Search Results for author:
Found 184 papers, 70 papers with code
PGL at TextGraphs 2020 Shared Task: Explanation Regeneration using Language and Graph Learning Methods
To address this problem, we use a pre-trained language model to recall the top-K relevant explanations for each question.
CVAE-based Re-anchoring for Implicit Discourse Relation Classification
Training implicit discourse relation classifiers suffers from data sparsity.
Test-Time Training for Generalization under Distribution Shifts
We introduce a general approach, called test-time training, for improving the performance of predictive models when training and test data come from different distributions.
An LLM-Driven Multi-Agent Debate System for Mendelian Diseases
Accurate diagnosis of Mendelian diseases is crucial for precision therapy and assistance in preimplantation genetic diagnosis.
One-Minute Video Generation with Test-Time Training
We have only experimented with one-minute videos due to resource constraints, but the approach can be extended to longer videos and more complex stories.
Audio-Enhanced Vision-Language Modeling with Latent Space Broadening for High Quality Data Expansion
Transformer-based multimodal models are widely used in industrial-scale recommendation, search, and advertising systems for content understanding and relevance ranking.
InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical Sciences
Plug-and-play diffusion priors (PnPDP) have emerged as a promising research direction for solving inverse problems.
STAR: A Foundation Model-driven Framework for Robust Task Planning and Failure Recovery in Robotic Systems
To address this, we propose STAR (Smart Task Adaptation and Recovery), a novel framework that synergizes Foundation Models (FMs) with dynamically expanding Knowledge Graphs (KGs) to enable resilient task planning and autonomous failure recovery.
Large-Scale AI in Telecom: Charting the Roadmap for Innovation, Scalability, and Enhanced Digital Experiences
This white paper discusses the role of large-scale AI in the telecommunications industry, with a specific focus on the potential of generative AI to revolutionize network functions and user experiences, especially in the context of 6G systems.
Large AI Model for Delay-Doppler Domain Channel Prediction in 6G OTFS-Based Vehicular Networks
Channel prediction is crucial for high-mobility vehicular networks, as it enables the anticipation of future channel conditions and the proactive adjustment of communication strategies.
BeamLoRA: Beam-Constraint Low-Rank Adaptation
Due to the demand for efficient fine-tuning of large language models, Low-Rank Adaptation (LoRA) has been widely adopted as one of the most effective parameter-efficient fine-tuning methods.
Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking
Large language models (LLMs) face inherent performance bottlenecks under parameter constraints, particularly in processing critical tokens that demand complex reasoning.
Proxy Prompt: Endowing SAM and SAM 2 with Auto-Interactive-Prompt for Medical Segmentation
In this paper, we aim to address the unmet demand for automated prompting and enhanced human-model interactions of SAM and SAM2 for the sake of promoting their widespread clinical adoption.
Curiosity-Driven Reinforcement Learning from Human Feedback
Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models (LLMs) with human preferences, but often at the cost of reduced output diversity.
A new perspective on brain stimulation interventions: Optimal stochastic tracking control of brain network dynamics
Results show that the energy associated with optimal stochastic tracking control is negatively correlated with the intrinsic average controllability of the brain network system, while the energy of the optimal state approaching control is significantly related to the target state value.
Graph Structure Learning for Spatial-Temporal Imputation: Adapting to Node and Feature Scales
Spatial-temporal data collected across different geographic locations often suffer from missing values, posing challenges to data analysis.
PrisonBreak: Jailbreaking Large Language Models with Fewer Than Twenty-Five Targeted Bit-flips
We show that our attack can reliably induce jailbreaking in systems similar to those affected by prior bit-flip attacks.
Mixture of Hidden-Dimensions Transformer
MOHD offers a new perspective for scaling the model, showcasing the potential of hidden dimension sparsity to boost efficiency
Photoacoustic Iterative Optimization Algorithm with Shape Prior Regularization
The shape prior is a probability matrix derived from the reconstruction results of multiple sets of random partial array signals in a computational imaging system using any reconstruction algorithm, such as Delay-and-Sum (DAS) and Back-Projection (BP).
Visual-Linguistic Agent: Towards Collaborative Contextual Object Reasoning
The Linguistic Agent evaluates and refines detections by reasoning over spatial and contextual relationships among objects, while the classification Vision Agent offers corrective feedback to improve classification accuracy.
MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions
However, token-level RLHF suffers from the credit assignment problem over long sequences, where delayed rewards make it challenging for the model to discern which actions contributed to successful outcomes.
Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging
To ensure that each specialized expert in the MoE model works as expected, we select a small amount of seed data that each expert excels to pre-optimize the router.
