language models in various natural language processing tasks. [2]
- Efficient and effective passage search has been achieved through contextualized late interaction over BERT (Colbert) and condensed retrieval (Baleen). [1]
Abstract
Since large language models (LLMs) have a tendency to generate factually inaccurate output, retrieval-augmented generation (RAG) has gained significant attention as a key means to mitigate this downside of harnessing only LLMs. However, existing RAG methods for simple and multi-hop question answering (QA) are still prone to incorrect retrievals and hallucinations. To address these limitations, we propose CoopRAG, a novel RAG framework for the question answering task in which a retriever and an LLM work cooperatively with each other by exchanging informative knowledge, and the earlier and later layers of the retriever model work cooperatively with each other to accurately rank the retrieved documents relevant to a given query. In this framework, we (i) unroll a question into sub-questions and a reasoning chain in which uncertain positions are masked, (ii) retrieve the documents relevant to the question augmented with the sub-questions and the reasoning chain, (iii) rerank the documents by contrasting layers of the retriever, and (iv) reconstruct the reasoning chain by filling the masked positions via the LLM. Our experiments demonstrate that CoopRAG consistently outperforms state-of-the-art QA methods on three multi-hop QA datasets as well as a simple QA dataset in terms of both the retrieval and QA performances. Our code is available.\footnote{https://github.com/meaningful96/CoopRAG}
Since large language models (LLMs) have a tendency to generate factually inaccurate output, retrieval-augmented generation (RAG) has gained significant attention as a key means to mitigate this downside of harnessing only LLMs. However, existing RAG methods for simple and multi-hop question answering (QA) are still prone to incorrect retrievals and hallucinations. To address these limitations, we propose CoopRAG, a novel RAG framework for the question answering task in which a retriever and an LLM work cooperatively with each other by exchanging informative knowledge, and the earlier and later layers of the retriever model work cooperatively with each other to accurately rank the retrieved documents relevant to a given query. In this framework, we (i) unroll a question into sub-questions and a reasoning chain in which uncertain positions are masked, (ii) retrieve the documents relevant to the question augmented with the sub-questions and the reasoning chain, (iii) rerank the documents by contrasting layers of the retriever, and (iv) reconstruct the reasoning chain by filling the masked positions via the LLM. Our experiments demonstrate that CoopRAG consistently outperforms state-of-the-art QA methods on three multi-hop QA datasets as well as a simple QA dataset in terms of both the retrieval and QA performances. Our code is available.\footnote{https://github.com/meaningful96/CoopRAG}
Why we think this paper is great for you:
This paper directly addresses question answering, a core interest within information retrieval. The use of RAG and ranking aligns with your interest in improving search and personalization techniques.
This paper directly addresses question answering, a core interest within information retrieval. The use of RAG and ranking aligns with your interest in improving search and personalization techniques.
Snap Inc
AI Summary
- Diffusion models: a type of generative model that learns to transform a noise signal into a data distribution. [3]
- Requires large amounts of data and computational resources. [3]
- It also mentions the work of Jason Wei et al. [3]
- The paper discusses the use of diffusion models for image synthesis and text-to-image translation. [2]
- (2022) on chain-of-thought prompting elicits reasoning in large language models. [1]
Abstract
Visual concept personalization aims to transfer only specific image attributes, such as identity, expression, lighting, and style, into unseen contexts. However, existing methods rely on holistic embeddings from general-purpose image encoders, which entangle multiple visual factors and make it difficult to isolate a single attribute. This often leads to information leakage and incoherent synthesis. To address this limitation, we introduce Omni-Attribute, the first open-vocabulary image attribute encoder designed to learn high-fidelity, attribute-specific representations. Our approach jointly designs the data and model: (i) we curate semantically linked image pairs annotated with positive and negative attributes to explicitly teach the encoder what to preserve or suppress; and (ii) we adopt a dual-objective training paradigm that balances generative fidelity with contrastive disentanglement. The resulting embeddings prove effective for open-vocabulary attribute retrieval, personalization, and compositional generation, achieving state-of-the-art performance across multiple benchmarks.
