← Authors

Yifei Wang

68 papers · 2020–2026 · 12 conferences · across top CS/AI conferences

Achievements

🧭 Keyword Pioneer πŸƒ Academic Marathon (5) 🐝 Cross-Pollinator (6) 🌍 Conference Polyglot (12) 🌈 Renaissance Researcher (6) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (19) 🐣 Hot Topic Early Bird 🏠 Conference Loyalist (20) 🀝 Dynamic Duo (39) πŸ‘‘ Triple Crown πŸ† Keyword Champion (2) πŸ† Grand Slam πŸ’Ž Century Club (67) πŸ”₯ Unstoppable (6) ⚑ Prolific Year (19) πŸ—ƒοΈ Keyword Collector (188) ❓ The Questioner (6)

Conferences

ICLR (20) NIPS (19) ICML (11) AAAI (4) ACL (4) EMNLP (4) ACML (1) COLING (1) CVPR (1) ICCV (1) IJCAI (1) JMLR (1)

Top co-authors

Yisen Wang (39) Qi Zhang (10) Stefanie Jegelka (9) Zhouchen Lin (9) Jiansheng Yang (7) Tianqi Du (5) Zeming Wei (4) Weize Chen (4) Cheng Yang (4) Chen Qian (4)

Research topics

Optimization & Theory (1)

Keywords

contrastive learning (9) self-supervised learning (7) adversarial training (5) representation learning (5) large language model (5) graph neural network (4) domain generalization (3) autonomous agent (3) node classification (3) multi-agent system (3) out-of-distribution generalization (3) convex optimization (2) llm agent (2) software development (2) invariant learning (2) adversarial robustness (2) neural network optimization (2) semi-supervised learning (2) graph classification (2) in-context learning (2)

Papers

MIRA: Evaluating Multimodal AI on Complex Clinical Reasoning in Interventional Radiology AAAI 2026
An Augmentation Overlap Theory of Contrastive Learning JMLR 2025
Semi-IIN: Semi-Supervised Intra-Inter Modal Interaction Learning Network for Multimodal Sentiment Analysis AAAI 2025
Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness ICLR 2025
Projection Head is Secretly an Information Bottleneck ICLR 2025
Multi-Agent Collaboration via Cross-Team Orchestration ACL 2025
Uncertainty Unveiled: Can Exposure to More In-context Examples Mitigate Uncertainty for Large Language Models? ACL 2025
Rethinking Invariance in In-context Learning ICLR 2025
Can In-context Learning Really Generalize to Out-of-distribution Tasks? ICLR 2025
On the Emergence of Position Bias in Transformers ICML 2025
What is Wrong with Perplexity for Long-context Language Modeling? ICLR 2025
Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation ICML 2025
POSITION BIAS MITIGATES POSITION BIAS: Mitigate Position Bias Through Inter-Position Knowledge Distillation EMNLP 2025
HS-STaR: Hierarchical Sampling for Self-Taught Reasoners via Difficulty Estimation and Budget Reallocation EMNLP 2025
Long-Short Alignment for Effective Long-Context Modeling in LLMs ICML 2025
Scaling Large Language Model-based Multi-Agent Collaboration ICLR 2025
Unveiling Factual Recall Behaviors of Large Language Models through Knowledge Neurons EMNLP 2024
Encourage or Inhibit Monosemanticity? Revisit Monosemanticity from a Feature Decorrelation Perspective EMNLP 2024
Look Ahead or Look Around? A Theoretical Comparison Between Autoregressive and Masked Pretraining ICML 2024
OODRobustBench: a Benchmark and Large-Scale Analysis of Adversarial Robustness under Distribution Shift ICML 2024
Autonomous Agents for Collaborative Task under Information Asymmetry NIPS 2024
On the Role of Attention Masks and LayerNorm in Transformers NIPS 2024
An Expectation-Maximization Algorithm for Training Clean Diffusion Models from Corrupted Observations NIPS 2024
On the Role of Discrete Tokenization in Visual Representation Learning ICLR 2024
Do Generated Data Always Help Contrastive Learning? ICLR 2024
Non-negative Contrastive Learning ICLR 2024
A Canonicalization Perspective on Invariant and Equivariant Learning NIPS 2024
Dissecting the Failure of Invariant Learning on Graphs NIPS 2024
A Theoretical Understanding of Self-Correction through In-context Alignment NIPS 2024
In-Context Symmetries: Self-Supervised Learning through Contextual World Models NIPS 2024
Understanding the Role of Equivariance in Self-supervised Learning NIPS 2024
Experiential Co-Learning of Software-Developing Agents ACL 2024
BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents ACL 2024
Graph Neural Networks (with Proper Weights) Can Escape Oversmoothing ACML 2024
On the Duality Between Sharpness-Aware Minimization and Adversarial Training ICML 2024
Unbiased Stochastic Proximal Solver for Graph Neural Networks with Equilibrium States ICLR 2023
Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding NIPS 2023
Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from a Minimax Game Perspective NIPS 2023
Adversarial Examples Are Not Real Features NIPS 2023
Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learning NIPS 2023
Identifiable Contrastive Learning with Automatic Feature Importance Discovery NIPS 2023
USER: Unsupervised Structural Entropy-Based Robust Graph Neural Network AAAI 2023
On the Connection between Invariant Learning and Adversarial Training for Out-of-Distribution Generalization AAAI 2023
CFA: Class-Wise Calibrated Fair Adversarial Training CVPR 2023
A Message Passing Perspective on Learning Dynamics of Contrastive Learning ICLR 2023
ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond ICLR 2023
Towards a Unified Theoretical Understanding of Non-contrastive Learning via Rank DifferentialΒ Mechanism ICLR 2023
Parallel Deep Neural Networks Have Zero Duality Gap ICLR 2023
Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learning ICLR 2023
Rethinking Weak Supervision in Helping Contrastive Learning ICML 2023
On the Generalization of Multi-modal Contrastive Learning ICML 2023
Contrastive Label Enhancement IJCAI 2023
Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap ICLR 2022
The Convex Geometry of Backpropagation: Neural Network Gradient Flows Converge to Extreme Points of the Dual Convex Program ICLR 2022
Beyond the Best: Distribution Functional Estimation in Infinite-Armed Bandits NIPS 2022
Improving Out-of-Distribution Generalization by Adversarial Training with Structured Priors NIPS 2022
How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders NIPS 2022
When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture NIPS 2022
The Hidden Convex Optimization Landscape of Regularized Two-Layer ReLU Networks: an Exact Characterization of Optimal Solutions ICLR 2022
A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Training ICLR 2022
Optimization-Induced Graph Implicit Nonlinear Diffusion ICML 2022
G$^2$CN: Graph Gaussian Convolution Networks with Concentrated Graph Filters ICML 2022
Adaptive Newton Sketch: Linear-time Optimization with Quadratic Convergence and Effective Hessian Dimensionality ICML 2021
Dynamic Context-Sensitive Filtering Network for Video Salient Object Detection ICCV 2021
Residual Relaxation for Multi-view Representation Learning NIPS 2021
Dissecting the Diffusion Process in Linear Graph Convolutional Networks NIPS 2021
On Dyadic Fairness: Exploring and Mitigating Bias in Graph Connections ICLR 2021
Train Once, and Decode As You Like COLING 2020