Orthogonal Finetuning for Direct Preference Optimization
Hence, we introduce orthogonal finetuning for DPO via a weight-Rotated Preference Optimization (RoPO) method, which merely conducts rotational and magnitude-stretching updates on the weight parameters to maintain the hyperspherical energy invariant, thereby preserving the knowledge encoded in the angle between neurons.
Sequence-aware Pre-training for Echocardiography Probe Guidance
Specifically, our approach learns personalized 2D and 3D cardiac structural features by predicting the masked-out images and actions in a scanning sequence.
NACL: A General and Effective KV Cache Eviction Framework for LLMs at Inference Time
Large Language Models (LLMs) have ignited an innovative surge of AI applications, marking a new era of exciting possibilities equipped with extended context windows.
Automated Sperm Morphology Analysis Based on Instance-Aware Part Segmentation
Automated morphology analysis of a high number of sperm requires accurate segmentation of each sperm part and quantitative morphology evaluation.
Spatial-Temporal Attention Model for Traffic State Estimation with Sparse Internet of Vehicles
The growing number of connected vehicles offers an opportunity to leverage internet of vehicles (IoV) data for traffic state estimation (TSE) which plays a crucial role in intelligent transportation systems (ITS).
Structure-aware World Model for Probe Guidance via Large-scale Self-supervised Pre-train
The complex structure of the heart leads to significant challenges in echocardiography, especially in acquisition cardiac ultrasound images.
Cardiac Copilot: Automatic Probe Guidance for Echocardiography with World Model
However, there is a severe shortage of experienced cardiac sonographers, due to the heart's complex structure and significant operational challenges.
DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion
Large language models (LLMs) with billions of parameters demonstrate impressive performance.
Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priors
Diffusion models (DMs) have recently shown outstanding capabilities in modeling complex image distributions, making them expressive image priors for solving Bayesian inverse problems.
DocReLM: Mastering Document Retrieval with Language Model
With over 200 million published academic documents and millions of new documents being written each year, academic researchers face the challenge of searching for information within this vast corpus.
HFT: Half Fine-Tuning for Large Language Models
Large language models (LLMs) with one or more fine-tuning phases have become a necessary step to unlock various capabilities, enabling LLMs to follow natural language instructions or align with human preferences.
TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation
We address the problem of regressing 3D human pose and shape from a single image, with a focus on 3D accuracy.
Ranked #35 on
3D Human Pose Estimation
on 3DPW
Autoregressive Pre-Training on Pixels and Texts
Our extensive evaluation across a wide range of benchmarks shows that incorporating both visual and textual data significantly improves the performance of pixel-based language models.
On Training Data Influence of GPT Models
This paper presents GPTfluence, a novel approach that leverages a featurized simulation to assess the impact of training examples on the training dynamics of GPT models.
Counting Objects in a Robotic Hand
A robot performing multi-object grasping needs to sense the number of objects in the hand after grasping.
InternLM2 Technical Report
The evolution of Large Language Models (LLMs) like ChatGPT and GPT-4 has sparked discussions on the advent of Artificial General Intelligence (AGI).
Ranked #5 on
Long-Context Understanding
on Ada-LEval (BestAnswer)
LOCR: Location-Guided Transformer for Optical Character Recognition
Academic documents are packed with texts, equations, tables, and figures, requiring comprehensive understanding for accurate Optical Character Recognition (OCR).
F-Eval: Assessing Fundamental Abilities with Refined Evaluation Methods
However, these evaluation benchmarks are limited to assessing the instruction-following capabilities, overlooking the fundamental abilities that emerge during the pre-training stage.
GI-PIP: Do We Require Impractical Auxiliary Dataset for Gradient Inversion Attacks?
Deep gradient inversion attacks expose a serious threat to Federated Learning (FL) by accurately recovering private data from shared gradients.
Consolidating Trees of Robotic Plans Generated Using Large Language Models to Improve Reliability
Leveraging GPT-4 further, the high-level task plan is converted into a low-level Planning Domain Definition Language (PDDL) plan executable by a robot.
CoLLiE: Collaborative Training of Large Language Models in an Efficient Way
This paper introduces CoLLiE, an efficient library that facilitates collaborative training of large language models using 3D parallelism, parameter-efficient fine-tuning (PEFT) methods, and optimizers such as Lion, Adan, Sophia, LOMO and AdaLomo.
ChatPose: Chatting about 3D Human Pose
Additionally, ChatPose empowers LLMs to apply their extensive world knowledge in reasoning about human poses, leading to two advanced tasks: speculative pose generation and reasoning about pose estimation.
Learning to (Learn at Test Time)
Our inner loop turns out to be equivalent to linear attention when the inner-loop learner is only a linear model, and to self-attention when it is a kernel estimator.
