Search Results for author:
Found 38 papers, 11 papers with code
Human-In-the-Loop Software Development Agents
In this paper, we introduce a Human-in-the-loop LLM-based Agents framework (HULA) for software development that allows software engineers to refine and guide LLMs when generating coding plans and source code for a given task.
Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent
In this paper, we introduce Hunyuan-Large, which is currently the largest open-source Transformer-based mixture of experts model, with a total of 389 billion parameters and 52 billion activation parameters, capable of handling up to 256K tokens.
DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization
Finally, our method can identify an optimal SubNet through few-step gradient optimization and a simple post-processing procedure.
Theta and/or alpha? Neural oscillational substrates for dynamic inter-brain synchrony during mother-child cooperation
Conversely, the {\alpha}-IBS state, accompanied by the EEG frequency-shift to the {\alpha} range, is more prominent during mother-led interactions.
Channel Estimation, Interpolation and Extrapolation in Doubly-dispersive Channels
Both aliasing and ISCI are considered in channel modelling, a low-complexity algorithm is proposed for channel estimation and interpolation through FFT.
Controllable Longer Image Animation with Diffusion Models
In contrast, we propose an efficient long-duration video generation method based on noise reschedule specifically tailored for image animation tasks, facilitating the creation of videos over 100 frames in length while maintaining consistency in content scenery and motion coordination.
Pre-training Cross-lingual Open Domain Question Answering with Large-scale Synthetic Supervision
Cross-lingual open domain question answering (CLQA) is a complex problem, comprising cross-lingual retrieval from a multilingual knowledge base, followed by answer generation in the query language.
UPDP: A Unified Progressive Depth Pruner for CNN and Vision Transformer
Our method also achieves state-of-the-art pruning performance on the vision transformer model.
Noisy Self-Training with Synthetic Queries for Dense Retrieval
Although existing neural retrieval models reveal promising results when training data is abundant and the performance keeps improving as training data increases, collecting high-quality annotated data is prohibitively costly.
Boot and Switch: Alternating Distillation for Zero-Shot Dense Retrieval
Experimental results demonstrate that our unsupervised $\texttt{ABEL}$ model outperforms both leading supervised and unsupervised retrievers on the BEIR benchmark.
A Novel Catastrophic Condition for Periodically Time-varying Convolutional Encoders Based on Time-varying Equivalent Convolutional Encoders
A convolutional encoder is said to be catastrophic if it maps an information sequence of infinite weight into a code sequence of finite weight.
Pro-PRIME: A general Temperature-Guided Language model to engineer enhanced Stability and Activity in Proteins
Designing protein mutants of both high stability and activity is a critical yet challenging task in protein engineering.
Learned Focused Plenoptic Image Compression with Microimage Preprocessing and Global Attention
Also, it achieves 18. 73% bitrate saving and generates perceptually pleasant reconstructions compared to the state-of-the-art end-to-end image compression methods, which benefits the applications of focused plenoptic cameras greatly.
Experimental Validation of Single BS 5G mmWave Positioning and Mapping for Intelligent Transport
Positioning with 5G signals generally requires connection to several base stations (BSs), which makes positioning more demanding in terms of infrastructure than communications.
Inter-brain substrates of role switching during mother-child interaction
Mother-child interaction is highly dynamic and reciprocal.
ESPRIT-Oriented Precoder Design for mmWave Channel Estimation
We consider the problem of ESPRIT-oriented precoder design for beamspace angle-of-departure (AoD) estimation in downlink mmWave multiple-input single-output communications.
FDViT: Improve the Hierarchical Architecture of Vision Transformer
In this paper, we propose FDViT to improve the hierarchical architecture of the vision transformer by using a flexible downsampling layer that is not limited to integer stride to smoothly reduce the sizes of the middle feature maps.
Wideband mmWave Massive MIMO Channel Estimation and Localization
Spatial wideband effects are known to affect channel estimation and localization performance in millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) systems.
Two-Timescale Transmission Design and RIS Optimization for Integrated Localization and Communications
Reconfigurable intelligent surfaces (RISs) have tremendous potential to boost communication performance, especially when the line-of-sight (LOS) path between the user equipment (UE) and base station (BS) is blocked.
An Iterative 5G Positioning and Synchronization Algorithm in NLOS Environments with Multi-Bounce Paths
Numerical simulations are carried out to evaluate the performance of the proposed algorithm.
