Hattie Zhou

6 papers · 2019–2025 · 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 ↓

+1 more ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🗺️ Taxonomy Completionist (14) 🐣 Hot Topic Early Bird 🧭 Keyword Pioneer

❓ The Questioner

Venues

ICLR (4) NeurIPS (2)

Top co-authors

Preetum Nakkiran (3) Jason Yosinski (2) Etai Littwin (2) Omid Saremi (2) Janice Lan (2) Rosanne Liu (2) Noam Razin (2) Arwen Bradley (2) Joshua M. Susskind (2) Vimal Thilak (1)

Research topics

Machine Learning (6) Optimization & Theory · Machine Learning (6) Deep Learning (4) Artificial Intelligence (3) Core AI (3) Learning Types (2) Techniques (2) Application Areas (1) Architectures (1) Learning Paradigms (1) Optimization & Theory · Deep Learning (1)

Keywords

length generalization (2) neural network optimization (2) lottery ticket hypothesis (1) continual learning (1) feature learning (1) neural network training (1) policy gradient (1) in-context learning (1) reward function (1) weight initialization (1) algorithmic reasoning (1) training dynamics (1) weight pruning (1) positional encoding (1) sparse training (1) causal transformer (1) vanishing gradient (1) iterative training (1) loss change allocation (1) theoretical framework (1)

Papers

A Formal Framework for Understanding Length Generalization in Transformers ICLR 2025 Vanishing Gradients in Reinforcement Finetuning of Language Models ICLR 2024 What Algorithms can Transformers Learn? A Study in Length Generalization ICLR 2024 Fortuitous Forgetting in Connectionist Networks ICLR 2022 Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask NeurIPS 2019 LCA: Loss Change Allocation for Neural Network Training NeurIPS 2019