Scott Geng

3 papers · 2023–2024 · 3 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 (14)

Venues

ICLR (1) ICML (1) NeurIPS (1)

Top co-authors

Junfeng Yang (2) Carl Vondrick (1) Weichen Li (1) Chengzhi Mao (1) Pang Wei Koh (1) Ranjay Krishna (1) Vivek Ramanujan (1) Qirui Jin (1) Kexin Pei (1) Cheng-Yu Hsieh (1)

Research topics

Machine Learning (3) Artificial Intelligence (2) Core AI (2) Learning Types · Machine Learning (2) Computer Vision (1) Deep Learning (1) Analysis (1) Application Areas (1) Core Methods (1) Domain-Specific (1) Learning Types · Deep Learning (1) Models (1) Processing (1)

Keywords

image classification (1) contrastive learning (1) zero-shot learning (1) adversarial robustness (1) domain generalization (1) adversarial training (1) text-to-image generation (1) synthetic data (1) vision-language model (1) stable diffusion (1) synthetic training data (1) real image retrieval (1) permutation group (1) equivariant self-attention (1) real image (1) program dependence graph (1) llms (1) code symmetries (1) group-theoretic framework (1)

Papers

Exploiting Code Symmetries for Learning Program Semantics ICML 2024 The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better NeurIPS 2024 Understanding Zero-shot Adversarial Robustness for Large-Scale Models ICLR 2023