Search Results for author:
Found 53 papers, 22 papers with code
Closed-Loop Open-Vocabulary Mobile Manipulation with GPT-4V
Autonomous robot navigation and manipulation in open environments require reasoning and replanning with closed-loop feedback.
Scaling Up Dynamic Human-Scene Interaction Modeling
Confronting the challenges of data scarcity and advanced motion synthesis in human-scene interaction modeling, we introduce the TRUMANS dataset alongside a novel HSI motion synthesis method.
MetaScript: Few-Shot Handwritten Chinese Content Generation via Generative Adversarial Networks
In this work, we propose MetaScript, a novel Chinese content generation system designed to address the diminishing presence of personal handwriting styles in the digital representation of Chinese characters.
Test-Time Augmentation for 3D Point Cloud Classification and Segmentation
We are inspired by the recent revolution of learning implicit representation and point cloud upsampling, which can produce high-quality 3D surface reconstruction and proximity-to-surface, respectively.
DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
The ML community is rapidly exploring techniques for prompting language models (LMs) and for stacking them into pipelines that solve complex tasks.
GelFlow: Self-supervised Learning of Optical Flow for Vision-Based Tactile Sensor Displacement Measurement
However, these methods need to be more precise for accurately measuring the displacement of markers during large elastic deformation of the gel, as this can significantly impact the accuracy of downstream tasks.
Incorporating Pre-trained Model Prompting in Multimodal Stock Volume Movement Prediction
Existing multimodal works that train models from scratch face the problem of lacking universal knowledge when modeling financial news.
Continuous Layout Editing of Single Images with Diffusion Models
However, none of these methods have been able to edit the layout of single existing images.
TransAct: Transformer-based Realtime User Action Model for Recommendation at Pinterest
This paper (1) presents Pinterest's ranking architecture for Homefeed, our personalized recommendation product and the largest engagement surface; (2) proposes TransAct, a sequential model that extracts users' short-term preferences from their realtime activities; (3) describes our hybrid approach to ranking, which combines end-to-end sequential modeling via TransAct with batch-generated user embeddings.
Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or Bias
To settle this issue, we propose the Fine-purifying approach, which utilizes the diffusion theory to study the dynamic process of fine-tuning for finding potentially poisonous dimensions.
Full-Body Articulated Human-Object Interaction
By learning the geometrical relationships in HOI, we devise the very first model that leverage human pose estimation to tackle the estimation of articulated object poses and shapes during whole-body interactions.
Learning a Task-specific Descriptor for Robust Matching of 3D Point Clouds
In this paper, we propose to learn a robust task-specific feature descriptor to consistently describe the correct point correspondence under interference.
Searching Dense Point Correspondences via Permutation Matrix Learning
In response, this paper presents a novel end-to-end learning-based method to estimate the dense correspondence of 3D point clouds, in which the problem of point matching is formulated as a zero-one assignment problem to achieve a permutation matching matrix to implement the one-to-one principle fundamentally.
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models
In this work, we take the first step to exploit the pre-trained (unfine-tuned) weights to mitigate backdoors in fine-tuned language models.
Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks
In this work, we take the first step to investigate the unconcealment of textual poisoned samples at the intermediate-feature level and propose a feature-based efficient online defense method.
Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation
NLP attacks tend to have small relative backdoor strengths, which may result in the failure of robust federated aggregation methods for NLP attacks.
GA-SAM: Gradient-Strength based Adaptive Sharpness-Aware Minimization for Improved Generalization
It demonstrates that flat minima tend to imply better generalization abilities.
Stock Trading Volume Prediction with Dual-Process Meta-Learning
Our method can model the common pattern behind different stocks with a meta-learner, while modeling the specific pattern for each stock across time spans with stock-dependent parameters.
Distributional Correlation--Aware Knowledge Distillation for Stock Trading Volume Prediction
Traditional knowledge distillation in classification problems transfers the knowledge via class correlations in the soft label produced by teacher models, which are not available in regression problems like stock trading volume prediction.
Context-Aware Video Reconstruction for Rolling Shutter Cameras
Then, a refinement scheme is proposed to guide the GS frame synthesis along with bilateral occlusion masks to produce high-fidelity GS video frames at arbitrary times.
VRNet: Learning the Rectified Virtual Corresponding Points for 3D Point Cloud Registration
3D point cloud registration is fragile to outliers, which are labeled as the points without corresponding points.
A Representation Separation Perspective to Correspondences-free Unsupervised 3D Point Cloud Registration
Existing correspondences-free methods generally learn the holistic representation of the entire point cloud, which is fragile for partial and noisy point clouds.
CVFNet: Real-time 3D Object Detection by Learning Cross View Features
In recent years 3D object detection from LiDAR point clouds has made great progress thanks to the development of deep learning technologies.
RIConv++: Effective Rotation Invariant Convolutions for 3D Point Clouds Deep Learning
3D point clouds deep learning is a promising field of research that allows a neural network to learn features of point clouds directly, making it a robust tool for solving 3D scene understanding tasks.
End-to-end Learning the Partial Permutation Matrix for Robust 3D Point Cloud Registration
Even though considerable progress has been made in deep learning-based 3D point cloud processing, how to obtain accurate correspondences for robust registration remains a major challenge because existing hard assignment methods cannot deal with outliers naturally.
Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning
Recent pretrained language models extend from millions to billions of parameters.
Adversarial Parameter Defense by Multi-Step Risk Minimization
To enhance neural networks, we propose the adversarial parameter defense algorithm that minimizes the average risk of multiple adversarial parameter corruptions.
How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data
In this work, we observe an interesting phenomenon that the variations of parameters are always AWPs when tuning the trained clean model to inject backdoors.
