Wenlong Ji

4 papers · 2022–2024 · 4 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 (11)

Venues

AISTATS (1) ICLR (1) ICML (1) JMLR (1)

Top co-authors

James Zou (3) Zhun Deng (3) Linjun Zhang (2) Ryumei Nakada (2) Yiliang Zhang (1) Tatsunori Hashimoto (1) Weijie J Su (1) Halil Ibrahim Gulluk (1) Yiping Lu (1) Ian Connick Covert (1)

Research topics

Machine Learning (4) Optimization & Theory (3) Learning Types · Machine Learning (2) Artificial Intelligence (1) Computer Vision (1) Deep Learning (1) Application Areas (1) Core AI · Artificial Intelligence (1) Core AI · Computer Vision (1) Core Methods (1) Learning Types · Deep Learning (1)

Keywords

representation learning (2) contrastive learning (2) feature learning (1) self-supervised learning (1) multimodal learning (1) singular value decomposition (1) subset selection (1) neural collapse (1) gradient flow (1) scaling law (1) downstream task (1) vision-language model (1) linear representation (1) unpaired data (1) multimodal contrastive learning (1) neural network (1) last-layer feature (1) estimators (1) exponent (1) individual data points (1)

Papers

Scaling Laws for the Value of Individual Data Points in Machine Learning ICML 2024 The Power of Contrast for Feature Learning: A Theoretical Analysis JMLR 2023 Understanding Multimodal Contrastive Learning and Incorporating Unpaired Data AISTATS 2023 An Unconstrained Layer-Peeled Perspective on Neural Collapse ICLR 2022