Provable Probabilistic Imaging using Score-Based Generative Priors
PMC is able to incorporate expressive score-based generative priors for high-quality image reconstruction while also performing uncertainty quantification via posterior sampling.
Tool-Augmented Reward Modeling
We validate our approach across a wide range of domains, incorporating seven distinct external tools.
From Cooking Recipes to Robot Task Trees -- Improving Planning Correctness and Task Efficiency by Leveraging LLMs with a Knowledge Network
Task planning for robotic cooking involves generating a sequence of actions for a robot to prepare a meal successfully.
ActionPrompt: Action-Guided 3D Human Pose Estimation With Text and Pose Prompting
Recent 2D-to-3D human pose estimation (HPE) utilizes temporal consistency across sequences to alleviate the depth ambiguity problem but ignore the action related prior knowledge hidden in the pose sequence.
Test-Time Training on Video Streams
Before making a prediction on each test instance, the model is first trained on the same instance using a self-supervised task such as reconstruction.
TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environments
Although the estimation of 3D human pose and shape (HPS) is rapidly progressing, current methods still cannot reliably estimate moving humans in global coordinates, which is critical for many applications.
Ranked #58 on
3D Human Pose Estimation
on 3DPW
Spectral Heterogeneous Graph Convolutions via Positive Noncommutative Polynomials
Furthermore, these methods cannot learn arbitrary valid heterogeneous graph filters within the spectral domain, which have limited expressiveness.
Ranked #6 on
Node Property Prediction
on ogbn-mag
Test-Time Training on Nearest Neighbors for Large Language Models
Surprisingly, retrieving and training on as few as 20 neighbors, each for only one gradient iteration, drastically improves performance across more than 20 language modeling tasks in the Pile.
Ranked #20 on
Language Modelling
on The Pile
Learning Task-Specific Strategies for Accelerated MRI
Traditional CS-MRI methods often separately address measurement subsampling, image reconstruction, and task prediction, resulting in a suboptimal end-to-end performance.
Label Information Enhanced Fraud Detection against Low Homophily in Graphs
Then, we combine the group aggregation and the learnable encodings into a Transformer encoder to capture the semantic information.
Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimation
There has been a recent surge of interest in introducing transformers to 3D human pose estimation (HPE) due to their powerful capabilities in modeling long-term dependencies.
ERNIE-Music: Text-to-Waveform Music Generation with Diffusion Models
In response to this lacuna, this paper introduces a pioneering contribution in the form of a text-to-waveform music generation model, underpinned by the utilization of diffusion models.
Instance-wise Batch Label Restoration via Gradients in Federated Learning
Furthermore, we demonstrate that our method facilitates the existing gradient inversion attacks by exploiting the recovered labels, with an increase of 6-7 in PSNR on both MNIST and CIFAR100.
ERNIE 3.0 Tiny: Frustratingly Simple Method to Improve Task-Agnostic Distillation Generalization
Experimental results demonstrate that our method yields a student with much better generalization, significantly outperforms existing baselines, and establishes a new state-of-the-art result on in-domain, out-domain, and low-resource datasets in the setting of task-agnostic distillation.
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.
ERNIE-Code: Beyond English-Centric Cross-lingual Pretraining for Programming Languages
Extensive results show that ERNIE-Code outperforms previous multilingual LLMs for PL or NL across a wide range of end tasks of code intelligence, including multilingual code-to-text, text-to-code, code-to-code, and text-to-text generation.
X-PuDu at SemEval-2022 Task 6: Multilingual Learning for English and Arabic Sarcasm Detection
Detecting sarcasm and verbal irony from people's subjective statements is crucial to understanding their intended meanings and real sentiments and positions in social scenarios.
X-PuDu at SemEval-2022 Task 7: A Replaced Token Detection Task Pre-trained Model with Pattern-aware Ensembling for Identifying Plausible Clarifications
This paper describes our winning system on SemEval 2022 Task 7: Identifying Plausible Clarifications of Implicit and Underspecified Phrases in Instructional Texts.
Coordinate-Based Seismic Interpolation in Irregular Land Survey: A Deep Internal Learning Approach
Physical and budget constraints often result in irregular sampling, which complicates accurate subsurface imaging.
ERNIE-UniX2: A Unified Cross-lingual Cross-modal Framework for Understanding and Generation
Recent cross-lingual cross-modal works attempt to extend Vision-Language Pre-training (VLP) models to non-English inputs and achieve impressive performance.
Ranked #1 on
Multimodal Machine Translation
on Multi30K
ERNIE-SAT: Speech and Text Joint Pretraining for Cross-Lingual Multi-Speaker Text-to-Speech
In this paper, we extend the pretraining method for cross-lingual multi-speaker speech synthesis tasks, including cross-lingual multi-speaker voice cloning and cross-lingual multi-speaker speech editing.
