Search Results for author:
Found 95 papers, 18 papers with code
Towards Agentic Recommender Systems in the Era of Multimodal Large Language Models
Recent breakthroughs in Large Language Models (LLMs) have led to the emergence of agentic AI systems that extend beyond the capabilities of standalone models.
Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Bases
In the Planning stage, MoR generates textual planning graphs delineating the logic for answering queries.
Towards Optimal Multi-draft Speculative Decoding
For a fixed draft sampling method, the optimal acceptance rate is a solution to an optimal transport problem, but the complexity of this problem makes it difficult to solve for the optimal acceptance rate and measure the gap between existing verification algorithms and the theoretical upper bound.
A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models
The rise of foundation models has transformed machine learning research, prompting efforts to uncover their inner workings and develop more efficient and reliable applications for better control.
From Selection to Generation: A Survey of LLM-based Active Learning
Active Learning (AL) has been a powerful paradigm for improving model efficiency and performance by selecting the most informative data points for labeling and training.
Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent
By explicitly disentangling the optimization of visual understanding from task-specific alignment, MDGD preserves pre-trained visual knowledge while enabling efficient task adaptation.
NoLiMa: Long-Context Evaluation Beyond Literal Matching
A popular method for evaluating these capabilities is the needle-in-a-haystack (NIAH) test, which involves retrieving a "needle" (relevant information) from a "haystack" (long irrelevant context).
Interactive Visualization Recommendation with Hier-SUCB
For more interactive and accurate recommendations, we propose Hier-SUCB, a contextual combinatorial semi-bandit in the PVisRec setting.
Understanding How Paper Writers Use AI-Generated Captions in Figure Caption Writing
By analyzing video recordings of the writing process through interaction analysis, we observed that participants often began by copying and refining AI-generated captions.
Personalized Graph-Based Retrieval for Large Language Models
As large language models (LLMs) evolve, their ability to deliver personalized and context-aware responses offers transformative potential for improving user experiences.
LUSIFER: Language Universal Space Integration for Enhanced Multilingual Embeddings with Large Language Models
Extensive experimental results demonstrate that LUSIFER significantly enhances the multilingual performance across various embedding tasks, particularly for medium and low-resource languages, without requiring explicit multilingual training data.
Retrieval-Augmented Generation with Graphs (GraphRAG)
However, unlike conventional RAG, where the retriever, generator, and external data sources can be uniformly designed in the neural-embedding space, the uniqueness of graph-structured data, such as diverse-formatted and domain-specific relational knowledge, poses unique and significant challenges when designing GraphRAG for different domains.
Multi-LLM Text Summarization
However, during evaluation, our multi-LLM centralized summarization approach leverages a single LLM to evaluate the summaries and select the best one whereas k LLMs are used for decentralized multi-LLM summarization.
GUI Agents: A Survey
Graphical User Interface (GUI) agents, powered by Large Foundation Models, have emerged as a transformative approach to automating human-computer interaction.
Numerical Pruning for Efficient Autoregressive Models
Transformers have emerged as the leading architecture in deep learning, proving to be versatile and highly effective across diverse domains beyond language and image processing.
VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation
Understanding information from a collection of multiple documents, particularly those with visually rich elements, is important for document-grounded question answering.
Personalized Multimodal Large Language Models: A Survey
We propose an intuitive taxonomy for categorizing the techniques used to personalize MLLMs to individual users, and discuss the techniques accordingly.
DynaSaur: Large Language Agents Beyond Predefined Actions
Existing LLM agent systems typically select actions from a fixed and predefined set at every step.
LoRA-Contextualizing Adaptation of Large Multimodal Models for Long Document Understanding
In this work, we present a novel framework named LoRA-Contextualizing Adaptation of Large multimodal models (LoCAL), which broadens the capabilities of any LMM to support long-document understanding.
GRS-QA -- Graph Reasoning-Structured Question Answering Dataset
Large Language Models (LLMs) have excelled in multi-hop question-answering (M-QA) due to their advanced reasoning abilities.
Personalization of Large Language Models: A Survey
Personalization of Large Language Models (LLMs) has recently become increasingly important with a wide range of applications.
Survey of User Interface Design and Interaction Techniques in Generative AI Applications
The applications of generative AI have become extremely impressive, and the interplay between users and AI is even more so.
A Survey of Small Language Models
We propose a novel taxonomy for categorizing the methods used to optimize SLMs, including model compression, pruning, and quantization techniques.
Taipan: Efficient and Expressive State Space Language Models with Selective Attention
Efficient long-context language modeling remains a significant challenge in Natural Language Processing (NLP).
