Search Results for author:
Found 26 papers, 7 papers with code
DIG3D: Marrying Gaussian Splatting with Deformable Transformer for Single Image 3D Reconstruction
By harnessing the benefits of 3D Gaussians, our approach offers an efficient and accurate solution for 3D reconstruction from single-view images.
IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact
Large language models (LLMs) excel in natural language processing but demand intensive computation.
Generative Learning for Forecasting the Dynamics of Complex Systems
We introduce generative models for accelerating simulations of complex systems through learning and evolving their effective dynamics.
Bayesian Conditional Diffusion Models for Versatile Spatiotemporal Turbulence Generation
A notable feature of our approach is the method proposed for long-span flow sequence generation, which is based on autoregressive gradient-based conditional sampling, eliminating the need for cumbersome retraining processes.
The Development of LLMs for Embodied Navigation
This article offers an exhaustive summary of the symbiosis between LLMs and embodied intelligence with a focus on navigation.
Discovering Symmetry Breaking in Physical Systems with Relaxed Group Convolution
Modeling symmetry breaking is essential for understanding the fundamental changes in the behaviors and properties of physical systems, from microscopic particle interactions to macroscopic phenomena like fluid dynamics and cosmic structures.
Exploring the Optimization Objective of One-Class Classification for Anomaly Detection
One-class classification (OCC) is a longstanding method for anomaly detection.
A Causal Framework to Unify Common Domain Generalization Approaches
Domain generalization (DG) is about learning models that generalize well to new domains that are related to, but different from, the training domain(s).
Mitigating Backdoor Attack Via Prerequisite Transformation
By introducing prerequisite calculation conditions during the training process, these conditions have little impact on normal features and trigger features, and can complete the training of a standard backdoor model.
Explicit Feature Interaction-aware Uplift Network for Online Marketing
Our EFIN includes four customized modules: 1) a feature encoding module encodes not only the user and contextual features, but also the treatment features; 2) a self-interaction module aims to accurately model the user's natural response with all but the treatment features; 3) a treatment-aware interaction module accurately models the degree to which a particular treatment motivates a user through interactions between the treatment features and other features, i. e., ITE; and 4) an intervention constraint module is used to balance the ITE distribution of users between the control and treatment groups so that the model would still achieve a accurate uplift ranking on data collected from a non-random intervention marketing scenario.
Towards Total Online Unsupervised Anomaly Detection and Localization in Industrial Vision
Although existing image anomaly detection methods yield impressive results, they are mostly an offline learning paradigm that requires excessive data pre-collection, limiting their adaptability in industrial scenarios with online streaming data.
Contrastive Domain Generalization via Logit Attribution Matching
Domain Generalization (DG) is an important open problem in machine learning.
Dynamic Security Region of Natural Gas Systems in Integrated Electricity-Gas Systems
In an integrated electricity-gas system (IEGS), the tight coupling of power and natural gas systems is embodied by frequent changes in gas withdrawal from gas-fired units to provide regulation services for the power system to handle uncertainty, which may in turn endanger the secure operation of the natural gas system and ultimately affect the safety of the whole IEGS.
Towards Efficient Visual Simplification of Computational Graphs in Deep Neural Networks
A computational graph in a deep neural network (DNN) denotes a specific data flow diagram (DFD) composed of many tensors and operators.
PatchGT: Transformer over Non-trainable Clusters for Learning Graph Representations
Recently the Transformer structure has shown good performances in graph learning tasks.
Correcting the Sub-optimal Bit Allocation
In this paper, we investigate the problem of bit allocation in Neural Video Compression (NVC).
Multi-Sample Training for Neural Image Compression
This paper considers the problem of lossy neural image compression (NIC).
Bit Allocation using Optimization
In this paper, we consider the problem of bit allocation in Neural Video Compression (NVC).
Depth-Assisted ResiDualGAN for Cross-Domain Aerial Images Semantic Segmentation
Generative methods are common approaches to minimizing the domain gap of aerial images which improves the performance of the downstream tasks, e. g., cross-domain semantic segmentation.
Bone marrow sparing for cervical cancer radiotherapy on multimodality medical images
Experiments on patient dataset reveal that our proposed method can enhance the multimodal image registration accuracy and efficiency for medical practitioners in sparing BM of cervical cancer radiotherapy.
Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression
Entropy modeling is a key component for high-performance image compression algorithms.
ResiDualGAN: Resize-Residual DualGAN for Cross-Domain Remote Sensing Images Semantic Segmentation
The performance of a semantic segmentation model for remote sensing (RS) images pretrained on an annotated dataset would greatly decrease when testing on another unannotated dataset because of the domain gap.
Predicting Physics in Mesh-reduced Space with Temporal Attention
Graph-based next-step prediction models have recently been very successful in modeling complex high-dimensional physical systems on irregular meshes.
Unsupervised cross-user adaptation in taste sensation recognition based on surface electromyography with conformal prediction and domain regularized component analysis
The results show that DRCA improved the classification accuracy on six subjects (p < 0. 05), compared with the baseline models trained only with the source domain data;, while CPSC did not guarantee the accuracy improvement.
Context Detection for Advanced Self-Aware Navigation using Smartphone Sensors
In order to operate across different contexts, a context-adaptive navigation solution introduces an element of self-awareness by detecting the operating context and configuring the positioning system accordingly.
Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recommender Systems
Social recommendation leverages social information to solve data sparsity and cold-start problems in traditional collaborative filtering methods.
Ranked #1 on
Recommendation Systems
on WeChat
