Search Results for author:
Found 36 papers, 13 papers with code
DuSQL: A Large-Scale and Pragmatic Chinese Text-to-SQL Dataset
This paper describes in detail the construction process and data statistics of DuSQL.
KAT-V1: Kwai-AutoThink Technical Report
We present Kwaipilot-AutoThink (KAT), an open-source 40B large language model developed to address the overthinking problem in reasoning-intensive tasks, where an automatic thinking training paradigm is proposed to dynamically switch between reasoning and non-reasoning modes based on task complexity.
FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency Consistency
To effectively exploit temporal information in robotic manipulation, we propose FreqPolicy, a novel approach that first imposes frequency consistency constraints on flow-based visuomotor policies.
HACTS: a Human-As-Copilot Teleoperation System for Robot Learning
Teleoperation is essential for autonomous robot learning, especially in manipulation tasks that require human demonstrations or corrections.
Stabilization Analysis and Mode Recognition of Kerosene Supersonic Combustion: A Deep Learning Approach Based on Res-CNN-beta-VAE
The scramjet engine is a key propulsion system for hypersonic vehicles, leveraging supersonic airflow to achieve high specific impulse, making it a promising technology for aerospace applications.
ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning
Motivated by the theoretical analysis, we propose a novel algorithm, ACL-QL, which uses two learnable adaptive weight functions to control the conservative level over each transition.
RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation
To the best of our knowledge, RoboMIND is the largest multi-embodiment teleoperation dataset collected on a unified platform, providing large-scale and high-quality robotic training data.
Code generation and runtime techniques for enabling data-efficient deep learning training on GPUs
Together, these contributions show that code generation and runtime techniques can systematically mitigate the data management bottlenecks in deep learning training, which stem from the data-intensive nature of workloads and the oversimplification inherent in the deep learning training software stack.
TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation
Vision-Language-Action (VLA) models have shown remarkable potential in visuomotor control and instruction comprehension through end-to-end learning processes.
Mamba Policy: Towards Efficient 3D Diffusion Policy with Hybrid Selective State Models
Diffusion models have been widely employed in the field of 3D manipulation due to their efficient capability to learn distributions, allowing for precise prediction of action trajectories.
SSDTrain: An Activation Offloading Framework to SSDs for Faster Large Language Model Training
Results demonstrate that SSDTrain reduces 47% of the activation peak memory usage.
LSM-GNN: Large-scale Storage-based Multi-GPU GNN Training by Optimizing Data Transfer Scheme
Graph Neural Networks (GNNs) are widely used today in recommendation systems, fraud detection, and node/link classification tasks.
Lifelong Histopathology Whole Slide Image Retrieval via Distance Consistency Rehearsal
Content-based histopathological image retrieval (CBHIR) has gained attention in recent years, offering the capability to return histopathology images that are content-wise similar to the query one from an established database.
Pan-cancer Histopathology WSI Pre-training with Position-aware Masked Autoencoder
The results have demonstrated the effectiveness and generalization of PAMA in discriminative WSI representation learning and pan-cancer WSI pre-training.
TransMA: an explainable multi-modal deep learning model for predicting properties of ionizable lipid nanoparticles in mRNA delivery
We design the mol-attention mechanism block, enabling it to align coarse and fine-grained atomic features and captures relationships between atomic spatial and sequential structures.
Unsupervised Domain Adaptation for Brain Vessel Segmentation through Transwarp Contrastive Learning
Unsupervised domain adaptation (UDA) aims to align the labelled source distribution with the unlabelled target distribution to obtain domain-invariant predictive models.
SoMeLVLM: A Large Vision Language Model for Social Media Processing
The powerful Large Vision Language Models make it possible to handle a variety of tasks simultaneously, but even with carefully designed prompting methods, the general domain models often fall short in aligning with the unique speaking style and context of social media tasks.
Efficient Training of Generalizable Visuomotor Policies via Control-Aware Augmentation
Improving generalization is one key challenge in embodied AI, where obtaining large-scale datasets across diverse scenarios is costly.