Knowledge-Aware Query Expansion with Large Language Models for Textual and Relational Retrieval
Large language models (LLMs) have been used to generate query expansions augmenting original queries for improving information search.
A Multi-LLM Debiasing Framework
Large Language Models (LLMs) are powerful tools with the potential to benefit society immensely, yet, they have demonstrated biases that perpetuate societal inequalities.
Visual Prompting in Multimodal Large Language Models: A Survey
This paper presents the first comprehensive survey on visual prompting methods in MLLMs, focusing on visual prompting, prompt generation, compositional reasoning, and prompt learning.
Diversify-verify-adapt: Efficient and Robust Retrieval-Augmented Ambiguous Question Answering
The retrieval augmented generation (RAG) framework addresses an ambiguity in user queries in QA systems by retrieving passages that cover all plausible interpretations and generating comprehensive responses based on the passages.
A Framework for Fine-Tuning LLMs using Heterogeneous Feedback
Additionally, datasets can vary extensively in supervision format, from numerical to binary as well as multi-dimensional with many different values.
KaPQA: Knowledge-Augmented Product Question-Answering
Question-answering for domain-specific applications has recently attracted much interest due to the latest advancements in large language models (LLMs).
Causal Discovery-Driven Change Point Detection in Time Series
Change point detection in time series seeks to identify times when the probability distribution of time series changes.
Causal Discovery in Semi-Stationary Time Series
The structural causal model (SCM) of this type of time series, called the semi-stationary time series, exhibits that a finite number of different causal mechanisms occur sequentially and periodically across time.
Towards Enhancing Coherence in Extractive Summarization: Dataset and Experiments with LLMs
Motivated by this, we propose a systematically created human-annotated dataset consisting of coherent summaries for five publicly available datasets and natural language user feedback, offering valuable insights into how to improve coherence in extractive summaries.
Learning to Reduce: Towards Improving Performance of Large Language Models on Structured Data
This paper proposes a framework, Learning to Reduce, that fine-tunes a language model with On-Policy Learning to generate a reduced version of an input structured data.
LongLaMP: A Benchmark for Personalized Long-form Text Generation
In this work, we demonstrate the importance of user-specific personalization for long-text generation tasks and develop the Long-text Language Model Personalization (LongLaMP) Benchmark.
Large Generative Graph Models
To remedy this crucial gap, we propose a new class of graph generative model called Large Graph Generative Model (LGGM) that is trained on a large corpus of graphs (over 5000 graphs) from 13 different domains.
Hallucination Diversity-Aware Active Learning for Text Summarization
Large Language Models (LLMs) have shown propensity to generate hallucinated outputs, i. e., texts that are factually incorrect or unsupported.
Which LLM to Play? Convergence-Aware Online Model Selection with Time-Increasing Bandits
In this paper, we propose a time-increasing bandit algorithm TI-UCB, which effectively predicts the increase of model performances due to finetuning and efficiently balances exploration and exploitation in model selection.
Learning to Reduce: Optimal Representations of Structured Data in Prompting Large Language Models
The model learns to reduce the input context using On-Policy Reinforcement Learning and aims to improve the reasoning performance of a fixed LLM.
Delivery Optimized Discovery in Behavioral User Segmentation under Budget Constraint
Following the discovery of segments, delivery of messages to users through preferred media channels like Facebook and Google can be challenging, as only a portion of users in a behavior segment find match in a medium, and only a fraction of those matched actually see the message (exposure).
Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes
Large language models (LLMs) have shown remarkable advances in language generation and understanding but are also prone to exhibiting harmful social biases.
ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search
It formulates the entire action space as a decision tree, where each node represents a possible API function call involved in a solution plan.
CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages
However, when it comes to training datasets for these LLMs, especially the recent state-of-the-art models, they are often not fully disclosed.
PDFTriage: Question Answering over Long, Structured Documents
Representing such structured documents as plain text is incongruous with the user's mental model of these documents with rich structure.
Bias and Fairness in Large Language Models: A Survey
Rapid advancements of large language models (LLMs) have enabled the processing, understanding, and generation of human-like text, with increasing integration into systems that touch our social sphere.
Knowledge Graph Prompting for Multi-Document Question Answering
Concurrently, the graph traversal agent acts as a local navigator that gathers pertinent context to progressively approach the question and guarantee retrieval quality.
Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback
Okapi introduces instruction and response-ranked data in 26 diverse languages to facilitate the experiments and development of future multilingual LLM research.
FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedback
Captions are crucial for understanding scientific visualizations and documents.
Fairness-Aware Graph Neural Networks: A Survey
In this article, we examine and categorize fairness techniques for improving the fairness of GNNs.