Visual concept personalization aims to transfer only specific image attributes, such as identity, expression, lighting, and style, into unseen contexts. However, existing methods rely on holistic embeddings from general-purpose image encoders, which entangle multiple visual factors and make it difficult to isolate a single attribute. This often leads to information leakage and incoherent synthesis. To address this limitation, we introduce Omni-Attribute, the first open-vocabulary image attribute encoder designed to learn high-fidelity, attribute-specific representations. Our approach jointly designs the data and model: (i) we curate semantically linked image pairs annotated with positive and negative attributes to explicitly teach the encoder what to preserve or suppress; and (ii) we adopt a dual-objective training paradigm that balances generative fidelity with contrastive disentanglement. The resulting embeddings prove effective for open-vocabulary attribute retrieval, personalization, and compositional generation, achieving state-of-the-art performance across multiple benchmarks.
Why we think this paper is great for you:
Given your interest in personalization, this paper's focus on visual concept personalization using attribute encoders is highly relevant. It explores techniques for tailoring visual representations to specific user needs.
Given your interest in personalization, this paper's focus on visual concept personalization using attribute encoders is highly relevant. It explores techniques for tailoring visual representations to specific user needs.
Hanyang University
AI Summary
- The use of large-scale knowledge graphs and subgraph-aware training has been explored as a means to improve the performance of RLMs on knowledge graph completion tasks. [3]
- Knowledge Graph Completion: The task of predicting missing links between entities in a knowledge graph based on their attributes and relationships. [3]
- Retrieval-Augmented Language Models (RLMs) have shown significant improvements over traditional language models in various natural language processing tasks. [2]
- Efficient and effective passage search has been achieved through contextualized late interaction over BERT (Colbert) and condensed retrieval (Baleen). [1]
Abstract
Since large language models (LLMs) have a tendency to generate factually inaccurate output, retrieval-augmented generation (RAG) has gained significant attention as a key means to mitigate this downside of harnessing only LLMs. However, existing RAG methods for simple and multi-hop question answering (QA) are still prone to incorrect retrievals and hallucinations. To address these limitations, we propose CoopRAG, a novel RAG framework for the question answering task in which a retriever and an LLM work cooperatively with each other by exchanging informative knowledge, and the earlier and later layers of the retriever model work cooperatively with each other to accurately rank the retrieved documents relevant to a given query. In this framework, we (i) unroll a question into sub-questions and a reasoning chain in which uncertain positions are masked, (ii) retrieve the documents relevant to the question augmented with the sub-questions and the reasoning chain, (iii) rerank the documents by contrasting layers of the retriever, and (iv) reconstruct the reasoning chain by filling the masked positions via the LLM. Our experiments demonstrate that CoopRAG consistently outperforms state-of-the-art QA methods on three multi-hop QA datasets as well as a simple QA dataset in terms of both the retrieval and QA performances. Our code is available.\footnote{https://github.com/meaningful96/CoopRAG}
Since large language models (LLMs) have a tendency to generate factually inaccurate output, retrieval-augmented generation (RAG) has gained significant attention as a key means to mitigate this downside of harnessing only LLMs. However, existing RAG methods for simple and multi-hop question answering (QA) are still prone to incorrect retrievals and hallucinations. To address these limitations, we propose CoopRAG, a novel RAG framework for the question answering task in which a retriever and an LLM work cooperatively with each other by exchanging informative knowledge, and the earlier and later layers of the retriever model work cooperatively with each other to accurately rank the retrieved documents relevant to a given query. In this framework, we (i) unroll a question into sub-questions and a reasoning chain in which uncertain positions are masked, (ii) retrieve the documents relevant to the question augmented with the sub-questions and the reasoning chain, (iii) rerank the documents by contrasting layers of the retriever, and (iv) reconstruct the reasoning chain by filling the masked positions via the LLM. Our experiments demonstrate that CoopRAG consistently outperforms state-of-the-art QA methods on three multi-hop QA datasets as well as a simple QA dataset in terms of both the retrieval and QA performances. Our code is available.\footnote{https://github.com/meaningful96/CoopRAG}
Why we think this paper is great for you:
The paper's investigation into RAG and ranking aligns with your interest in improving search and retrieval systems. It tackles the challenge of generating accurate and relevant information.