Learning from Imperfect Demonstrations with Self-Supervision for Robotic Manipulation
High-quality segments from the failed data are used to expand the training dataset.
Multi-Clue Reasoning with Memory Augmentation for Knowledge-based Visual Question Answering
Visual Question Answering (VQA) has emerged as one of the most challenging tasks in artificial intelligence due to its multi-modal nature.
Cross-Modal Reasoning with Event Correlation for Video Question Answering
Video Question Answering (VideoQA) is a very attractive and challenging research direction aiming to understand complex semantics of heterogeneous data from two domains, i. e., the spatio-temporal video content and the word sequence in question.
Hector: An Efficient Programming and Compilation Framework for Implementing Relational Graph Neural Networks in GPU Architectures
Relational graph neural networks (RGNNs) are graph neural networks with dedicated structures for modeling the different types of nodes and edges in heterogeneous graphs.
Continual Few-Shot Learning with Adversarial Class Storage
In this paper, we define a new problem called continual few-shot learning, in which tasks arrive sequentially and each task is associated with a few training samples.
Lesion-Aware Contrastive Representation Learning for Histopathology Whole Slide Images Analysis
In this paper, we proposed a novel contrastive representation learning framework named Lesion-Aware Contrastive Learning (LACL) for histopathology whole slide image analysis.
Faster and Better Grammar-based Text-to-SQL Parsing via Clause-level Parallel Decoding and Alignment Loss
Grammar-based parsers have achieved high performance in the cross-domain text-to-SQL parsing task, but suffer from low decoding efficiency due to the much larger number of actions for grammar selection than that of tokens in SQL queries.
CADRE: A Cascade Deep Reinforcement Learning Framework for Vision-based Autonomous Urban Driving
Vision-based autonomous urban driving in dense traffic is quite challenging due to the complicated urban environment and the dynamics of the driving behaviors.
A GAN-based Denoising Method for Chinese Stele and Rubbing Calligraphic Image
By introducing an attention mechanism, we use a recurrent network with multiple progressive network units to generate a noise attention map.
Graph Neural Network Training with Data Tiering
With our data tiering method, we additionally provide a new data placement and access strategy to further minimize the CPU-GPU communication overhead.
Human Pose Transfer with Augmented Disentangled Feature Consistency
Deep generative models have made great progress in synthesizing images with arbitrary human poses and transferring poses of one person to others.
Large Graph Convolutional Network Training with GPU-Oriented Data Communication Architecture
In this work, we propose a novel GPU-oriented data communication approach for GCN training, where GPU threads directly access sparse features in host memory through zero-copy accesses without much CPU help.
Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-domain Text-to-SQL Parsing
For better distribution matching, we require that at least 80% of SQL patterns in the training data are covered by generated queries.
PyTorch-Direct: Enabling GPU Centric Data Access for Very Large Graph Neural Network Training with Irregular Accesses
While this process accounts for a significant portion of the training time, we find existing GNN implementations using popular deep neural network (DNN) libraries such as PyTorch are limited to a CPU-centric approach for the entire data preparation step.
Hierarchical Graph Attention Network for Few-Shot Visual-Semantic Learning
Deep learning has made tremendous success in computer vision, natural language processing and even visual-semantic learning, which requires a huge amount of labeled training data.
TEMPI: An Interposed MPI Library with a Canonical Representation of CUDA-aware Datatypes
MPI derived datatypes are an abstraction that simplifies handling of non-contiguous data in MPI applications.
Distributed, Parallel, and Cluster Computing
Knowledge Transfer in Multi-Task Deep Reinforcement Learning for Continuous Control
While Deep Reinforcement Learning (DRL) has emerged as a promising approach to many complex tasks, it remains challenging to train a single DRL agent that is capable of undertaking multiple different continuous control tasks.
On Batch Adaptive Training for Deep Learning: Lower Loss and Larger Step Size
Mini-batch gradient descent and its variants are commonly used in deep learning.
