Search Results for author:
Found 22 papers, 6 papers with code
PalmBench: A Comprehensive Benchmark of Compressed Large Language Models on Mobile Platforms
Deploying large language models (LLMs) locally on mobile devices is advantageous in scenarios where transmitting data to remote cloud servers is either undesirable due to privacy concerns or impractical due to network connection.
SwinGS: Sliding Window Gaussian Splatting for Volumetric Video Streaming with Arbitrary Length
Recent advances in 3D Gaussian Splatting (3DGS) have garnered significant attention in computer vision and computer graphics due to its high rendering speed and remarkable quality.
An Effective Tag Assignment Approach for Billboard Advertisement
Given trajectory, billboard database, and a set of selected billboard slots and tags, this problem asks to output a mapping of selected tags to the selected slots so that the influence is maximized.
Buffer-based Gradient Projection for Continual Federated Learning
For example, in a task-incremental learning scenario using the CIFAR-100 dataset, our method can increase the accuracy by up to 27%.
Advancing Multi-Modal Sensing Through Expandable Modality Alignment
To tackle this challenge, we introduce the Babel framework, encompassing the neural network architecture, data preparation and processing, as well as the training strategies.
Distilling Opinions at Scale: Incremental Opinion Summarization using XL-OPSUMM
However, the existing test set, AMASUM has only 560 reviews per product on average.
Product Description and QA Assisted Self-Supervised Opinion Summarization
For evaluation, due to the unavailability of test sets with additional sources, we extend the Amazon, Oposum+, and Flipkart test sets and leverage ChatGPT to annotate summaries.
A Picture is Worth 500 Labels: A Case Study of Demographic Disparities in Local Machine Learning Models for Instagram and TikTok
Capitalizing on this new processing model of locally analyzing user images, we analyze two popular social media apps, TikTok and Instagram, to reveal (1) what insights vision models in both apps infer about users from their image and video data and (2) whether these models exhibit performance disparities with respect to demographics.
Leveraging Domain Knowledge for Efficient Reward Modelling in RLHF: A Case-Study in E-Commerce Opinion Summarization
While this strategy has proven effective, the training methodology requires a lot of human preference annotation (usually in the order of tens of thousands) to train $\varphi$.
One Prompt To Rule Them All: LLMs for Opinion Summary Evaluation
Evaluation of opinion summaries using conventional reference-based metrics rarely provides a holistic evaluation and has been shown to have a relatively low correlation with human judgments.
Minimizing Regret in Billboard Advertisement under Zonal Influence Constraint
In the second one, we introduce randomness with the first one, where we perform the marginal gain computation for a sample of randomly chosen billboard slots.
Towards Regret Free Slot Allocation in Billboard Advertisement
In the context of an influence provider, it is a loss for him if he offers more or less views.
Hierarchical Federated Learning with Privacy
Federated learning (FL), where data remains at the federated clients, and where only gradient updates are shared with a central aggregator, was assumed to be private.
Fast and Sample-Efficient Domain Adaptation for Autoencoder-Based End-to-End Communication
In this paper, we address the setting where the target domain has only limited labeled data from a distribution that is expected to change frequently.
Few-Shot Domain Adaptation For End-to-End Communication
The problem of end-to-end learning of a communication system using an autoencoder -- consisting of an encoder, channel, and decoder modeled using neural networks -- has recently been shown to be an effective approach.
A General Framework For Detecting Anomalous Inputs to DNN Classifiers
We propose an unsupervised anomaly detection framework based on the internal DNN layer representations in the form of a meta-algorithm with configurable components.
Earned Benefit Maximization in Social Networks Under Budget Constraint
In this paper, we study this problem with a variation, where a set of nodes are designated as target nodes, each of them is assigned with a benefit value, that can be earned by influencing them, and our goal is to maximize the earned benefit by initially activating a set of nodes within the budget.
Social and Information Networks Data Structures and Algorithms Multiagent Systems
Graph Convolutional Network with Sequential Attention For Goal-Oriented Dialogue Systems
Domain specific goal-oriented dialogue systems typically require modeling three types of inputs, viz., (i) the knowledge-base associated with the domain, (ii) the history of the conversation, which is a sequence of utterances and (iii) the current utterance for which the response needs to be generated.
Target Set Selection parameterized by vertex cover and more
We have the following results on the TSS problem: -> It was shown by Nichterlein et al. [Social Network Analysis and Mining, 2013] that it is possible to compute an optimal-sized target set in $O(2^{(2^{t}+1)t}\cdot m)$ time, where $t$ denotes the cardinality of a minimum degree-$0$ modulator of $G$.
Computational Complexity Data Structures and Algorithms Social and Information Networks 68W25, 68Q17, 68R10,
Towards Exploiting Background Knowledge for Building Conversation Systems
Existing dialog datasets contain a sequence of utterances and responses without any explicit background knowledge associated with them.
A Survey on Influence Maximization in a Social Network
Given a social network with diffusion probabilities as edge weights and an integer k, which k nodes should be chosen for initial injection of information to maximize influence in the network?
Social and Information Networks
A Dataset for Building Code-Mixed Goal Oriented Conversation Systems
("Can you help me in booking a table at this restaurant?").