SDCL: Self-Distillation Contrastive Learning for Chinese Spell Checking
To adapt BERT to the CSC task, we propose a token-level self-distillation contrastive learning method.
ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model with Knowledge-Enhanced Mixture-of-Denoising-Experts
Recent progress in diffusion models has revolutionized the popular technology of text-to-image generation.
Ranked #12 on
Text-to-Image Generation
on MS COCO
Clip-Tuning: Towards Derivative-free Prompt Learning with a Mixture of Rewards
Derivative-free prompt learning has emerged as a lightweight alternative to prompt tuning, which only requires model inference to optimize the prompts.
CPS-MEBR: Click Feedback-Aware Web Page Summarization for Multi-Embedding-Based Retrieval
Meanwhile, we introduce sentence-level semantic interaction to design a multi-embedding-based retrieval (MEBR) model, which can generate multiple embeddings to deal with different potential queries by using frequently clicked sentences in web pages.
ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding
Recent years have witnessed the rise and success of pre-training techniques in visually-rich document understanding.
Ranked #2 on
Semantic entity labeling
on FUNSD
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training
They attempt to learn cross-modal representation using contrastive learning on image-text pairs, however, the built inter-modal correlations only rely on a single view for each modality.
Ranked #1 on
Image Retrieval
on AIC-ICC
ERNIE-mmLayout: Multi-grained MultiModal Transformer for Document Understanding
At first, a document graph is proposed to model complex relationships among multi-grained multimodal elements, in which salient visual regions are detected by a cluster-based method.
Test-Time Training with Masked Autoencoders
Test-time training adapts to a new test distribution on the fly by optimizing a model for each test input using self-supervision.
WOC: A Handy Webcam-based 3D Online Chatroom
We develop WOC, a webcam-based 3D virtual online chatroom for multi-person interaction, which captures the 3D motion of users and drives their individual 3D virtual avatars in real-time.
An Embarrassingly Easy but Strong Baseline for Nested Named Entity Recognition
In this paper, we propose using Convolutional Neural Network (CNN) to model these spatial relations in the score matrix.
Ranked #3 on
Nested Named Entity Recognition
on ACE 2005
A General Multiple Data Augmentation Based Framework for Training Deep Neural Networks
Combining multiple DA methods, namely multi-DA, for DNN training, provides a way to boost generalisation.
Nebula-I: A General Framework for Collaboratively Training Deep Learning Models on Low-Bandwidth Cloud Clusters
We took natural language processing (NLP) as an example to show how Nebula-I works in different training phases that include: a) pre-training a multilingual language model using two remote clusters; and b) fine-tuning a machine translation model using knowledge distilled from pre-trained models, which run through the most popular paradigm of recent deep learning.
Simple and Effective Relation-based Embedding Propagation for Knowledge Representation Learning
Notably, it averagely brings about 10% relative improvement to triplet-based embedding methods on OGBL-WikiKG2 and takes 5%-83% time to achieve comparable results as the state-of-the-art GC-OTE.
Robust Neonatal Face Detection in Real-world Clinical Settings
Current face detection algorithms are extremely generalized and can obtain decent accuracy when detecting the adult faces.
ERNIE-SPARSE: Learning Hierarchical Efficient Transformer Through Regularized Self-Attention
We argue that two factors, information bottleneck sensitivity and inconsistency between different attention topologies, could affect the performance of the Sparse Transformer.
Learning Cross-Video Neural Representations for High-Quality Frame Interpolation
This paper considers the problem of temporal video interpolation, where the goal is to synthesize a new video frame given its two neighbors.
Ranked #1 on
Video Frame Interpolation
on Xiph 4k
Graph Neural Networks for Double-Strand DNA Breaks Prediction
Double-strand DNA breaks (DSBs) are a form of DNA damage that can cause abnormal chromosomal rearrangements.
ERNIE-ViLG: Unified Generative Pre-training for Bidirectional Vision-Language Generation
To explore the landscape of large-scale pre-training for bidirectional text-image generation, we train a 10-billion parameter ERNIE-ViLG model on a large-scale dataset of 145 million (Chinese) image-text pairs which achieves state-of-the-art performance for both text-to-image and image-to-text tasks, obtaining an FID of 7. 9 on MS-COCO for text-to-image synthesis and best results on COCO-CN and AIC-ICC for image captioning.
Ranked #41 on
Text-to-Image Generation
on MS COCO
ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation
A unified framework named ERNIE 3. 0 was recently proposed for pre-training large-scale knowledge enhanced models and trained a model with 10 billion parameters.
