Search Results for author:
Found 55 papers, 27 papers with code
Smooth and Stepwise Self-Distillation for Object Detection
Distilling the structured information captured in feature maps has contributed to improved results for object detection tasks, but requires careful selection of baseline architectures and substantial pre-training.
ERNIE-Music: Text-to-Waveform Music Generation with Diffusion Models
In recent years, there has been an increased popularity in image and speech generation using diffusion models.
PASSerRank: Prediction of Allosteric Sites with Learning to Rank
Allostery plays a crucial role in regulating protein activity, making it a highly sought-after target in drug development.
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.
Attention-Aware Anime Line Drawing Colorization
Automatic colorization of anime line drawing has attracted much attention in recent years since it can substantially benefit the animation industry.
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.
BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision
The proposed method is verified with a wide spectrum of traditional and modern image backbones and achieves new SoTA results on the large-scale nuScenes dataset.
Ranked #1 on
3D Object Detection
on nuScenes Camera Only
Arbitrary Style Guidance for Enhanced Diffusion-Based Text-to-Image Generation
Diffusion-based text-to-image generation models like GLIDE and DALLE-2 have gained wide success recently for their superior performance in turning complex text inputs into images of high quality and wide diversity.
Extreme Generative Image Compression by Learning Text Embedding from Diffusion Models
With the recent success of diffusion models for text-to-image generation, we propose a generative image compression method that demonstrates the potential of saving an image as a short text embedding which in turn can be used to generate high-fidelity images which is equivalent to the original one perceptually.
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-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 #7 on
Text-to-Image Generation
on 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.
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 #1 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
Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe
As sensor configurations get more complex, integrating multi-source information from different sensors and representing features in a unified view come of vital importance.
Graph Kernels Based on Multi-scale Graph Embeddings
To mitigate the two challenges, we propose a novel graph kernel called the Multi-scale Path-pattern Graph kernel (MPG), at the heart of which is the multi-scale path-pattern node feature map.
ERNIE-Search: Bridging Cross-Encoder with Dual-Encoder via Self On-the-fly Distillation for Dense Passage Retrieval
Our method 1) introduces a self on-the-fly distillation method that can effectively distill late interaction (i. e., ColBERT) to vanilla dual-encoder, and 2) incorporates a cascade distillation process to further improve the performance with a cross-encoder teacher.
LAST: Latent Space Assisted Adaptive Sampling for Protein Trajectories
Based on this characteristic, we proposed a new adaptive sampling method, latent space assisted adaptive sampling for protein trajectories (LAST), to accelerate the exploration of protein conformational space.
Accurate ADMET Prediction with XGBoost
The absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties are important in drug discovery as they define efficacy and safety.
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.
Indicative Image Retrieval: Turning Blackbox Learning into Grey
In many applications, we need the matching evidence to be indicated rather than just have the ranked list (e. g., the locations of the target proteins/cells/lesions in medical images).
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 #36 on
Text-to-Image Generation
on 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.
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.
Do What Nature Did To Us: Evolving Plastic Recurrent Neural Networks For Generalized Tasks
While artificial neural networks (ANNs) have been widely adopted in machine learning, researchers are increasingly obsessed by the gaps between ANNs and natural neural networks (NNNs).
Reinforcement Learning with Evolutionary Trajectory Generator: A General Approach for Quadrupedal Locomotion
However, due to the complex nonlinear dynamics in quadrupedal robots and reward sparsity, it is still difficult for RL to learn effective gaits from scratch, especially in challenging tasks such as walking over the balance beam.
ADER:Adapting between Exploration and Robustness for Actor-Critic Methods
Combining off-policy reinforcement learning methods with function approximators such as neural networks has been found to lead to overestimation of the value function and sub-optimal solutions.
Evolving Decomposed Plasticity Rules for Information-Bottlenecked Meta-Learning
In contrast, biological neural networks (BNNs) can adapt to various new tasks by continually updating the neural connections based on the inputs, which is aligned with the paradigm of learning effective learning rules in addition to static parameters, e. g., meta-learning.
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.
Action Set Based Policy Optimization for Safe Power Grid Management
At the planning stage, the search space is limited to the action set produced by the policy.
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.
The Flare and Warp of the Young Stellar Disk traced with LAMOST DR5 OB-type stars
We present analysis of the spatial density structure for the outer disk from 8$-$14 \, kpc with the LAMOST DR5 13534 OB-type stars and observe similar flaring on north and south sides of the disk implying that the flaring structure is symmetrical about the Galactic plane, for which the scale height at different Galactocentric distance is from 0. 14 to 0. 5 \, kpc.
Astrophysics of Galaxies
Exploring the Galactic Anticenter substructure with LAMOST & Gaia DR2
Their location in [$\alpha$/M] vs. [M/H] space is more metal poor than typical thin disk stars, with [$\alpha$/M] \textbf{lower} than the thick disk.
Astrophysics of Galaxies
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 #1 on
Text Classification
on IMDb
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
Unsupervised Object Detection with LiDAR Clues
We further identify another major issue, seldom noticed by the community, that the long-tailed and open-ended (sub-)category distribution should be accommodated.
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.
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 #1 on
Visual Question Answering (VQA)
on VCR (QA-R) test
Referring Expression Comprehension
Visual Question Answering (VQA)
SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis
In particular, the prediction of aspect-sentiment pairs is converted into multi-label classification, aiming to capture the dependency between words in a pair.
ivis Dimensionality Reduction Framework for Biomacromolecular Simulations
Molecular dynamics (MD) simulations have been widely applied to study macromolecules including proteins.
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)
Efficient and Robust Reinforcement Learning with Uncertainty-based Value Expansion
By integrating dynamics models into model-free reinforcement learning (RL) methods, model-based value expansion (MVE) algorithms have shown a significant advantage in sample efficiency as well as value estimation.
Learning to Recommend via Meta Parameter Partition
The fixed part, capturing user invariant features, is shared by all users and is learned during offline meta learning stage.
MBCAL: Sample Efficient and Variance Reduced Reinforcement Learning for Recommender Systems
The proposed method takes advantage of the characteristics of recommender systems and draws ideas from the model-based reinforcement learning method for higher sample efficiency.
Model-based Reinforcement Learning
Recommendation Systems
+2
Risk Averse Value Expansion for Sample Efficient and Robust Policy Learning
A promising direction is to combine model-based reinforcement learning with model-free reinforcement learning, such as model-based value expansion(MVE).
Model-based Reinforcement Learning
reinforcement-learning
+1
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.
Chinese Named Entity Recognition
Chinese Reading Comprehension
+8
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
Chinese Sentiment Analysis
on ChnSentiCorp Dev
Chinese Named Entity Recognition
Chinese Sentence Pair Classification
+8
Artificial Intelligence for Prosthetics - challenge solutions
In the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge, participants were tasked with building a controller for a musculoskeletal model with a goal of matching a given time-varying velocity vector.
Sequential Evaluation and Generation Framework for Combinatorial Recommender System
On the one hand of this framework, an evaluation model is trained to evaluate the expected overall utility, by fully considering the user, item information and the correlations among the co-exposed items.
Intervention Aided Reinforcement Learning for Safe and Practical Policy Optimization in Navigation
We built neural networks as our policy to map sensor readings to control signals on the UAV.
Transferring Grasp Configurations using Active Learning and Local Replanning
We compute a grasp space for each part of the example object using active learning.
Robotics
