Search Results for author:
Found 50 papers, 17 papers with code
Dynamic Compressing Prompts for Efficient Inference of Large Language Models
We model prompt compression as a Markov Decision Process (MDP), enabling the DCP-Agent to sequentially remove redundant tokens by adapting to dynamic contexts and retaining crucial content.
Skeleton and Font Generation Network for Zero-shot Chinese Character Generation
We used generated misspelled characters as data augmentation in Chinese character error correction tasks, simulating the scenario where students learn handwritten Chinese characters with the help of misspelled characters.
Generating Long-form Story Using Dynamic Hierarchical Outlining with Memory-Enhancement
Long-form story generation task aims to produce coherent and sufficiently lengthy text, essential for applications such as novel writingand interactive storytelling.
Dynamic Ensemble Reasoning for LLM Experts
Ensemble reasoning for the strengths of different LLM experts is critical to achieving consistent and satisfactory performance on diverse inputs across a wide range of tasks.
DCF-DS: Deep Cascade Fusion of Diarization and Separation for Speech Recognition under Realistic Single-Channel Conditions
First, we sequentially integrate the NSD and SS modules within a joint training framework, enabling the separation module to leverage speaker time boundaries from the diarization module effectively.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
WildOcc: A Benchmark for Off-Road 3D Semantic Occupancy Prediction
3D semantic occupancy prediction is an essential part of autonomous driving, focusing on capturing the geometric details of scenes.
Proto-OOD: Enhancing OOD Object Detection with Prototype Feature Similarity
We observe that features of the same category are more tightly clustered in feature space, while those of different categories are more dispersed.
TeFF: Tracking-enhanced Forgetting-free Few-shot 3D LiDAR Semantic Segmentation
However, this approach introduces a data imbalance biased to novel data that presents a new challenge of catastrophic forgetting.
PID: Physics-Informed Diffusion Model for Infrared Image Generation
Infrared imaging technology has gained significant attention for its reliable sensing ability in low visibility conditions, prompting many studies to convert the abundant RGB images to infrared images.
SRFUND: A Multi-Granularity Hierarchical Structure Reconstruction Benchmark in Form Understanding
Accurately identifying and organizing textual content is crucial for the automation of document processing in the field of form understanding.
Disturbance Rejection-Guarded Learning for Vibration Suppression of Two-Inertia Systems
On the other hand, machine learning benefits from an additional assurance layer provided by the ESO, as any imperfections in the machine learning model can be compensated for by the ESO.
FreqMamba: Viewing Mamba from a Frequency Perspective for Image Deraining
Recent studies have witnessed the effectiveness and efficiency of Mamba for perceiving global and local information based on its exploiting local correlation among patches, however, rarely attempts have been explored to extend it with frequency analysis for image deraining, limiting its ability to perceive global degradation that is relevant to frequency modeling (e. g. Fourier transform).
Technical note: ShinyAnimalCV: open-source cloud-based web application for object detection, segmentation, and three-dimensional visualization of animals using computer vision
Moreover, the rapid expansion of precision livestock farming is creating a growing need to educate and train animal science students in CV.
RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark
To fill this gap, we introduce RL4CO, a unified and extensive benchmark with in-depth library coverage of 23 state-of-the-art methods and more than 20 CO problems.
PA&DA: Jointly Sampling PAth and DAta for Consistent NAS
Our method only requires negligible computation cost for optimizing the sampling distributions of path and data, but achieves lower gradient variance during supernet training and better generalization performance for the supernet, resulting in a more consistent NAS.
Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback
Large language models (LLMs), such as ChatGPT, are able to generate human-like, fluent responses for many downstream tasks, e. g., task-oriented dialog and question answering.
Few-shot 3D LiDAR Semantic Segmentation for Autonomous Driving
Thus, we propose a few-shot 3D LiDAR semantic segmentation method that predicts both novel classes and base classes simultaneously.
Autonomous Driving
Generalized Few-Shot Semantic Segmentation
+4
Uniform tensor clustering by jointly exploring sample affinities of various orders
Conventional clustering methods based on pairwise affinity usually suffer from the concentration effect while processing huge dimensional features yet low sample sizes data, resulting in inaccuracy to encode the sample proximity and suboptimal performance in clustering.
Unleashing the Power of Gradient Signal-to-Noise Ratio for Zero-Shot NAS
Neural Architecture Search (NAS) aims to automatically find optimal neural network architectures in an efficient way.
Mapping effective connectivity by virtually perturbing a surrogate brain
Effective connectivity (EC), indicative of the causal interactions between brain regions, is fundamental to understanding information processing in the brain.
CloudBrain-ReconAI: An Online Platform for MRI Reconstruction and Image Quality Evaluation
Efficient collaboration between engineers and radiologists is important for image reconstruction algorithm development and image quality evaluation in magnetic resonance imaging (MRI).
FeatureBooster: Boosting Feature Descriptors with a Lightweight Neural Network
We introduce a lightweight network to improve descriptors of keypoints within the same image.
A General Model-Based Extended State Observer with Built-In Zero Dynamics
A general model-based extended state observer (GMB-ESO) is proposed for single-input single-output linear time-invariant systems with a given state space model, where the total disturbance, a lump sum of model uncertainties and external disturbances, is defined as an extended state in the same manner as in the original formulation of ESO.