Putting People in their Place: Monocular Regression of 3D People in Depth
To do so, we exploit a 3D body model space that lets BEV infer shapes from infants to adults.
Ranked #1 on
3D Depth Estimation
on Relative Human
(using extra training data)
Functional Task Tree Generation from a Knowledge Graph to Solve Unseen Problems
To address the problem of producing novel and flexible task plans called task trees, we explore how we can derive plans with concepts not originally in the robot's knowledge base.
Graph4Rec: A Universal Toolkit with Graph Neural Networks for Recommender Systems
In recent years, owing to the outstanding performance in graph representation learning, graph neural network (GNN) techniques have gained considerable interests in many real-world scenarios, such as recommender systems and social networks.
Multi-Object Grasping -- Estimating the Number of Objects in a Robotic Grasp
To do so, a robot needs to grasp within a pile, sense the number of objects in the grasp before lifting, and predict the number of objects that will remain in the grasp after lifting.
Recovery of Continuous 3D Refractive Index Maps from Discrete Intensity-Only Measurements using Neural Fields
The representation in DeCAF is learned directly from the measurements of the test sample by using the IDT forward model, without any ground-truth RI maps.
Hierarchical Graph Networks for 3D Human Pose Estimation
Recent 2D-to-3D human pose estimation works tend to utilize the graph structure formed by the topology of the human skeleton.
Ranked #47 on
3D Human Pose Estimation
on MPI-INF-3DHP
(AUC metric)
ERNIE-SPARSE: Robust Efficient Transformer Through Hierarchically Unifying Isolated Information
The first factor is information bottleneck sensitivity, which is caused by the key feature of Sparse Transformer — only a small number of global tokens can attend to all other tokens.
Pattern Recognition in Vital Signs Using Spectrograms
The results from the proposed approach are promising with an accuracy of 91. 55% and 91. 67% in prediction and classification tasks respectively.
Research Challenges and Progress in Robotic Grasping and Manipulation Competitions
This paper discusses recent research progress in robotic grasping and manipulation in the light of the latest Robotic Grasping and Manipulation Competitions (RGMCs).
Alpha at SemEval-2021 Task 6: Transformer Based Propaganda Classification
This paper describes our system participated in Task 6 of SemEval-2021: the task focuses on multimodal propaganda technique classification and it aims to classify given image and text into 22 classes.
abcbpc at SemEval-2021 Task 7: ERNIE-based Multi-task Model for Detecting and Rating Humor and Offense
This paper describes our system participated in Task 7 of SemEval-2021: Detecting and Rating Humor and Offense.
Deformation-Compensated Learning for Image Reconstruction without Ground Truth
Deep neural networks for medical image reconstruction are traditionally trained using high-quality ground-truth images as training targets.
ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation
We trained the model with 10 billion parameters on a 4TB corpus consisting of plain texts and a large-scale knowledge graph.
ERNIE-Tiny : A Progressive Distillation Framework for Pretrained Transformer Compression
Specifically, the first stage, General Distillation, performs distillation with guidance from pretrained teacher, gerenal data and latent distillation loss.
Parallel sentences mining with transfer learning in an unsupervised setting
In this paper, we propose an approach based on transfer learning to mine parallel sentences in the unsupervised setting. With the help of bilingual corpora of rich-resource language pairs, we can mine parallel sentences without bilingual supervision of low-resource language pairs.
A Road-map to Robot Task Execution with the Functional Object-Oriented Network
Following work on joint object-action representations, the functional object-oriented network (FOON) was introduced as a knowledge graph representation for robots.
Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective
We believe this survey will provide the readers with a deep and insightful understanding of monocular human pose estimation.
CoIL: Coordinate-based Internal Learning for Imaging Inverse Problems
We propose Coordinate-based Internal Learning (CoIL) as a new deep-learning (DL) methodology for the continuous representation of measurements.
SGD-Net: Efficient Model-Based Deep Learning with Theoretical Guarantees
Deep unfolding networks have recently gained popularity in the context of solving imaging inverse problems.
ERNIE-M: Enhanced Multilingual Representation by Aligning Cross-lingual Semantics with Monolingual Corpora
In this paper, we propose ERNIE-M, a new training method that encourages the model to align the representation of multiple languages with monolingual corpora, to overcome the constraint that the parallel corpus size places on the model performance.
Ranked #14 on
Zero-Shot Cross-Lingual Transfer
on XTREME
ERNIE-Doc: A Retrospective Long-Document Modeling Transformer
Transformers are not suited for processing long documents, due to their quadratically increasing memory and time consumption.
