Search Results for author:
Found 46 papers, 7 papers with code
Joint Goal Segmentation and Goal Success Prediction on Multi-Domain Conversations
To evaluate the performance of a multi-domain goal-oriented Dialogue System (DS), it is important to understand what the users’ goals are for the conversations and whether those goals are successfully achieved.
DeepTraverse: A Depth-First Search Inspired Network for Algorithmic Visual Understanding
Conventional vision backbones, despite their success, often construct features through a largely uniform cascade of operations, offering limited explicit pathways for adaptive, iterative refinement.
JointDistill: Adaptive Multi-Task Distillation for Joint Depth Estimation and Scene Segmentation
While existing solutions transfer multiple teachers' knowledge in a static way, we propose a self-adaptive distillation method that can dynamically adjust the knowledge amount from each teacher according to the student's current learning ability.
SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Activation Sparsity
Despite the growing integration of deep models into mobile terminals, the accuracy of these models declines significantly due to various deployment interferences.
Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs
For example, the KV cache size of Llama2-7B is reduced by 92. 19%, with only a 0. 5% drop in LongBench performance.
AntLM: Bridging Causal and Masked Language Models
For the BabyLM Challenge 2024, we propose a novel language modeling paradigm named $\textbf{AntLM}$, which integrates both CLM and MLM to leverage the advantages of these two classic paradigms.
AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices
However, the \textit{dynamic} and \textit{diverse} deployment contexts of mobile devices pose significant challenges.
Towards Robust Cross-Domain Recommendation with Joint Identifiability of User Preference
To achieve this, we introduce a hierarchical user preference modeling framework that organizes user representations by the neural network encoder's depth, allowing separate treatment of shallow and deeper subspaces.
DaYu: Data-Driven Model for Geostationary Satellite Observed Cloud Images Forecasting
Unlike existing data-driven weather forecasting models, DaYu is specifically designed for geostationary satellite observations, with a temporal resolution of 0. 5 hours and a spatial resolution of ${0. 05}^\circ$ $\times$ ${0. 05}^\circ$.
AdaFlow: Opportunistic Inference on Asynchronous Mobile Data with Generalized Affinity Control
In response, we present a shift to \textit{opportunistic} inference for asynchronous distributed multi-modal data, enabling inference as soon as partial data arrives.
UbiHR: Resource-efficient Long-range Heart Rate Sensing on Ubiquitous Devices
Ubiquitous on-device heart rate sensing is vital for high-stress individuals and chronic patients.
AdaShadow: Responsive Test-time Model Adaptation in Non-stationary Mobile Environments
AdaShadow addresses these challenges with a backpropagation-free assessor to rapidly identify critical layers, a unit-based runtime predictor to account for resource dynamics in latency estimation, and an online scheduler for prompt layer update planning.
DiffSG: A Generative Solver for Network Optimization with Diffusion Model
In summary, we demonstrate the potential of generative diffusion models in tackling complex network optimization problems and outline a promising path for their broader application in the communication community.
Inference Performance Optimization for Large Language Models on CPUs
Large language models (LLMs) have shown exceptional performance and vast potential across diverse tasks.
CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Community
Knowledge transfer is an effective method to enhance learning performance by avoiding the exorbitant costs associated with data recollection and model retraining.
Hawk: Learning to Understand Open-World Video Anomalies
Video Anomaly Detection (VAD) systems can autonomously monitor and identify disturbances, reducing the need for manual labor and associated costs.
Deep Learning Inference on Heterogeneous Mobile Processors: Potentials and Pitfalls
There is a growing demand to deploy computation-intensive deep learning (DL) models on resource-constrained mobile devices for real-time intelligent applications.
Joint Identifiability of Cross-Domain Recommendation via Hierarchical Subspace Disentanglement
Such a failure may overlook the conditionality between two domains and how it contributes to latent factor disentanglement, leading to negative transfer when domains are weakly correlated.
The Future of Cognitive Strategy-enhanced Persuasive Dialogue Agents: New Perspectives and Trends
To depict the research trends of CogAgent, in this paper, we first present several fundamental cognitive psychology theories and give the formalized definition of three typical cognitive strategies, including the persuasion strategy, the topic path planning strategy, and the argument structure prediction strategy.
Learning Decentralized Traffic Signal Controllers with Multi-Agent Graph Reinforcement Learning
Nevertheless, existing MARL algorithms ignore effective information aggregation which is fundamental for improving the learning capacity of decentralized agents.
RaftFed: A Lightweight Federated Learning Framework for Vehicular Crowd Intelligence
Although federated learning (FL) is a promising tool to solve the problem, adapting conventional FL frameworks to VCI is nontrivial.
Enabling Resource-efficient AIoT System with Cross-level Optimization: A survey
Accordingly, the accuracy and responsiveness of DL models are bounded by resource availability.
Distributional Domain-Invariant Preference Matching for Cross-Domain Recommendation
Next, we aim to build distributional implicit matchings between the domain-level preferences of two domains.