The paper's investigation into RAG and ranking aligns with your interest in improving search and retrieval systems. It tackles the challenge of generating accurate and relevant information.
National University of
AI Summary
- The study also explores the impact of different input features on the performance of the models and finds that using both air quality index and weather data improves the predictive power of the models. [3]
- AQI: Air Quality Index MAE: Mean Absolute Error The study demonstrates the effectiveness of machine learning models in predicting AQIs and highlights the importance of using both air quality index and weather data for improved predictive power. [3]
- The results of this study can be used to inform policy decisions related to air pollution control and mitigation strategies. [3]
- The study only evaluates the performance of different models on a single dataset and does not explore the generalizability of the results to other locations or datasets. [3]
- The authors do not provide any discussion on the limitations of the study, such as the potential impact of data quality issues or the lack of consideration for non-linear relationships between input features. [3]
- The paper presents a comparative study of various machine learning models for predicting air quality indices (AQIs) in Beijing, China. [2]
- The results show that the Prophet model outperforms other models in terms of accuracy, with a mean absolute error (MAE) of 4.35 μg/m³. [1]
Abstract
Accurate forecasting of urban air pollution is essential for protecting public health and guiding mitigation policies. While Deep Learning (DL) and hybrid pipelines dominate recent research, their complexity and limited interpretability hinder operational use. This study investigates whether lightweight additive models -- Facebook Prophet (FBP) and NeuralProphet (NP) -- can deliver competitive forecasts for particulate matter (PM$_{2.5}$, PM$_{10}$) in Beijing, China. Using multi-year pollutant and meteorological data, we applied systematic feature selection (correlation, mutual information, mRMR), leakage-safe scaling, and chronological data splits. Both models were trained with pollutant and precursor regressors, with NP additionally leveraging lagged dependencies. For context, two machine learning baselines (LSTM, LightGBM) and one traditional statistical model (SARIMAX) were also implemented. Performance was evaluated on a 7-day holdout using MAE, RMSE, and $R^2$. Results show that FBP consistently outperformed NP, SARIMAX, and the learning-based baselines, achieving test $R^2$ above 0.94 for both pollutants. These findings demonstrate that interpretable additive models remain competitive with both traditional and complex approaches, offering a practical balance of accuracy, transparency, and ease of deployment.
Accurate forecasting of urban air pollution is essential for protecting public health and guiding mitigation policies. While Deep Learning (DL) and hybrid pipelines dominate recent research, their complexity and limited interpretability hinder operational use. This study investigates whether lightweight additive models -- Facebook Prophet (FBP) and NeuralProphet (NP) -- can deliver competitive forecasts for particulate matter (PM$_{2.5}$, PM$_{10}$) in Beijing, China. Using multi-year pollutant and meteorological data, we applied systematic feature selection (correlation, mutual information, mRMR), leakage-safe scaling, and chronological data splits. Both models were trained with pollutant and precursor regressors, with NP additionally leveraging lagged dependencies. For context, two machine learning baselines (LSTM, LightGBM) and one traditional statistical model (SARIMAX) were also implemented. Performance was evaluated on a 7-day holdout using MAE, RMSE, and $R^2$. Results show that FBP consistently outperformed NP, SARIMAX, and the learning-based baselines, achieving test $R^2$ above 0.94 for both pollutants. These findings demonstrate that interpretable additive models remain competitive with both traditional and complex approaches, offering a practical balance of accuracy, transparency, and ease of deployment.
Why we think this paper is great for you:
With your interest in information retrieval, this paper's focus on forecasting, particularly in the context of air quality, is a good fit. Accurate forecasting is a key component of effective information systems.
With your interest in information retrieval, this paper's focus on forecasting, particularly in the context of air quality, is a good fit. Accurate forecasting is a key component of effective information systems.