Ranked #1000000000 on
Text Classification
on IMDb
Developing Motion Code Embedding for Action Recognition in Videos
In this work, we propose a motion embedding strategy known as motion codes, which is a vectorized representation of motions based on a manipulation's salient mechanical attributes.
Multimodal Spatio-Temporal Deep Learning Approach for Neonatal Postoperative Pain Assessment
We compare the performance of the multimodal and unimodal postoperative pain assessment, and measure the impact of temporal information integration.
Joint Reconstruction and Calibration using Regularization by Denoising
Cal-RED extends the traditional RED methodology to imaging problems that require the calibration of the measurement operator.
Robot Gaining Accurate Pouring Skills through Self-Supervised Learning and Generalization
We have also evaluated the proposed self-supervised generalization approach using unaccustomed containers that are far different from the ones in the training set.
Synthetic Training for Monocular Human Mesh Recovery
To solve this problem, we design a multi-branch framework to disentangle the regression of different body properties, enabling us to separate each component's training in a synthetic training manner using unpaired data available.
ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding
We argue that such contiguously masking method neglects to model the intra-dependencies and inter-relation of coarse-grained linguistic information.
Generalizable and Explainable Dialogue Generation via Explicit Action Learning
To alleviate the need of action annotations, latent action learning is introduced to map each utterance to a latent representation.
Galileo at SemEval-2020 Task 12: Multi-lingual Learning for Offensive Language Identification using Pre-trained Language Models
In Sub-task A - Offensive Language Identification, we ranked first in terms of average F1 scores in all languages.
Async-RED: A Provably Convergent Asynchronous Block Parallel Stochastic Method using Deep Denoising Priors
Regularization by denoising (RED) is a recently developed framework for solving inverse problems by integrating advanced denoisers as image priors.
Deep Image Reconstruction using Unregistered Measurements without Groundtruth
One of the key limitations in conventional deep learning based image reconstruction is the need for registered pairs of training images containing a set of high-quality groundtruth images.
Weakly-Supervised Online Hashing
However, existing hashing methods for social image retrieval are based on batch mode which violates the nature of social images, i. e., social images are usually generated periodically or collected in a stream fashion.
ERNIE at SemEval-2020 Task 10: Learning Word Emphasis Selection by Pre-trained Language Model
This paper describes the system designed by ERNIE Team which achieved the first place in SemEval-2020 Task 10: Emphasis Selection For Written Text in Visual Media.
kk2018 at SemEval-2020 Task 9: Adversarial Training for Code-Mixing Sentiment Classification
Code switching is a linguistic phenomenon that may occur within a multilingual setting where speakers share more than one language.
Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification
Graph neural network (GNN) and label propagation algorithm (LPA) are both message passing algorithms, which have achieved superior performance in semi-supervised classification.
Ranked #1 on
Node Property Prediction
on ogbn-proteins
Monocular, One-stage, Regression of Multiple 3D People
Through a body-center-guided sampling process, the body mesh parameters of all people in the image are easily extracted from the Mesh Parameter map.
Ranked #1 on
3D Multi-Person Mesh Recovery
on Relative Human
(using extra training data)
Estimating Motion Codes from Demonstration Videos
A motion taxonomy can encode manipulations as a binary-encoded representation, which we refer to as motion codes.
A Motion Taxonomy for Manipulation Embedding
To represent motions from a mechanical point of view, this paper explores motion embedding using the motion taxonomy.
Self-Supervised Policy Adaptation during Deployment
A natural solution would be to keep training after deployment in the new environment, but this cannot be done if the new environment offers no reward signal.
ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph
Thus, ERNIE-ViL can learn the joint representations characterizing the alignments of the detailed semantics across vision and language.
Ranked #2 on
Visual Question Answering (VQA)
on VCR (QA-R) test
Scalable Plug-and-Play ADMM with Convergence Guarantees
Plug-and-play priors (PnP) is a broadly applicable methodology for solving inverse problems by exploiting statistical priors specified as denoisers.
Provable Convergence of Plug-and-Play Priors with MMSE denoisers
Plug-and-play priors (PnP) is a methodology for regularized image reconstruction that specifies the prior through an image denoiser.
Semi-Supervised Dialogue Policy Learning via Stochastic Reward Estimation
This approach requires complete state-action annotations of human-to-human dialogues (i. e., expert demonstrations), which is labor intensive.
Learning Individual Models for Imputation (Technical Report)
We propose to adaptively learn individual models over various number l of neighbors for different complete tuples.
First Investigation Into the Use of Deep Learning for Continuous Assessment of Neonatal Postoperative Pain
This paper presents the first investigation into the use of fully automated deep learning framework for assessing neonatal postoperative pain.
ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation
Current pre-training works in natural language generation pay little attention to the problem of exposure bias on downstream tasks.