Doppler Exploitation in Bistatic mmWave Radio SLAM
Networks in 5G and beyond utilize millimeter wave (mmWave) radio signals, large bandwidths, and large antenna arrays, which bring opportunities in jointly localizing the user equipment and mapping the propagation environment, termed as simultaneous localization and mapping (SLAM).
Doppler-Enabled Single-Antenna Localization and Mapping Without Synchronization
With the help of multipath components (MPCs), localization and mapping tasks can be done with a single base station (BS) and single unsynchronized user equipment (UE) if both of them are equipped with an antenna array.
SADN: Learned Light Field Image Compression with Spatial-Angular Decorrelation
Light field image becomes one of the most promising media types for immersive video applications.
Incorporating Constituent Syntax for Coreference Resolution
Moreover, we also explore to utilise higher-order neighbourhood information to encode rich structures in constituent trees.
Iterated Posterior Linearization PMB Filter for 5G SLAM
In this paper, we study the linearization of the measurement function with respect to the posterior PDF, and implement the iterated posterior linearization filter into the Poisson multi-Bernoulli SLAM filter.
Probabilistic Tracking with Deep Factors
In this paper, we show how to use a deep feature encoding in conjunction with generative densities over the features in a factor-graph based, probabilistic tracking framework.
EndHiC: assemble large contigs into chromosomal-level scaffolds using the Hi-C links from contig ends
As the Hi-C links of two adjacent contigs concentrate only at the neighbor ends of the contigs, larger contig size will reduce the power to differentiate adjacent (signal) and non-adjacent (noise) contig linkages, leading to a higher rate of mis-assembly.
Beamspace Multidimensional ESPRIT Approaches for Simultaneous Localization and Communications
The proposed method is compared to the tensor ESPRIT method, in terms of channel estimation, communication, localization, and sensing performance, further validating the perturbation analysis.
Beyond 5G RIS mmWave Systems: Where Communication and Localization Meet
Upcoming beyond fifth generation (5G) communications systems aim at further enhancing key performance indicators and fully supporting brand new use cases by embracing emerging techniques, e. g., reconfigurable intelligent surface (RIS), integrated communication, localization, and sensing, and mmWave/THz communications.
A Computationally Efficient EK-PMBM Filter for Bistatic mmWave Radio SLAM
Millimeter wave (mmWave) signals are useful for simultaneous localization and mapping (SLAM), due to their inherent geometric connection to the propagation environment and the propagation channel.
Facial expression recognition with grid-wise attention and visual transformer
In particular, in the low-level feature learning, a grid-wise attention mechanism is proposed to capture the dependencies of different regions from a facial expression image such that the parameter update of convolutional filters in low-level feature learning is regularized.
Ranked #8 on
Facial Expression Recognition (FER)
on FER+
(using extra training data)
Facial Expression Recognition
Facial Expression Recognition (FER)
Cooperative mmWave PHD-SLAM with Moving Scatterers
Using the multiple-model (MM) probability hypothesis density (PHD) filter, millimeter wave (mmWave) radio simultaneous localization and mapping (SLAM) in vehicular scenarios is susceptible to movements of objects, in particular vehicles driving in parallel with the ego vehicle.
Incorporating Syntax and Semantics in Coreference Resolution with Heterogeneous Graph Attention Network
External syntactic and semantic information has been largely ignored by existing neural coreference resolution models.
Optimal Spatial Signal Design for mmWave Positioning under Imperfect Synchronization
We consider the problem of spatial signal design for multipath-assisted mmWave positioning under limited prior knowledge on the user's location and clock bias.
Network Massive MIMO Transmission Over Millimeter-Wave and Terahertz Bands: Mobility Enhancement and Blockage Mitigation
Based on these insights, the network massive MIMO precoding design is reduced to a network sum-rate maximization problem with respect to beam domain power allocation.
Estimation of genome size using k-mer frequencies from corrected long reads
We show that corrected third-generation data can be used to count k-mer frequencies and estimate genome size reliably, in replacement of using second-generation data.
Asymptotic expansion for the transition densities of stochastic differential equations driven by the gamma processes
In this paper, enlightened by the asymptotic expansion methodology developed by Li(2013b) and Li and Chen (2016), we propose a Taylor-type approximation for the transition densities of the stochastic differential equations (SDEs) driven by the gamma processes, a special type of Levy processes.
Deep Scene Text Detection with Connected Component Proposals
The second task aims to output a bundle of character candidates used later to verify the word proposals.