University of WisconsinM
AI Summary
- This is used to decompose technological change into two orthogonal components: a gradient component corresponding to earnings changes, and a divergence-free component corresponding to reallocation. [3]
- The objective minimizes the sum of squared differences between technological change and a gradient. [3]
- Rather than fitting a line (as in the case of linear regression), or any other particular function (as in the case of nonlinear regression), the function is restricted to be a gradient. [3]
- The complementarity matrix captures the degree of substitutability between different skills, which affects the reallocation of workers in response to technological change. [3]
- The results have important implications for understanding the impact of technological change on labor markets. [3]
- They provide a framework for analyzing how different skills are affected by technological progress and how workers are reallocated in response. [3]
- Helmholtz decomposition: A mathematical technique used to decompose a vector field into two orthogonal components: a gradient component and a divergence-free component. [3]
- Gradient regression: A type of regression analysis where the goal is to find the best-fitting linear combination of gradients that explain the data. [3]
- Once worker earnings are solved for, reallocation follows residually. [2]
- The Poisson equation gives a direct way to characterize earnings changes. [1]
- The Helmholtz decomposition states that any vector field can be written as the sum of a gradient component and divergence-free component. [0]
Abstract
In sorting literature, comparative statics for multidimensional assignment models with general output functions and input distributions is an important open question. We provide a complete theory of comparative statics for technological change in general multidimensional assignment models. Our main result is that any technological change is uniquely decomposed into two distinct components. The first component (gradient) gives a characterization of changes in marginal earnings through a Poisson equation. The second component (divergence-free) gives a characterization of labor reallocation. For U.S. data, we quantify equilibrium responses in sorting and earnings with respect to cognitive skill-biased technological change.
In sorting literature, comparative statics for multidimensional assignment models with general output functions and input distributions is an important open question. We provide a complete theory of comparative statics for technological change in general multidimensional assignment models. Our main result is that any technological change is uniquely decomposed into two distinct components. The first component (gradient) gives a characterization of changes in marginal earnings through a Poisson equation. The second component (divergence-free) gives a characterization of labor reallocation. For U.S. data, we quantify equilibrium responses in sorting and earnings with respect to cognitive skill-biased technological change.
Why we think this paper is great for you:
This paper's exploration of comparative statics in multidimensional sorting aligns with your interest in ranking and optimization techniques. It addresses a fundamental problem in data analysis.
This paper's exploration of comparative statics in multidimensional sorting aligns with your interest in ranking and optimization techniques. It addresses a fundamental problem in data analysis.
Stanford
AI Summary
- Welfare (WN): The expected total utility of the population at a given restaurant choice probability ρ and population size N. [3]
- The problem involves finding the maximum welfare for a given population size N and restaurant choice probability ρ. [2]
- Stopping time (n∗): The first time the process stops. [1]
Abstract
If agents engage in motivated reasoning, how does that affect the aggregation of information in society? We study the effects of motivated reasoning in two canonical settings - the Condorcet jury theorem (CJT), and the sequential social learning model (SLM). We define a notion of motivated reasoning that applies to these and a broader class of other settings, and contrast it to other approaches in the literature. We show for the CJT that information aggregates in the large electorate limit even with motivated reasoning. When signal quality differs across states, increasing motivation improves welfare in the state with the more informative signal and worsens it in the other state. In the SLM, motivated reasoning improves information aggregation up to a point; but if agents place too little weight on truth-seeking, this can lead to worse aggregation relative to the fully Bayesian benchmark.
If agents engage in motivated reasoning, how does that affect the aggregation of information in society? We study the effects of motivated reasoning in two canonical settings - the Condorcet jury theorem (CJT), and the sequential social learning model (SLM). We define a notion of motivated reasoning that applies to these and a broader class of other settings, and contrast it to other approaches in the literature. We show for the CJT that information aggregates in the large electorate limit even with motivated reasoning. When signal quality differs across states, increasing motivation improves welfare in the state with the more informative signal and worsens it in the other state. In the SLM, motivated reasoning improves information aggregation up to a point; but if agents place too little weight on truth-seeking, this can lead to worse aggregation relative to the fully Bayesian benchmark.
Why we think this paper is great for you:
Given your interest in information retrieval, this paper's investigation into how agents aggregate information, including potential biases, is a valuable area of study.
Given your interest in information retrieval, this paper's investigation into how agents aggregate information, including potential biases, is a valuable area of study.