A Model-free Closeness-of-influence Test for Features in Supervised Learning
Ideally, it is desired to understand how a set of collected features combine together and influence the response value, but this problem is notoriously difficult, due to the high-dimensionality of data and limited number of labeled data points, among many others.
Learning the Visualness of Text Using Large Vision-Language Models
Visual text evokes an image in a person's mind, while non-visual text fails to do so.
Structured Dynamic Pricing: Optimal Regret in a Global Shrinkage Model
We consider dynamic pricing strategies in a streamed longitudinal data set-up where the objective is to maximize, over time, the cumulative profit across a large number of customer segments.
PersonaSAGE: A Multi-Persona Graph Neural Network
Furthermore, PersonaSAGE learns the appropriate set of persona embeddings for each node in the graph, and every node can have a different number of assigned persona embeddings.
A Hypergraph Neural Network Framework for Learning Hyperedge-Dependent Node Embeddings
In this work, we introduce a hypergraph representation learning framework called Hypergraph Neural Networks (HNN) that jointly learns hyperedge embeddings along with a set of hyperedge-dependent embeddings for each node in the hypergraph.
Robustness of Fusion-based Multimodal Classifiers to Cross-Modal Content Dilutions
Our work aims to highlight and encourage further research on the robustness of deep multimodal models to realistic variations, especially in human-facing societal applications.
Direct Embedding of Temporal Network Edges via Time-Decayed Line Graphs
We present a simple method that avoids both shortcomings: construct the line graph of the network, which includes a node for each interaction, and weigh the edges of this graph based on the difference in time between interactions.
Implicit Session Contexts for Next-Item Recommendations
Session-based recommender systems capture the short-term interest of a user within a session.
Network Report: A Structured Description for Network Datasets
Challenges arise as networks are often used across different domains (e. g., network science, physics, etc) and have complex structures.
CyCLIP: Cyclic Contrastive Language-Image Pretraining
Recent advances in contrastive representation learning over paired image-text data have led to models such as CLIP that achieve state-of-the-art performance for zero-shot classification and distributional robustness.
Online MAP Inference and Learning for Nonsymmetric Determinantal Point Processes
In this paper, we introduce the online and streaming MAP inference and learning problems for Non-symmetric Determinantal Point Processes (NDPPs) where data points arrive in an arbitrary order and the algorithms are constrained to use a single-pass over the data as well as sub-linear memory.
Influence-guided Data Augmentation for Neural Tensor Completion
In this paper, we propose DAIN, a general data augmentation framework that enhances the prediction accuracy of neural tensor completion methods.
Edge: Enriching Knowledge Graph Embeddings with External Text
Knowledge graphs suffer from sparsity which degrades the quality of representations generated by various methods.
Insight-centric Visualization Recommendation
This global ranking makes it difficult and time-consuming for users to find the most interesting or relevant insights.
Personalized Visualization Recommendation
Visualization recommendation work has focused solely on scoring visualizations based on the underlying dataset and not the actual user and their past visualization feedback.
Fundamental Tradeoffs in Distributionally Adversarial Training
We study the tradeoff between standard risk and adversarial risk and derive the Pareto-optimal tradeoff, achievable over specific classes of models, in the infinite data limit with features dimension kept fixed.
Heterogeneous Graphlets
Notably, since typed graphlet is more general than colored graphlet (and untyped graphlets), the counts of various typed graphlets can be combined to obtain the counts of the much simpler notion of colored graphlets.
Graph Deep Factors for Forecasting
GraphDF is a hybrid forecasting framework that consists of a relational global and relational local model.
Graph Neural Networks with Heterophily
Graph Neural Networks (GNNs) have proven to be useful for many different practical applications.
A Context Integrated Relational Spatio-Temporal Model for Demand and Supply Forecasting
We propose a novel context integrated relational model, Context Integrated Graph Neural Network (CIGNN), which leverages the temporal, relational, spatial, and dynamic contextual dependencies for multi-step ahead demand forecasting.
ML-based Visualization Recommendation: Learning to Recommend Visualizations from Data
Finally, we observed a strong preference by the human experts in our user study towards the visualizations recommended by our ML-based system as opposed to the rule-based system (5. 92 from a 7-point Likert scale compared to only 3. 45).
Automating Outlier Detection via Meta-Learning
Given an unsupervised outlier detection (OD) task on a new dataset, how can we automatically select a good outlier detection method and its hyperparameter(s) (collectively called a model)?
From Static to Dynamic Node Embeddings
While previous work on dynamic modeling and embedding has focused on representing a stream of timestamped edges using a time-series of graphs based on a specific time-scale (e. g., 1 month), we propose the notion of an $\epsilon$-graph time-series that uses a fixed number of edges for each graph, and show its superiority over the time-scale representation used in previous work.
