← Authors

Liwei Wang

163 papers · 2009–2025 · 16 conferences · across top CS/AI conferences

Achievements

🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (16) πŸ—ΊοΈ Taxonomy Completionist (29) 🐝 Cross-Pollinator (15) πŸƒ Academic Marathon (16) 🌈 Renaissance Researcher (9) πŸŒ‰ Interdisciplinary Bridge 🌟 Keyword Trendsetter Combo (5) 🏠 Conference Loyalist (34) 🀝 Dynamic Duo (33) πŸ‘‘ Triple Crown πŸ† Grand Slam 🌱 Topic Pioneer πŸ”¬ Deep Specialist (18) 🧬 Topic Evolution πŸ† Keyword Champion πŸ”₯ Unstoppable (11) ⚑ Prolific Year (20) πŸ’Ž Century Club (163) πŸ—ƒοΈ Keyword Collector (83) ❓ The Questioner (3) πŸ“ˆ Trend Setter πŸš€ Conference Pioneer

Conferences

NIPS (34) ICML (25) ICLR (22) CVPR (21) ICCV (14) ACL (10) ECCV (9) EMNLP (9) AISTATS (3) COLT (3) IJCAI (3) JMLR (3) NAACL (3) IJCNLP (2) AAAI (1) UAI (1)

Top co-authors

Di He (33) Han Zhong (15) Tie-yan Liu (14) Bohang Zhang (11) Xiaoyu Chen (10) Yanyang Li (10) Jiaya Jia (9) Shengjie Luo (9) Tao Qin (8) Haiyang Wang (8)

Research topics

Differential Privacy (5) Statistics (1)

Keywords

regret bound (12) object detection (8) point cloud (8) large language model (7) neural network (7) reinforcement learning (7) semantic segmentation (7) representation learning (5) differential privacy (5) learning theory (5) multi-armed bandit (5) semi-supervised learning (4) attention mechanism (4) contrastive learning (4) function approximation (4) instance segmentation (4) 3d object detection (4) model compression (4) visual grounding (4) autonomous driving (4)

