Search Results for author:
Found 29 papers, 10 papers with code
Tackling Zero Pronoun Resolution and Non-Zero Coreference Resolution Jointly
Zero pronoun resolution aims at recognizing dropped pronouns and pointing out their anaphoric mentions, while non-zero coreference resolution targets at clustering mentions referring to the same entity.
PANDA: Preference Adaptation for Enhancing Domain-Specific Abilities of LLMs
While Large language models (LLMs) have demonstrated considerable capabilities across various natural language tasks, they often fall short of the performance achieved by domain-specific state-of-the-art models.
Bayesian Federated Learning Via Expectation Maximization and Turbo Deep Approximate Message Passing
In this work, we propose a message passing based Bayesian federated learning (BFL) framework to avoid these drawbacks. Specifically, we formulate the problem of deep neural network (DNN) learning and compression and as a sparse Bayesian inference problem, in which group sparse prior is employed to achieve structured model compression.
Towards Unified Alignment Between Agents, Humans, and Environment
We also conduct proof-of-concept studies by introducing realistic features to WebShop, including user profiles to demonstrate intentions, personalized reranking for complex environmental dynamics, and runtime cost statistics to reflect self-constraints.
Improving the Robustness of Knowledge-Grounded Dialogue via Contrastive Learning
Knowledge-grounded dialogue (KGD) learns to generate an informative response based on a given dialogue context and external knowledge (\emph{e. g.}, knowledge graphs; KGs).
Planning and Rendering: Towards End-to-End Product Poster Generation
At the planning stage, we propose a PlanNet to generate the layout of the product and other visual components considering both the appearance features of the product and semantic features of the text, which improves the diversity and rationality of the layouts.
A Two-Stage 2D Channel Extrapolation Scheme for TDD 5G NR Systems
A novel two-stage two-dimensional (2D) channel extrapolation scheme in both frequency and time domain is proposed, designed to mitigate the negative effects of imperfection factors and ensure high-accuracy channel estimation.
A Stochastic Particle Variational Bayesian Inference Inspired Deep-Unfolding Network for Non-Convex Parameter Estimation
Given these challenges, firstly, we propose a parallel stochastic particle variational Bayesian inference (PSPVBI) algorithm.
Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
Specifically, we introduce a well-designed visual tokenizer to translate the non-linguistic image into a sequence of discrete tokens like a foreign language that LLM can read.
Successive Linear Approximation VBI for Joint Sparse Signal Recovery and Dynamic Grid Parameters Estimation
To overcome these drawbacks, we first propose a successive linear approximation VBI (SLA-VBI) algorithm that can provide Bayesian estimation of both sparse signals and dynamic grid parameters.
Snowman: A Million-scale Chinese Commonsense Knowledge Graph Distilled from Foundation Model
Constructing commonsense knowledge graphs (CKGs) has attracted wide research attention due to its significant importance in cognitive intelligence.
Relation-Aware Diffusion Model for Controllable Poster Layout Generation
To advance research in this field, we have constructed a poster layout dataset named CGL-Dataset V2.
A Single-Loop Deep Actor-Critic Algorithm for Constrained Reinforcement Learning with Provable Convergence
In spite of the biased policy gradient estimation incurred by the single-loop design and observation reuse, we prove that the SLDAC with a feasible initial point can converge to a Karush-Kuhn-Tuker (KKT) point of the original problem almost surely.
Joint Scattering Environment Sensing and Channel Estimation Based on Non-stationary Markov Random Field
A location domain channel modeling method is proposed based on the position of targets and scatterers in the scattering environment, and the resulting radar and communication channels exhibit a two-dimensional (2-D) joint burst sparsity.
Joint Scattering Environment Sensing and Channel Estimation for Integrated Sensing and Communication
A location domain channel modeling method is proposed based on the position of targets and scatterers in the scattering environment, and the resulting radar and communication channels exhibit a partially common sparsity.
Long-Document Cross-Lingual Summarization
Cross-Lingual Summarization (CLS) aims at generating summaries in one language for the given documents in another language.
Fundamental Limits and Optimization of Multiband Sensing
Then, a metric called the statistical resolution limit (SRL) that provides a resolution limit is employed to investigate the fundamental limits of delay resolution.
A Two-stage Multiband WiFi Sensing Scheme via Stochastic Particle-Based Variational Bayesian Inference
Multiband fusion enhances WiFi sensing by jointly utilizing signals from multiple non-contiguous frequency bands.
RT-KGD: Relation Transition Aware Knowledge-Grounded Dialogue Generation
Nevertheless, the correlations between knowledge implied in the multi-turn context and the transition regularities between relations in KGs are under-explored.
Latency Minimization for mmWave D2D Mobile Edge Computing Systems: Joint Task Allocation and Hybrid Beamforming Design
Mobile edge computing (MEC) and millimeter wave (mmWave) communications are capable of significantly reducing the network's delay and enhancing its capacity.
Multiband Delay Estimation for Localization Using a Two-Stage Global Estimation Scheme
In the coarse stage, we exploit the group sparsity structure of the multiband channel and propose a Turbo Bayesian inference (Turbo-BI) algorithm to achieve a good initial delay estimation based on a coarse signal model, which is transformed from the original multiband signal model by absorbing the carrier frequency terms.
Channel Tracking and Prediction for IRS-aided Wireless Communications
Based on the proposed transmission protocol, we propose a two-stage channel tracking and prediction (2SCTP) scheme to obtain the direct and reflected channels with low channel training overhead, which is achieved by exploiting the temporal correlation of the time-varying channels.
Incorporating Commonsense Knowledge into Story Ending Generation via Heterogeneous Graph Networks
Story ending generation is an interesting and challenging task, which aims to generate a coherent and reasonable ending given a story context.
Knowledge Enhanced Sports Game Summarization
Additionally, we also introduce a knowledge-enhanced summarizer that utilizes both live commentaries and the knowledge to generate sports news.
Successive Convex Approximation Based Off-Policy Optimization for Constrained Reinforcement Learning
We propose a successive convex approximation based off-policy optimization (SCAOPO) algorithm to solve the general constrained reinforcement learning problem, which is formulated as a constrained Markov decision process (CMDP) in the context of average cost.
Two-Stage Stochastic Optimization via Primal-Dual Decomposition and Deep Unrolling
Then we propose a PDD-based stochastic successive convex approximation (PDD-SSCA) algorithmic framework to find KKT solutions for two-stage stochastic optimization problems.
Energy Efficiency Optimization for Millimeter Wave System with Resolution-Adaptive ADCs
This letter investigates the uplink of a multi-user millimeter wave (mmWave) system, where the base station (BS) is equipped with a massive multiple-input multiple-output (MIMO) array and resolution-adaptive analog-to-digital converters (RADCs).
Sparse Bayesian Learning Approach for Discrete Signal Reconstruction
By integrating the discretization enforcing prior into the SBL framework and applying the variational Bayesian inference (VBI) methodology, we devise an alternating optimization algorithm to jointly characterize the finite-alphabet feature and reconstruct the unknown signal.
Stochastic Successive Convex Approximation for Non-Convex Constrained Stochastic Optimization
The proposed CSSCA algorithm can also handle stochastic non-convex constraints in optimization problems, and it opens the way to solving more challenging optimization problems that occur in many applications.
Information Theory Information Theory
