Search Results for author:
Found 50 papers, 18 papers with code
Snapmoji: Instant Generation of Animatable Dual-Stylized Avatars
Our system is capable of producing 3D Gaussian avatars that support dynamic animation, including accurate facial expression transfer.
LUCAS: Layered Universal Codec Avatars
We present LUCAS, a novel Universal Prior Model (UPM) for codec avatar modeling that disentangles face and hair through a layered representation.
The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering
Extensive experiments show that VISTA on average reduces hallucination by abount 40% on evaluated open-ended generation task, and it consistently outperforms existing methods on four benchmarks across four architectures under three decoding strategies.
Temporal Action Localization with Cross Layer Task Decoupling and Refinement
Temporal action localization (TAL) involves dual tasks to classify and localize actions within untrimmed videos.
Efficient Deep Learning Infrastructures for Embedded Computing Systems: A Comprehensive Survey and Future Envision
Specifically, we discuss recent efficient deep learning infrastructures for embedded computing systems from the lens of (1) efficient manual network design for embedded computing systems, (2) efficient automated network design for embedded computing systems, (3) efficient network compression for embedded computing systems, (4) efficient on-device learning for embedded computing systems, (5) efficient large language models for embedded computing systems, (6) efficient deep learning software and hardware for embedded computing systems, and (7) efficient intelligent applications for embedded computing systems.
DICE: Discrete Inversion Enabling Controllable Editing for Multinomial Diffusion and Masked Generative Models
Discrete diffusion models have achieved success in tasks like image generation and masked language modeling but face limitations in controlled content editing.
RingMo-Aerial: An Aerial Remote Sensing Foundation Model With A Affine Transformation Contrastive Learning
Furthermore, the ARS-Adapter, an efficient parameter fine-tuning method, is proposed to improve the model's adaptability and effectiveness in various ARS vision tasks.
RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
This paper proposes RetrievalAttention, a training-free approach to both accelerate attention computation and reduce GPU memory consumption.
Resolving Inconsistent Semantics in Multi-Dataset Image Segmentation
Notably, on four benchmark datasets with label space inconsistencies during inference, we outperform previous methods by 1. 6% mIoU for semantic segmentation, 9. 1% PQ for panoptic segmentation, 12. 1% AP for instance segmentation, and 3. 0% in the newly proposed PIQ metric.
Layout Agnostic Scene Text Image Synthesis with Diffusion Models
While diffusion models have significantly advanced the quality of image generation their capability to accurately and coherently render text within these images remains a substantial challenge.
Make Safe Decisions in Power System: Safe Reinforcement Learning Based Pre-decision Making for Voltage Stability Emergency Control
The high penetration of renewable energy and power electronic equipment bring significant challenges to the efficient construction of adaptive emergency control strategies against various presumed contingencies in today's power systems.
Implicit In-context Learning
In-context Learning (ICL) empowers large language models (LLMs) to adapt to unseen tasks during inference by prefixing a few demonstration examples prior to test queries.
Instantaneous Perception of Moving Objects in 3D
Specifically, due to the lack of correspondences between consecutive frames of sparse Lidar point clouds, static objects might appear to be moving - the so-called swimming effect.
Evaluating the Application of ChatGPT in Outpatient Triage Guidance: A Comparative Study
However, the between-version consistency is relatively low (mean consistency score=1. 43/3, median=1), indicating few recommendations match between the two versions.
AC-EVAL: Evaluating Ancient Chinese Language Understanding in Large Language Models
Given the importance of ancient Chinese in capturing the essence of rich historical and cultural heritage, the rapid advancements in Large Language Models (LLMs) necessitate benchmarks that can effectively evaluate their understanding of ancient contexts.
"When He Feels Cold, He Goes to the Seahorse"-Blending Generative AI into Multimaterial Storymaking for Family Expressive Arts Therapy
And there is a lack of HCI implications on how to support families and therapists in this context.
Clustering Molecular Energy Landscapes by Adaptive Network Embedding
In order to efficiently explore the chemical space of all possible small molecules, a common approach is to compress the dimension of the system to facilitate downstream machine learning tasks.
Pairwise GUI Dataset Construction Between Android Phones and Tablets
There are currently several publicly accessible GUI page datasets for phones, but none for pairwise GUIs between phones and tablets.
DeFormer: Integrating Transformers with Deformable Models for 3D Shape Abstraction from a Single Image
Accurate 3D shape abstraction from a single 2D image is a long-standing problem in computer vision and graphics.
Deep Deformable Models: Learning 3D Shape Abstractions with Part Consistency
The task of shape abstraction with semantic part consistency is challenging due to the complex geometries of natural objects.
Network Embedding Using Sparse Approximations of Random Walks
In this paper, we propose an efficient numerical implementation of Network Embedding based on commute times, using sparse approximation of a diffusion process on the network obtained by a modified version of the diffusion wavelet algorithm.
Improving Tuning-Free Real Image Editing with Proximal Guidance
Null-text inversion (NTI) optimizes null embeddings to align the reconstruction and inversion trajectories with larger CFG scales, enabling real image editing with cross-attention control.
Training Like a Medical Resident: Context-Prior Learning Toward Universal Medical Image Segmentation
Inspired by the training program of medical radiology residents, we propose a shift towards universal medical image segmentation, a paradigm aiming to build medical image understanding foundation models by leveraging the diversity and commonality across clinical targets, body regions, and imaging modalities.
Cooperative IoT Data Sharing with Heterogeneity of Participants Based on Electricity Retail
With the development of Internet of Things (IoT) and big data technology, the data value is increasingly explored in multiple practical scenarios, including electricity transactions.