Papers

BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning ICML 2025
DPO Meets PPO: Reinforced Token Optimization for RLHF ICML 2025
The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability ICML 2025
End-to-End Entity-Predicate Association Reasoning for Dynamic Scene Graph Generation ICCV 2025
TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters ICLR 2025
How Numerical Precision Affects Arithmetical Reasoning Capabilities of LLMs ACL 2025
Can Machines Understand Composition? Dataset and Benchmark for Photographic Image Composition Embedding and Understanding CVPR 2025
DeformCL: Learning Deformable Centerline Representation for Vessel Extraction in 3D Medical Image CVPR 2025
UTSamuel at ArchEHR-QA 2025: A Clinical Question Answering System for Responding to Patient Portal Messages Using Generative AI ACL 2025
C2LEVA: Toward Comprehensive and Contamination-Free Language Model Evaluation ACL 2025
AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning ICCV 2025
Homomorphism Expressivity of Spectral Invariant Graph Neural Networks ICLR 2025
Fine-grained Spatiotemporal Grounding on Egocentric Videos ICCV 2025
Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding CVPR 2025
Learning to Reason from Feedback at Test-Time ACL 2025
Enhancing Temporal Modeling of Video LLMs via Time Gating EMNLP 2024
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction NIPS 2024
GraphMorph: Tubular Structure Extraction by Morphing Predicted Graphs NIPS 2024
Bridging Geometric States via Geometric Diffusion Bridge NIPS 2024
Quantum Algorithms and Lower Bounds for Finite-Sum Optimization ICML 2024
Do Efficient Transformers Really Save Computation? ICML 2024
Making Long-Context Language Models Better Multi-Hop Reasoners ACL 2024
GiT: Towards Generalist Vision Transformer through Universal Language Interface ECCV 2024
Beyond Embeddings: The Promise of Visual Table in Visual Reasoning EMNLP 2024
Towards Learning a Generalist Model for Embodied Navigation CVPR 2024
GeoMFormer: A General Architecture for Geometric Molecular Representation Learning ICML 2024
Wonder at Chemotimelines 2024: MedTimeline: An End-to-End NLP System for Timeline Extraction from Clinical Narratives NAACL 2024
Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret ICML 2024
Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation ICML 2024
Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness ICLR 2024
On cyclical MCMC sampling AISTATS 2024
Horizon-Free and Instance-Dependent Regret Bounds for Reinforcement Learning with General Function Approximation AISTATS 2024
Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds NIPS 2023
VL-PET: Vision-and-Language Parameter-Efficient Tuning via Granularity Control ICCV 2023
Offline Meta Reinforcement Learning with In-Distribution Online Adaptation ICML 2023
Learning Preference Model for LLMs via Automatic Preference Data Generation EMNLP 2023
CLEVA: Chinese Language Models EVAluation Platform EMNLP 2023
PRED: Pre-training via Semantic Rendering on LiDAR Point Clouds NIPS 2023
A Reduction-based Framework for Sequential Decision Making with Delayed Feedback NIPS 2023
UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation ICCV 2023
Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective NIPS 2023
MVP-Tuning: Multi-View Knowledge Retrieval with Prompt Tuning for Commonsense Reasoning ACL 2023
Learning Physics-Informed Neural Networks without Stacked Back-propagation AISTATS 2023
Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling ICLR 2023
Rethinking the Expressive Power of GNNs via Graph Biconnectivity ICLR 2023
One Transformer Can Understand Both 2D & 3D Molecular Data ICLR 2023
Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game ICLR 2023
Denoising Masked Autoencoders Help Robust Classification ICLR 2023
Provable Sim-to-real Transfer in Continuous Domain with Partial Observations ICLR 2023
A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Tests ICML 2023
On the Power of Pre-training for Generalization in RL: Provable Benefits and Hardness ICML 2023
DSVT: Dynamic Sparse Voxel Transformer With Rotated Sets CVPR 2023
ContraNeRF: Generalizable Neural Radiance Fields for Synthetic-to-Real Novel View Synthesis via Contrastive Learning CVPR 2023
Eliciting Knowledge from Large Pre-Trained Models for Unsupervised Knowledge-Grounded Conversation EMNLP 2022
FlowEval: A Consensus-Based Dialogue Evaluation Framework Using Segment Act Flows EMNLP 2022
Near-Optimal Reward-Free Exploration for Linear Mixture MDPs with Plug-in Solver ICLR 2022
Understanding Domain Randomization for Sim-to-real Transfer ICLR 2022
Your Transformer May Not be as Powerful as You Expect NIPS 2022
Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation ICML 2022
Boosting the Certified Robustness of L-infinity Distance Nets ICLR 2022
DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation ECCV 2022
A Reduction-Based Framework for Conservative Bandits and Reinforcement Learning ICLR 2022
Voxel Field Fusion for 3D Object Detection CVPR 2022
RBGNet: Ray-Based Grouping for 3D Object Detection CVPR 2022
Multi-View Transformer for 3D Visual Grounding CVPR 2022
Probing Structured Pruning on Multilingual Pre-trained Models: Settings, Algorithms, and Efficiency ACL 2022
CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds NIPS 2022
Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function Perspective NIPS 2022
Stratified Transformer for 3D Point Cloud Segmentation CVPR 2022
Is $L^2$ Physics Informed Loss Always Suitable for Training Physics Informed Neural Network? NIPS 2022
ComGAN: Unsupervised Disentanglement and Segmentation via Image Composition NIPS 2022
Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive Power NIPS 2022
Check and Link: Pairwise Lesion Correspondence Guides Mammogram Mass Detection ECCV 2022
PointScatter: Point Set Representation for Tubular Structure Extraction ECCV 2022
Nearly Optimal Policy Optimization with Stable at Any Time Guarantee ICML 2022
Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets ICML 2022
Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation CVPR 2021
Non-convex Distributionally Robust Optimization: Non-asymptotic Analysis NIPS 2021
Breaking the Moments Condition Barrier: No-Regret Algorithm for Bandits with Super Heavy-Tailed Payoffs NIPS 2021
Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning NIPS 2021
Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding NIPS 2021
Towards a Theoretical Framework of Out-of-Distribution Generalization NIPS 2021
Augmented Partial Mutual Learning with Frame Masking for Video Captioning AAAI 2021
JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs ACL 2021
Semi-Supervised Semantic Segmentation With Directional Context-Aware Consistency CVPR 2021
Self-Supervised 3D Mesh Reconstruction From Single Images CVPR 2021
Fully Convolutional Networks for Panoptic Segmentation CVPR 2021
Dense Relation Distillation With Context-Aware Aggregation for Few-Shot Object Detection CVPR 2021
RAST: Domain-Robust Dialogue Rewriting as Sequence Tagging EMNLP 2021
Region-Aware Contrastive Learning for Semantic Segmentation ICCV 2021
Deep Structured Instance Graph for Distilling Object Detectors ICCV 2021
Learnable Boundary Guided Adversarial Training ICCV 2021
SAT: 2D Semantics Assisted Training for 3D Visual Grounding ICCV 2021
Efficient Reinforcement Learning in Factored MDPs with Application to Constrained RL ICLR 2021
GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training ICML 2021
Near-Optimal Representation Learning for Linear Bandits and Linear RL ICML 2021
On Reinforcement Learning with Adversarial Corruption and Its Application to Block MDP ICML 2021
Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neurons ICML 2021
JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs IJCNLP 2021
DAGN: Discourse-Aware Graph Network for Logical Reasoning NAACL 2021
Combinatorial semi-bandit in the non-stationary environment UAI 2021
Boosting Few-Shot Learning With Adaptive Margin Loss CVPR 2020
Comprehensive Image Captioning via Scene Graph Decomposition ECCV 2020
Learning to Group: A Bottom-Up Framework for 3D Part Discovery in Unseen Categories ICLR 2020
Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks ICLR 2020
Distributed Bandit Learning: Near-Optimal Regret with Efficient Communication ICLR 2020
Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP ICLR 2020
MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radius ICLR 2020
Robust Local Features for Improving the Generalization of Adversarial Training ICLR 2020
Improving One-stage Visual Grounding by Recursive Sub-query Construction ECCV 2020
Memory Enhanced Global-Local Aggregation for Video Object Detection CVPR 2020
FocalMix: Semi-Supervised Learning for 3D Medical Image Detection CVPR 2020
MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning ACL 2020
(Locally) Differentially Private Combinatorial Semi-Bandits ICML 2020
On Layer Normalization in the Transformer Architecture ICML 2020
Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot NIPS 2020
Improved Analysis of Clipping Algorithms for Non-convex Optimization NIPS 2020
Locally Differentially Private (Contextual) Bandits Learning NIPS 2020
RepPoints v2: Verification Meets Regression for Object Detection NIPS 2020
Semi-Supervised Learning for Video Captioning EMNLP 2020
Dense RepPoints: Representing Visual Objects with Dense Point Sets ECCV 2020
Equipping Experts/Bandits with Long-term Memory NIPS 2019
McDiarmid-Type Inequalities for Graph-Dependent Variables and Stability Bounds NIPS 2019
Hint-Based Training for Non-Autoregressive Machine Translation IJCNLP 2019
Learning Relationships for Multi-View 3D Object Recognition ICCV 2019
Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network ACL 2019
A Fast and Accurate One-Stage Approach to Visual Grounding ICCV 2019
Large-Scale Few-Shot Learning: Knowledge Transfer With Class Hierarchy CVPR 2019
Fast, Diverse and Accurate Image Captioning Guided by Part-Of-Speech CVPR 2019
Gradient Descent Finds Global Minima of Deep Neural Networks ICML 2019
Efficient Training of BERT by Progressively Stacking ICML 2019
RepPoints: Point Set Representation for Object Detection ICCV 2019
Few-Shot Learning With Global Class Representations ICCV 2019
Hint-Based Training for Non-Autoregressive Machine Translation EMNLP 2019
Representation Degeneration Problem in Training Natural Language Generation Models ICLR 2019
Improving the Generalization of Adversarial Training with Domain Adaptation ICLR 2019
Attention Neural Model for Temporal Relation Extraction NAACL 2019
Convergence of Adversarial Training in Overparametrized Neural Networks NIPS 2019
Generalization Bounds of SGLD for Non-convex Learning: Two Theoretical Viewpoints COLT 2018
Towards Binary-Valued Gates for Robust LSTM Training ICML 2018
Dropout Training, Data-dependent Regularization, and Generalization Bounds ICML 2018
FRAGE: Frequency-Agnostic Word Representation NIPS 2018
Learning to Navigate for Fine-grained Classification ECCV 2018
Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same Representation NIPS 2018
Learning Region Features for Object Detection ECCV 2018
Efficient Private ERM for Smooth Objectives IJCAI 2017
Collect at Once, Use Effectively: Making Non-interactive Locally Private Learning Possible ICML 2017
Quadratic Upper Bound for Recursive Teaching Dimension of Finite VC Classes COLT 2017
Diverse and Accurate Image Description Using a Variational Auto-Encoder with an Additive Gaussian Encoding Space NIPS 2017
The Expressive Power of Neural Networks: A View from the Width NIPS 2017
Decoding with Value Networks for Neural Machine Translation NIPS 2017
Learning Deep Structure-Preserving Image-Text Embeddings CVPR 2016
Dual Learning for Machine Translation NIPS 2016
Differentially Private Data Releasing for Smooth Queries JMLR 2016
Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models ICCV 2015
Social Image Parsing by Cross-Modal Data Refinement IJCAI 2015
A Theoretical Analysis of NDCG Type Ranking Measures COLT 2013
Efficient Algorithm for Privately Releasing Smooth Queries NIPS 2013
A Game-Theoretic Machine Learning Approach for Revenue Maximization in Sponsored Search IJCAI 2013
Dimensionality Dependent PAC-Bayes Margin Bound NIPS 2012
Smoothness, Disagreement Coefficient, and the Label Complexity of Agnostic Active Learning JMLR 2011
A Refined Margin Analysis for Boosting Algorithms via Equilibrium Margin JMLR 2011
Sufficient Conditions for Agnostic Active Learnable NIPS 2009