Structured Policy Iteration for Linear Quadratic Regulator
In this paper, we introduce the \textit{Structured Policy Iteration} (S-PI) for LQR, a method capable of deriving a structured linear policy.
Temporal Network Sampling
In addition, we propose a temporally decaying sampling algorithm with unbiased estimators for studying networks that evolve in continuous time, where the strength of links is a function of time, and the motif patterns are temporally-weighted.
On Proximity and Structural Role-based Embeddings in Networks: Misconceptions, Techniques, and Applications
Unfortunately, recent work has sometimes confused the notion of structural roles and communities (based on proximity) leading to misleading or incorrect claims about the capabilities of network embedding methods.
Higher-Order Ranking and Link Prediction: From Closing Triangles to Closing Higher-Order Motifs
In this work, we investigate higher-order network motifs and develop techniques based on the notion of closing higher-order motifs that move beyond closing simple triangles.
Dynamic Node Embeddings from Edge Streams
In this work, we propose using the notion of temporal walks for learning dynamic embeddings from temporal networks.
Heterogeneous Network Motifs
To address this problem, we propose a fast, parallel, and space-efficient framework for counting typed graphlets in large networks.
Higher-order Spectral Clustering for Heterogeneous Graphs
Using typed-graphlets as a basis, we develop a general principled framework for higher-order clustering in heterogeneous networks.
Higher-order Graph Convolutional Networks
Experiments show that our proposed method is able to achieve state-of-the-art results on the semi-supervised node classification task.
Attention Models in Graphs: A Survey
However, in the real-world, graphs can be both large - with many complex patterns - and noisy which can pose a problem for effective graph mining.
Predicting Graph Categories from Structural Properties
Even though the current version of this paper is withdrawn, there was no disagreement between authors on the novel work in this paper.
HONE: Higher-Order Network Embeddings
This paper describes a general framework for learning Higher-Order Network Embeddings (HONE) from graph data based on network motifs.
Similarity-based Multi-label Learning
Multi-label classification is an important learning problem with many applications.
Inductive Representation Learning in Large Attributed Graphs
To make these methods more generally applicable, we propose a framework for inductive network representation learning based on the notion of attributed random walk that is not tied to node identity and is instead based on learning a function $\Phi : \mathrm{\rm \bf x} \rightarrow w$ that maps a node attribute vector $\mathrm{\rm \bf x}$ to a type $w$.
A Framework for Generalizing Graph-based Representation Learning Methods
Random walks are at the heart of many existing deep learning algorithms for graph data.
Network Classification and Categorization
To the best of our knowledge, this paper presents the first large-scale study that tests whether network categories (e. g., social networks vs. web graphs) are distinguishable from one another (using both categories of real-world networks and synthetic graphs).
Deep Feature Learning for Graphs
This paper presents a general graph representation learning framework called DeepGL for learning deep node and edge representations from large (attributed) graphs.
Estimation of Graphlet Statistics
In this work, we propose an unbiased graphlet estimation framework that is (a) fast with significant speedups compared to the state-of-the-art, (b) parallel with nearly linear-speedups, (c) accurate with <1% relative error, (d) scalable and space-efficient for massive networks with billions of edges, and (e) flexible for a variety of real-world settings, as well as estimating macro and micro-level graphlet statistics (e. g., counts) of both connected and disconnected graphlets.
Revisiting Role Discovery in Networks: From Node to Edge Roles
The experimental results demonstrate the utility of edge roles for network analysis tasks on a variety of graphs from various problem domains.
Hybrid CPU-GPU Framework for Network Motifs
In this paper, we propose a key class of hybrid parallel graphlet algorithms that leverages multiple CPUs and GPUs simultaneously for computing k-vertex induced subgraph statistics (called graphlets).
Relational Similarity Machines
Despite the importance of relational learning, most existing methods are hard to adapt to different settings, due to issues with efficiency, scalability, accuracy, and flexibility for handling a wide variety of classification problems, data, constraints, and tasks.
Graphlet Decomposition: Framework, Algorithms, and Applications
From social science to biology, numerous applications often rely on graphlets for intuitive and meaningful characterization of networks at both the global macro-level as well as the local micro-level.
A Web-based Interactive Visual Graph Analytics Platform
This paper proposes a web-based visual graph analytics platform for interactive graph mining, visualization, and real-time exploration of networks.
Parallel Maximum Clique Algorithms with Applications to Network Analysis and Storage
We propose a fast, parallel maximum clique algorithm for large sparse graphs that is designed to exploit characteristics of social and information networks.
Social and Information Networks Distributed, Parallel, and Cluster Computing Discrete Mathematics Data Structures and Algorithms Physics and Society 05C69 G.2.2