AGNAS: Attention-Guided Micro- and Macro-Architecture Search
We utilize the attention weights to represent the importance of the relevant operations for the micro search or the importance of the relevant blocks for the macro search.
Potential utilization of Battery Energy Storage Systems (BESS) in the major European electricity markets
The result shows that under the current empirical estimation of the battery cost and lifetime, BESS is not feasible for energy arbitrage in most of the European electricity markets.
DU-DARTS: Decreasing the Uncertainty of Differentiable Architecture Search
Differentiable Neural Architecture Search (DARTS) recently attracts a lot of research attention because of its high efficiency.
Ranked #9 on
Neural Architecture Search
on CIFAR-100
Learning Linear Polytree Structural Equation Models
We are interested in the problem of learning the directed acyclic graph (DAG) when data are generated from a linear structural equation model (SEM) and the causal structure can be characterized by a polytree.
Deep learning based low-dose synchrotron radiation CT reconstruction
Synchrotron radiation sources are widely used in various fields, among which computed tomography (CT) is one of the most important.
Quantization of Deep Neural Networks for Accurate Edge Computing
Deep neural networks (DNNs) have demonstrated their great potential in recent years, exceeding the per-formance of human experts in a wide range of applications.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
DPointNet: A Density-Oriented PointNet for 3D Object Detection in Point Clouds
In this paper, we put forward a novel density-oriented PointNet (DPointNet) for 3D object detection in point clouds, in which the density of points increases layer by layer.
Model-based cellular kinetic analysis of SARS-CoV-2 infection: different immune response modes and treatment strategies
Integrating theoretical results with clinical COVID-19 patients' data, we classified the COVID-19 development processes into three typical modes of immune responses, correlated with the clinical classification of mild & moderate, severe and critical patients.
ALFA: Adversarial Feature Augmentation for Enhanced Image Recognition
Adversarial training is an effective method to combat adversarial attacks in order to create robust neural networks.
Lip-reading with Hierarchical Pyramidal Convolution and Self-Attention
In this paper, we propose a novel deep learning architecture to improving word-level lip-reading.
Tracking Interaction States for Multi-Turn Text-to-SQL Semantic Parsing
The dynamic schema-state and SQL-state representations are then utilized to decode the SQL query corresponding to current utterance.
Correlating Subword Articulation with Lip Shapes for Embedding Aware Audio-Visual Speech Enhancement
We first extract visual embedding from lip frames using a pre-trained phone or articulation place recognizer for visual-only EASE (VEASE).
A Density-Aware PointRCNN for 3D Object Detection in Point Clouds
We present an improved version of PointRCNN for 3D object detection, in which a multi-branch backbone network is adopted to handle the non-uniform density of point clouds.
Barriers to grid-connected battery systems: Evidence from the Spanish electricity market
The concept of "potentially profitable utilization time" is proposed and introduced to identify and evaluate future potential grid applications for battery systems.
Exploring Spatial-Temporal Multi-Frequency Analysis for High-Fidelity and Temporal-Consistency Video Prediction
Inspired by the frequency band decomposition characteristic of Human Vision System (HVS), we propose a video prediction network based on multi-level wavelet analysis to deal with spatial and temporal information in a unified manner.
Ranked #1 on
Video Prediction
on KTH
(PSNR metric)
PosNeg-Balanced Anchors with Aligned Features for Single-Shot Object Detection
We introduce a novel single-shot object detector to ease the imbalance of foreground-background class by suppressing the easy negatives while increasing the positives.
Integrating Tensor Similarity to Enhance Clustering Performance
The performance of most the clustering methods hinges on the used pairwise affinity, which is usually denoted by a similarity matrix.
See and Think: Disentangling Semantic Scene Completion
Semantic scene completion predicts volumetric occupancy and object category of a 3D scene, which helps intelligent agents to understand and interact with the surroundings.
VarNet: Exploring Variations for Unsupervised Video Prediction
For the KTH dataset, the VarNet outperforms the state-of-the-art works up to 11. 9% on PSNR and 9. 5% on SSIM.
Ranked #1 on
Video Prediction
on KTH
(Cond metric)
Quantization of Fully Convolutional Networks for Accurate Biomedical Image Segmentation
Unlike existing litera- ture on quantization which primarily targets memory and computation complexity reduction, we apply quan- tization as a method to reduce over tting in FCNs for better accuracy.
Commonsense Knowledge Enhanced Embeddings for Solving Pronoun Disambiguation Problems in Winograd Schema Challenge
The PDP task we investigate in this paper is a complex coreference resolution task which requires the utilization of commonsense knowledge.
Ranked #63 on
Coreference Resolution
on Winograd Schema Challenge
Probabilistic Reasoning via Deep Learning: Neural Association Models
We propose to use neural networks to model association between any two events in a domain.
Ranked #11 on
Natural Language Understanding
on PDP60
Part-of-Speech Relevance Weights for Learning Word Embeddings
The model proposed in this paper paper jointly optimizes word vectors and the POS relevance matrices.
Feedforward Sequential Memory Networks: A New Structure to Learn Long-term Dependency
In this paper, we propose a novel neural network structure, namely \emph{feedforward sequential memory networks (FSMN)}, to model long-term dependency in time series without using recurrent feedback.