ASAT: Adaptively Scaled Adversarial Training in Time Series
Besides the security concerns of potential adversarial examples, adversarial training can also improve the generalization ability of neural networks, train robust neural networks, and provide interpretability for neural networks.
Neural Network Surgery: Injecting Data Patterns into Pre-trained Models with Minimal Instance-wise Side Effects
Motivated by neuroscientific evidence and theoretical results, we demonstrate that side effects can be controlled by the number of changed parameters and thus, we propose to conduct \textit{neural network surgery} by only modifying a limited number of parameters.
Rethinking Skip Connection with Layer Normalization in Transformers and ResNets
In this work, we investigate how the scale factors in the effectiveness of the skip connection and reveal that a trivial adjustment of the scale will lead to spurious gradient exploding or vanishing in line with the deepness of the models, which could be addressed by normalization, in particular, layer normalization, which induces consistent improvements over the plain skip connection.
Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models
However, in this paper, we find that it is possible to hack the model in a data-free way by modifying one single word embedding vector, with almost no accuracy sacrificed on clean samples.
Spatial Structure Engineering in Enhancing Performance of Mosaic Electrocatalysts
Understanding the mechanism and developing strategies toward efficient electrocatalysis at gas-liquidsolid interfaces are important yet challenging.
Applied Physics Materials Science
Learning Robust Representation for Clustering through Locality Preserving Variational Discriminative Network
Recent deep learning based methods focus on learning clustering oriented representations.
Rethinking Skip Connection with Layer Normalization
In this work, we investigate how the scale factors in the effectiveness of the skip connection and reveal that a trivial adjustment of the scale will lead to spurious gradient exploding or vanishing in line with the deepness of the models, which could by addressed by normalization, in particular, layer normalization, which induces consistent improvements over the plain skip connection.
RRCN: A Reinforced Random Convolutional Network based Reciprocal Recommendation Approach for Online Dating
In particular, we technically propose a novel random CNN component that can randomly convolute non-adjacent features to capture their interaction information and learn feature embeddings of key attributes to make the final recommendation.
Pretrain-KGE: Learning Knowledge Representation from Pretrained Language Models
Conventional knowledge graph embedding (KGE) often suffers from limited knowledge representation, leading to performance degradation especially on the low-resource problem.
Global Context Aware Convolutions for 3D Point Cloud Understanding
We found that a key reason is that compared to point coordinates, rotation-invariant features consumed by point cloud convolution are not as distinctive.
Shop The Look: Building a Large Scale Visual Shopping System at Pinterest
As online content becomes ever more visual, the demand for searching by visual queries grows correspondingly stronger.
Is the Skip Connection Provable to Reform the Neural Network Loss Landscape?
In this paper, we follow this line to study the topology (sub-level sets) of the loss landscape of deep ReLU neural networks with a skip connection and theoretically prove that the skip connection network inherits the good properties of the two-layer network and skip connections can help to control the connectedness of the sub-level sets, such that any local minima worse than the global minima of some two-layer ReLU network will be very ``shallow".
Exploring the Vulnerability of Deep Neural Networks: A Study of Parameter Corruption
We argue that the vulnerability of model parameters is of crucial value to the study of model robustness and generalization but little research has been devoted to understanding this matter.
Explicit Sparse Transformer: Concentrated Attention Through Explicit Selection
Self-attention based Transformer has demonstrated the state-of-the-art performances in a number of natural language processing tasks.
Pretrain-KGEs: Learning Knowledge Representation from Pretrained Models for Knowledge Graph Embeddings
Learning knowledge graph embeddings (KGEs) is an efficient approach to knowledge graph completion.
MUSE: Parallel Multi-Scale Attention for Sequence to Sequence Learning
In this work, we explore parallel multi-scale representation learning on sequence data, striving to capture both long-range and short-range language structures.
Ranked #8 on
Machine Translation
on WMT2014 English-French
Understanding and Improving Layer Normalization
Unlike them, we find that the derivatives of the mean and variance are more important than forward normalization by re-centering and re-scaling backward gradients.
Ranked #5 on
Machine Translation
on IWSLT2015 English-Vietnamese
Sparse Transformer: Concentrated Attention Through Explicit Selection
Extensive experimental results on a series of natural language processing tasks, including neural machine translation, image captioning, and language modeling, all demonstrate the advantages of Sparse Transformer in model performance.
ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statistics
Deep learning with 3D data has progressed significantly since the introduction of convolutional neural networks that can handle point order ambiguity in point cloud data.
Ranked #8 on
3D Semantic Segmentation
on DALES
Rotation Invariant Convolutions for 3D Point Clouds Deep Learning
Our core idea is to use low-level rotation invariant geometric features such as distances and angles to design a convolution operator for point cloud learning.
PKUSEG: A Toolkit for Multi-Domain Chinese Word Segmentation
Through this method, we generate synthetic data using a large amount of unlabeled data in the target domain and then obtain a word segmentation model for the target domain.
Memorized Sparse Backpropagation
Neural network learning is usually time-consuming since backpropagation needs to compute full gradients and backpropagate them across multiple layers.
Primal Meaning Recommendation via On-line Encyclopedia
We define the primal meaning of an expression to be a frequently used sense of that expression from which its other frequent senses can be deduced.
Automatic Translating between Ancient Chinese and Contemporary Chinese with Limited Aligned Corpora
In this paper, we propose to build an end-to-end neural model to automatically translate between ancient and contemporary Chinese.
Building an Ellipsis-aware Chinese Dependency Treebank for Web Text
Web 2. 0 has brought with it numerous user-produced data revealing one's thoughts, experiences, and knowledge, which are a great source for many tasks, such as information extraction, and knowledge base construction.
