Tianqi Du

6 papers · 2023–2025 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (10) ❓ The Questioner

Venues

ICLR (4) ICML (2)

Top co-authors

Yisen Wang (6) Yifei Wang (5) Haotian Huang (2) Qi Zhang (2) Jiansheng Yang (1) Xiaojun Guo (1) Weiran Huang (1) Xuyang Zhao (1) Zhouchen Lin (1) Jun Yao (1)

Research topics

Machine Learning (5) Learning Types (5) Deep Learning (4) Architectures (3) Artificial Intelligence (1) Natural Language Processing (1) Application Areas (1) Core AI (1) Core Methods (1) Generation (1) Models (1) Techniques (1)

Keywords

contrastive learning (4) self-supervised learning (3) graph neural network (2) visual representation (1) message passing (1) output distribution (1) length generalization (1) discrete tokenization (1) dimensional collapse (1) classification task (1) regularization term (1) domain-invariant feature (1) long-context modeling (1) masked image modeling (1) large language model (1) augmentation graph (1) long-short alignment (1) autoregressive ssl (1) content generation tasks (1) fixed position tokens (1)

Papers

Long-Short Alignment for Effective Long-Context Modeling in LLMs ICML 2025 Look Ahead or Look Around? A Theoretical Comparison Between Autoregressive and Masked Pretraining ICML 2024 On the Role of Discrete Tokenization in Visual Representation Learning ICLR 2024 A Message Passing Perspective on Learning Dynamics of Contrastive Learning ICLR 2023 ArCL: Enhancing Contrastive Learning with Augmentation-Robust Representations ICLR 2023 ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond ICLR 2023