Liwei Wang

78

Papers

2,187

Total Citations

Papers (78)

The Expressive Power of Neural Networks: A View from the Width

NeurIPS 2017arXiv

Dual Learning for Machine Translation

NeurIPS 2016arXiv

Diverse and Accurate Image Description Using a Variational Auto-Encoder with an Additive Gaussian Encoding Space

NeurIPS 2017arXiv

Towards Learning a Generalist Model for Embodied Navigation

AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning

BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning

Fine-grained Spatiotemporal Grounding on Egocentric Videos

Learning Deep Structure-Preserving Image-Text Embeddings

Large-Scale Few-Shot Learning: Knowledge Transfer With Class Hierarchy

Fast, Diverse and Accurate Image Captioning Guided by Part-Of-Speech

FocalMix: Semi-Supervised Learning for 3D Medical Image Detection

Memory Enhanced Global-Local Aggregation for Video Object Detection

Boosting Few-Shot Learning With Adaptive Margin Loss

Semi-Supervised Semantic Segmentation With Directional Context-Aware Consistency

Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding

Fully Convolutional Networks for Panoptic Segmentation

Dense Relation Distillation With Context-Aware Aggregation for Few-Shot Object Detection

Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation

Voxel Field Fusion for 3D Object Detection

RBGNet: Ray-Based Grouping for 3D Object Detection

Multi-View Transformer for 3D Visual Grounding

Stratified Transformer for 3D Point Cloud Segmentation

DSVT: Dynamic Sparse Voxel Transformer With Rotated Sets

ContraNeRF: Generalizable Neural Radiance Fields for Synthetic-to-Real Novel View Synthesis via Contrastive Learning

Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models

A Fast and Accurate One-Stage Approach to Visual Grounding

Learning Relationships for Multi-View 3D Object Recognition

RepPoints: Point Set Representation for Object Detection

Few-Shot Learning With Global Class Representations

Region-Aware Contrastive Learning for Semantic Segmentation

Deep Structured Instance Graph for Distilling Object Detectors

Learnable Boundary Guided Adversarial Training

SAT: 2D Semantics Assisted Training for 3D Visual Grounding

VL-PET: Vision-and-Language Parameter-Efficient Tuning via Granularity Control

UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation

Comprehensive Image Captioning via Scene Graph Decomposition

Improving One-stage Visual Grounding by Recursive Sub-query Construction

Dense RepPoints: Representing Visual Objects with Dense Point Sets

PointScatter: Point Set Representation for Tubular Structure Extraction

Check and Link: Pairwise Lesion Correspondence Guides Mammogram Mass Detection

DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation

Decoding with Value Networks for Neural Machine Translation

Self-Supervised 3D Mesh Reconstruction From Single Images

DeformCL: Learning Deformable Centerline Representation for Vessel Extraction in 3D Medical Image

GeoMFormer: A General Architecture for Geometric Molecular Representation Learning

Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation

Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret

Quantum Algorithms and Lower Bounds for Finite-Sum Optimization

Do Efficient Transformers Really Save Computation?

Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same Representation

FRAGE: Frequency-Agnostic Word Representation

Convergence of Adversarial Training in Overparametrized Neural Networks

Equipping Experts/Bandits with Long-term Memory

McDiarmid-Type Inequalities for Graph-Dependent Variables and Stability Bounds

RepPoints v2: Verification Meets Regression for Object Detection

Locally Differentially Private (Contextual) Bandits Learning

Improved Analysis of Clipping Algorithms for Non-convex Optimization

Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot

NeurIPS 2020arXiv

Non-convex Distributionally Robust Optimization: Non-asymptotic Analysis

Breaking the Moments Condition Barrier: No-Regret Algorithm for Bandits with Super Heavy-Tailed Payoffs

Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning

Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding

Towards a Theoretical Framework of Out-of-Distribution Generalization

Your Transformer May Not be as Powerful as You Expect

Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive Power

ComGAN: Unsupervised Disentanglement and Segmentation via Image Composition

Is $L^2$ Physics Informed Loss Always Suitable for Training Physics Informed Neural Network?

Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function Perspective

CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds

PRED: Pre-training via Semantic Rendering on LiDAR Point Clouds

A Reduction-based Framework for Sequential Decision Making with Delayed Feedback

Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds

Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective

Collect at Once, Use Effectively: Making Non-interactive Locally Private Learning Possible

Towards Binary-Valued Gates for Robust LSTM Training

Dropout Training, Data-dependent Regularization, and Generalization Bounds

Gradient Descent Finds Global Minima of Deep Neural Networks

Efficient Training of BERT by Progressively Stacking