Resilience in Platoons of Cooperative Heterogeneous Vehicles: Self-organization Strategies and Provably-correct Design
We show that self-organization promotes resilience to acceleration limits and communication failures, i. e., homogenizing to a common group behavior makes the platoon recover from these causes of impairments.
Dealing With Heterogeneous 3D MR Knee Images: A Federated Few-Shot Learning Method With Dual Knowledge Distillation
The supervised learning of the proposed method extracts features from limited labeled data in each client, while the unsupervised data is used to distill both feature and response-based knowledge from a national data repository to further improve the accuracy of the collaborative model and reduce the communication cost.
Improving Generalization with Domain Convex Game
A classical solution to DG is domain augmentation, the common belief of which is that diversifying source domains will be conducive to the out-of-distribution generalization.
Steering Prototypes with Prompt-tuning for Rehearsal-free Continual Learning
In the context of continual learning, prototypes-as representative class embeddings-offer advantages in memory conservation and the mitigation of catastrophic forgetting.
Biomedical image analysis competitions: The state of current participation practice
Of these, 84% were based on standard architectures.
You Only Search Once: On Lightweight Differentiable Architecture Search for Resource-Constrained Embedded Platforms
Benefiting from the search efficiency, differentiable neural architecture search (NAS) has evolved as the most dominant alternative to automatically design competitive deep neural networks (DNNs).
Accurate RNA 3D structure prediction using a language model-based deep learning approach
Accurate prediction of RNA three-dimensional (3D) structure remains an unsolved challenge.
DeepRecon: Joint 2D Cardiac Segmentation and 3D Volume Reconstruction via A Structure-Specific Generative Method
Joint 2D cardiac segmentation and 3D volume reconstruction are fundamental to building statistical cardiac anatomy models and understanding functional mechanisms from motion patterns.
Multi-scale frequency separation network for image deblurring
MSFS-Net introduces the frequency separation module (FSM) into an encoder-decoder network architecture to capture the low- and high-frequency information of image at multiple scales.
Causality Inspired Representation Learning for Domain Generalization
Specifically, we assume that each input is constructed from a mix of causal factors (whose relationship with the label is invariant across domains) and non-causal factors (category-independent), and only the former cause the classification judgments.
TransFusion: Multi-view Divergent Fusion for Medical Image Segmentation with Transformers
Combining information from multi-view images is crucial to improve the performance and robustness of automated methods for disease diagnosis.
Region Proposal Rectification Towards Robust Instance Segmentation of Biological Images
Top-down instance segmentation framework has shown its superiority in object detection compared to the bottom-up framework.
A Data-scalable Transformer for Medical Image Segmentation: Architecture, Model Efficiency, and Benchmark
Transformers have demonstrated remarkable performance in natural language processing and computer vision.
Improving Robustness of Convolutional Neural Networks Using Element-Wise Activation Scaling
Recent works reveal that re-calibrating the intermediate activation of adversarial examples can improve the adversarial robustness of a CNN model.
FAT: An In-Memory Accelerator with Fast Addition for Ternary Weight Neural Networks
Quantization is applied to reduce the latency and storage cost of CNNs.
Pareto Domain Adaptation
Domain adaptation (DA) attempts to transfer the knowledge from a labeled source domain to an unlabeled target domain that follows different distribution from the source.
Incentive Compatible Pareto Alignment for Multi-Source Large Graphs
Challenges of the problem include 1) how to align large-scale entities between sources to share information and 2) how to mitigate negative transfer from joint learning multi-source data.
Scalable Multi-Agent Reinforcement Learning for Residential Load Scheduling under Data Governance
As a data-driven approach, multi-agent reinforcement learning (MARL) has made remarkable advances in solving cooperative residential load scheduling problems.
HSCoNAS: Hardware-Software Co-Design of Efficient DNNs via Neural Architecture Search
In this paper, we present a novel multi-objective hardware-aware neural architecture search (NAS) framework, namely HSCoNAS, to automate the design of deep neural networks (DNNs) with high accuracy but low latency upon target hardware.
Hardware Aware Neural Architecture Search
Neural Architecture Search
Narrow inhomogeneous distribution of spin-active emitters in silicon carbide
Optically active solid-state spin registers have demonstrated their unique potential in quantum computing, communication and sensing.
Quantum Physics Optics
A zero density estimate and fractional imaginary parts of zeros for $\mathrm{GL}_2$ $L$-functions
We prove an analogue of Selberg's zero density estimate for $\zeta(s)$ that holds for any $\mathrm{GL}_2$ $L$-function.
Number Theory
Forbidden Dark Matter Annihilations into Standard Model Particles
We present kinematically forbidden dark matter annihilations into Standard Model leptons.
High Energy Physics - Phenomenology
Bringing AI To Edge: From Deep Learning's Perspective
To bridge the gap, a plethora of deep learning techniques and optimization methods are proposed in the past years: light-weight deep learning models, network compression, and efficient neural architecture search.
Identifying Transition States of Chemical Kinetic Systems using Network Embedding Techniques
Using random walk sampling methods for feature learning on networks, we develop a method for generating low-dimensional node embeddings for directed graphs and identifying transition states of stochastic chemical reacting systems.
The Function Transformation Omics - Funomics
Function transformation, such as f(x, y) and f(x, y, z), can transform two, three, or multiple input/observation variables (in biology, it generally refers to the observed/measured value of biomarkers, biological characteristics, or other indicators) into a new output variable (new characteristics or indicators).