Ranked #1 on
Question Generation
on SQuAD1.1
(using extra training data)
MALA: Cross-Domain Dialogue Generation with Action Learning
These two components, however, have a discrepancy in their objectives, i. e., task completion and language quality.
Manipulation Motion Taxonomy and Coding for Robots
This paper introduces a taxonomy of manipulations as seen especially in cooking for 1) grouping manipulations from the robotics point of view, 2) consolidating aliases and removing ambiguity for motion types, and 3) provide a path to transferring learned manipulations to new unlearned manipulations.
Test-Time Training with Self-Supervision for Generalization under Distribution Shifts
In this paper, we propose Test-Time Training, a general approach for improving the performance of predictive models when training and test data come from different distributions.
Ranked #34 on
Language Modelling
on LAMBADA
Building change detection for remote sensing images
CARLA MAP Leaderboard
+6
Unsupervised Domain Adaptation through Self-Supervision
This paper addresses unsupervised domain adaptation, the setting where labeled training data is available on a source domain, but the goal is to have good performance on a target domain with only unlabeled data.
Test-Time Training for Out-of-Distribution Generalization
We introduce a general approach, called test-time training, for improving the performance of predictive models when test and training data come from different distributions.
Infusing Learned Priors into Model-Based Multispectral Imaging
We introduce a new algorithm for regularized reconstruction of multispectral (MS) images from noisy linear measurements.
Harnessing the Power of Deep Learning Methods in Healthcare: Neonatal Pain Assessment from Crying Sound
Neonatal pain assessment in clinical environments is challenging as it is discontinuous and biased.
Online Regularization by Denoising with Applications to Phase Retrieval
Regularization by denoising (RED) is a powerful framework for solving imaging inverse problems.
Multi-Channel Neural Network for Assessing Neonatal Pain from Videos
Neonates do not have the ability to either articulate pain or communicate it non-verbally by pointing.
CARL: Aggregated Search with Context-Aware Module Embedding Learning
To model and utilize the context information for aggregated search, we propose a model with context attention and representation learning (CARL).
ERNIE 2.0: A Continual Pre-training Framework for Language Understanding
Recently, pre-trained models have achieved state-of-the-art results in various language understanding tasks, which indicates that pre-training on large-scale corpora may play a crucial role in natural language processing.
Ranked #1 on
Chinese Sentence Pair Classification
on LCQMC Dev
Chinese Named Entity Recognition
Chinese Reading Comprehension
+8
Predicting Different Types of Conversions with Multi-Task Learning in Online Advertising
Conversion prediction plays an important role in online advertising since Cost-Per-Action (CPA) has become one of the primary campaign performance objectives in the industry.
RLTM: An Efficient Neural IR Framework for Long Documents
This paper proposes a novel End-to-End neural ranking framework called Reinforced Long Text Matching (RLTM) which matches a query with long documents efficiently and effectively.
Accurate Robotic Pouring for Serving Drinks
Pouring is the second most frequently executed motion in cooking scenarios.
OleNet at SemEval-2019 Task 9: BERT based Multi-Perspective Models for Suggestion Mining
This paper describes our system partici- pated in Task 9 of SemEval-2019: the task is focused on suggestion mining and it aims to classify given sentences into sug- gestion and non-suggestion classes in do- main specific and cross domain training setting respectively.
Doubly Robust Joint Learning for Recommendation on Data Missing Not at Random
In recommender systems, usually the ratings of a user to most items are missing and a critical problem is that the missing ratings are often missing not at random (MNAR) in reality.
Joint Object and State Recognition using Language Knowledge
The pipeline presented in this paper includes a CNN with a double classification layer and the Concept-Net language knowledge graph on top.
Block Coordinate Regularization by Denoising
In this work, we develop a new block coordinate RED algorithm that decomposes a large-scale estimation problem into a sequence of updates over a small subset of the unknown variables.
Task Planning with a Weighted Functional Object-Oriented Network
The paper also presents a task planning algorithm for the weighted FOON to allocate manipulation action load to the robot and human to achieve optimal performance while minimizing human effort.
ERNIE: Enhanced Representation through Knowledge Integration
We present a novel language representation model enhanced by knowledge called ERNIE (Enhanced Representation through kNowledge IntEgration).
Ranked #3 on
Natural Language Inference
on XNLI Chinese Dev
Chinese Named Entity Recognition
Chinese Sentence Pair Classification
+8
KDGAN: Knowledge Distillation with Generative Adversarial Networks
An alternative method is to adversarially train the classifier against a discriminator in a two-player game akin to generative adversarial networks (GAN), which can ensure the classifier to learn the true data distribution at the equilibrium of this game.