Collaborative Route Planning of UAVs, Workers and Cars for Crowdsensing in Disaster Response
In this paper, we explicitly address the route planning for a group of agents, including UAVs, workers, and cars, with the goal of maximizing the task completion rate.
PersonaPKT: Building Personalized Dialogue Agents via Parameter-efficient Knowledge Transfer
Personalized dialogue agents (DAs) powered by large pre-trained language models (PLMs) often rely on explicit persona descriptions to maintain personality consistency.
Limits of Predictability in Top-N Recommendation
This work investigates such predictability by studying the degree of regularity from a specific set of user behavior data.
AdaEnlight: Energy-aware Low-light Video Stream Enhancement on Mobile Devices
We report extensive experiments on diverse datasets, scenarios, and platforms and demonstrate the superiority of AdaEnlight compared with state-of-the-art low-light image and video enhancement solutions.
Spatial Temporal Graph Convolution with Graph Structure Self-learning for Early MCI Detection
The proposed spatial temporal graph convolution block directly exploits BOLD time series as input features, which provides an interesting view for rsfMRI-based preclinical AD diagnosis.
IDNP: Interest Dynamics Modeling using Generative Neural Processes for Sequential Recommendation
In this study, we address these concerns by learning (1) multi-scale representations of short-term interests; and (2) dynamics-aware representations of long-term interests.
Enabling Harmonious Human-Machine Interaction with Visual-Context Augmented Dialogue System: A Review
The intelligent dialogue system, aiming at communicating with humans harmoniously with natural language, is brilliant for promoting the advancement of human-machine interaction in the era of artificial intelligence.
AskMe: Joint Individual-level and Community-level Behavior Interaction for Question Recommendation
On the one hand, we model the rich correlations between the users' diverse behaviors (e. g., answer, follow, vote) to obtain the individual-level behavior interaction.
Multiway sparse distance weighted discrimination
We conducted extensive simulation studies, showing that our model is robust to the degree of sparsity and improves classification accuracy when the data have multiway structure.
DeepExpress: Heterogeneous and Coupled Sequence Modeling for Express Delivery Prediction
To address these issues, we propose DeepExpress - a deep-learning based express delivery sequence prediction model, which extends the classic seq2seq framework to learning complex coupling between sequence and features.
TL-SDD: A Transfer Learning-Based Method for Surface Defect Detection with Few Samples
To solve the imbalanced distribution problem, in this paper we propose TL-SDD: a novel Transfer Learning-based method for Surface Defect Detection.
AdaSpring: Context-adaptive and Runtime-evolutionary Deep Model Compression for Mobile Applications
There are many deep learning (e. g., DNN) powered mobile and wearable applications today continuously and unobtrusively sensing the ambient surroundings to enhance all aspects of human lives.
Towards information-rich, logical text generation with knowledge-enhanced neural models
Text generation system has made massive promising progress contributed by deep learning techniques and has been widely applied in our life.
Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities
In this study, we present a survey of the state-of-the-art deep learning methods for sensor-based human activity recognition.
The Future of Misinformation Detection: New Perspectives and Trends
We first give a brief review of the literature history of MID, based on which we present several new research challenges and techniques of it, including early detection, detection by multimodal data fusion, and explanatory detection.
Conditional Text Generation for Harmonious Human-Machine Interaction
In recent years, with the development of deep learning, text generation technology has undergone great changes and provided many kinds of services for human beings, such as restaurant reservation and daily communication.
From Crowdsourcing to Crowdmining: Using Implicit Human Intelligence for Better Understanding of Crowdsourced Data
A generic model for CrowdMining is further proposed based on a set of existing studies.
Learning Cross-Domain Representation with Multi-Graph Neural Network
In fact, user's behaviors from different domains regarding the same items are usually relevant.
Multi-agent Attentional Activity Recognition
And the multiple agents in the proposed model represent activities with collective motions across body parts by independently selecting modalities associated with single motions.
AI-Powered Text Generation for Harmonious Human-Machine Interaction: Current State and Future Directions
In the last two decades, the landscape of text generation has undergone tremendous changes and is being reshaped by the success of deep learning.
Smart City Development with Urban Transfer Learning
To address this problem, transfer learning can be leveraged to accelerate the smart city development, which we term the urban transfer learning paradigm.
CityTransfer: Transferring Inter- and Intra-City Knowledge for Chain Store Site Recommendation based on Multi-Source Urban Data
To solve the cold-start problem, we propose CityTransfer, which transfers chain store knowledge from semantically-relevant domains (e. g., other cities with rich knowledge, similar chain enterprises in the target city) for chain store placement recommendation in a new city.
Cautionary Tales on Air-Quality Improvement in Beijing
While this statistic offered some relief for the inhabitants of the capital, we present several analyses based on Beijing's PM2. 5 data of the past 4 years at 36 monitoring sites along with meteorological data of the past 7 years.