Tsinghua University
Abstract
The Azadkia-Chatterjee coefficient is a rank-based measure of dependence between a random variable $Y \in \mathbb{R}$ and a random vector ${\boldsymbol Z} \in \mathbb{R}^{d_Z}$. This paper proposes a multivariate extension that measures dependence between random vectors ${\boldsymbol Y} \in \mathbb{R}^{d_Y}$ and ${\boldsymbol Z} \in \mathbb{R}^{d_Z}$, based on $n$ i.i.d. samples. The proposed coefficient converges almost surely to a limit with the following properties: i) it lies in $[0, 1]$; ii) it equals zero if and only if ${\boldsymbol Y}$ and ${\boldsymbol Z}$ are independent; and iii) it equals one if and only if ${\boldsymbol Y}$ is almost surely a function of ${\boldsymbol Z}$. Remarkably, the only assumption required by this convergence is that ${\boldsymbol Y}$ is not almost surely a constant. We further prove that under the same mild condition, the coefficient is asymptotically normal when ${\boldsymbol Y}$ and ${\boldsymbol Z}$ are independent and propose a merge sort based algorithm to calculate this coefficient in time complexity $O(n (\log n)^{d_Y})$. Finally, we show that it can be used to measure conditional dependence between ${\boldsymbol Y}$ and ${\boldsymbol Z}$ conditional on a third random vector ${\boldsymbol X}$, and prove that the measure is monotonic with respect to the deviation from an independence distribution under certain model restrictions.
The Azadkia-Chatterjee coefficient is a rank-based measure of dependence between a random variable $Y \in \mathbb{R}$ and a random vector ${\boldsymbol Z} \in \mathbb{R}^{d_Z}$. This paper proposes a multivariate extension that measures dependence between random vectors ${\boldsymbol Y} \in \mathbb{R}^{d_Y}$ and ${\boldsymbol Z} \in \mathbb{R}^{d_Z}$, based on $n$ i.i.d. samples. The proposed coefficient converges almost surely to a limit with the following properties: i) it lies in $[0, 1]$; ii) it equals zero if and only if ${\boldsymbol Y}$ and ${\boldsymbol Z}$ are independent; and iii) it equals one if and only if ${\boldsymbol Y}$ is almost surely a function of ${\boldsymbol Z}$. Remarkably, the only assumption required by this convergence is that ${\boldsymbol Y}$ is not almost surely a constant. We further prove that under the same mild condition, the coefficient is asymptotically normal when ${\boldsymbol Y}$ and ${\boldsymbol Z}$ are independent and propose a merge sort based algorithm to calculate this coefficient in time complexity $O(n (\log n)^{d_Y})$. Finally, we show that it can be used to measure conditional dependence between ${\boldsymbol Y}$ and ${\boldsymbol Z}$ conditional on a third random vector ${\boldsymbol X}$, and prove that the measure is monotonic with respect to the deviation from an independence distribution under certain model restrictions.
Why we think this paper is great for you:
This paper's focus on multivariate dependence measures and ranking aligns with your interest in information retrieval and ranking algorithms.
This paper's focus on multivariate dependence measures and ranking aligns with your interest in information retrieval and ranking algorithms.
Deep Learning
Universidad de Guanajuato
Abstract
This document reports the sequence of practices and methodologies implemented during the Big Data course. It details the workflow beginning with the processing of the Epsilon dataset through group and individual strategies, followed by text analysis and classification with RestMex and movie feature analysis with IMDb. Finally, it describes the technical implementation of a distributed computing cluster with Apache Spark on Linux using Scala.
This document reports the sequence of practices and methodologies implemented during the Big Data course. It details the workflow beginning with the processing of the Epsilon dataset through group and individual strategies, followed by text analysis and classification with RestMex and movie feature analysis with IMDb. Finally, it describes the technical implementation of a distributed computing cluster with Apache Spark on Linux using Scala.
AI Summary
- In the big data era, data completeness can be as important as algorithm sophistication. [3]
- Big Data Analytics Distributed Computing Scalability Algorithm Sophistication Data Completeness The chronological progression demonstrates that mastering big data requires a systematic approach. [3]
- The choice between local and distributed architectures is not merely about computational resources, but about the quality and completeness of the data available to the model. [2]
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.
- Search
You can edit or add more interests any time.
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