Plug-In Stochastic Gradient Method
Plug-and-play priors (PnP) is a popular framework for regularized signal reconstruction by using advanced denoisers within an iterative algorithm.
Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge
This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i. e., 2012-2018.
Regularized Fourier Ptychography using an Online Plug-and-Play Algorithm
The plug-and-play priors (PnP) framework has been recently shown to achieve state-of-the-art results in regularized image reconstruction by leveraging a sophisticated denoiser within an iterative algorithm.
Image Restoration using Total Variation Regularized Deep Image Prior
In the past decade, sparsity-driven regularization has led to significant improvements in image reconstruction.
An Online Plug-and-Play Algorithm for Regularized Image Reconstruction
The results in this paper have the potential to expand the applicability of the PnP framework to very large and redundant datasets.
SSCU: an R/Bioconductor package for analyzing selective profile in synonymous codon usage
Background Synonymous codon choice is mainly affected by mutation and selection.
Genomics
A Survey of Knowledge Representation in Service Robotics
Within the realm of service robotics, researchers have placed a great amount of effort into learning, understanding, and representing motions as manipulations for task execution by robots.
Functional Object-Oriented Network: Construction & Expansion
To further improve the performance of knowledge retrieval as a follow up to our previous work, we discuss generalizing knowledge to be applied to objects which are similar to what we have in FOON without manually annotating new sources of knowledge.
Neonatal Pain Expression Recognition Using Transfer Learning
In this paper, we propose a new pipeline for pain expression recognition in neonates using transfer learning.
Long Activity Video Understanding using Functional Object-Oriented Network
Each action is therefore associated with a functional unit and the sequence of actions is further evaluated to identify the single on-going activity in the video.
Stability of Scattering Decoder For Nonlinear Diffractive Imaging
The problem of image reconstruction under multiple light scattering is usually formulated as a regularized non-convex optimization.
An empirical study on evaluation metrics of generative adversarial networks
Evaluating generative adversarial networks (GANs) is inherently challenging.
Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertising
The data involved in CTR prediction are typically multi-field categorical data, i. e., every feature is categorical and belongs to one and only one field.
Construction of all-in-focus images assisted by depth sensing
A graph-based segmentation algorithm is used to segment the depth map from the depth sensor, and the segmented regions are used to guide a focus algorithm to locate in-focus image blocks from among multi-focus source images to construct the reference all-in-focus image.
Identifying Object States in Cooking-Related Images
The trained state identification model is evaluated on a subset of the Imagenet dataset and state labels are provided using a combination of the model with manual checking.
Efficient and accurate inversion of multiple scattering with deep learning
Image reconstruction under multiple light scattering is crucial in a number of applications such as diffraction tomography.
On Calibration of Modern Neural Networks
Confidence calibration -- the problem of predicting probability estimates representative of the true correctness likelihood -- is important for classification models in many applications.
Learning to Pour
We present a pouring trajectory generation approach, which uses force feedback from the cup to determine the future velocity of pouring.
Multivariate Regression with Gross Errors on Manifold-valued Data
Our model first takes a correction step on the grossly corrupted responses via geodesic curves on the manifold, and then performs multivariate linear regression on the corrected data.
Concept Drift Adaptation by Exploiting Historical Knowledge
Incremental learning with concept drift has often been tackled by ensemble methods, where models built in the past can be re-trained to attain new models for the current data.
Supervised Word Mover's Distance
Accurately measuring the similarity between text documents lies at the core of many real world applications of machine learning.
Latest Datasets and Technologies Presented in the Workshop on Grasping and Manipulation Datasets
This paper reports the activities and outcomes in the Workshop on Grasping and Manipulation Datasets that was organized under the International Conference on Robotics and Automation (ICRA) 2016.
Machine-based Multimodal Pain Assessment Tool for Infants: A Review
In addition, it reviews the databases available to the research community and discusses the current limitations of the automated pain assessment.
Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classification
To tackle the sentiment classification problem in low-resource languages without adequate annotated data, we propose an Adversarial Deep Averaging Network (ADAN) to transfer the knowledge learned from labeled data on a resource-rich source language to low-resource languages where only unlabeled data exists.
Deep Networks with Stochastic Depth
With stochastic depth we can increase the depth of residual networks even beyond 1200 layers and still yield meaningful improvements in test error (4. 91% on CIFAR-10).
Ranked #20 on
Image Classification
on SVHN
Private Causal Inference
Causal inference has the potential to have significant impact on medical research, prevention and control of diseases, and identifying factors that impact economic changes to name just a few.
Information Transfer in Swarms with Leaders
Depending upon the leadership model, leaders can use their external information either all the time or in response to local conditions [Couzin et al. 2005; Sun et al. 2013].
