Arwen Bradley

5 papers · 2021–2025 · 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 🐣 Hot Topic Early Bird ❓ The Questioner 📈 Trend Setter

Venues

ICLR (2) AISTATS (1) ICML (1) WACV (1)

Top co-authors

Preetum Nakkiran (4) Joshua M. Susskind (3) Etai Littwin (2) Hattie Zhou (2) James Thornton (2) Noam Razin (2) Omid Saremi (2) Ruixiang ZHANG (1) Rudolph van der Merwe (1) Joseph Triscari (1)

Research topics

Machine Learning (4) Optimization & Theory (3) Artificial Intelligence (2) Deep Learning (2) Core AI (2) Models (2) Mathematics & Optimization (1) Bayesian & Probabilistic (1) Learning Paradigms (1) Learning Types (1) Optimization (1)

Keywords

length generalization (2) policy gradient (1) motion estimation (1) model distillation (1) in-context learning (1) sequential monte carlo (1) reward function (1) l1 minimization (1) diffusion model (1) algorithmic reasoning (1) energy-based model (1) vanishing gradient (1) feynman-kac model (1) video stabilization (1) reinforcement fine-tuning (1) helmholtz decomposition (1) energy diffusion model (1) linear score combination (1) out-of-distribution extrapolation (1) projective composition (1)

Papers

Composition and Control with Distilled Energy Diffusion Models and Sequential Monte Carlo AISTATS 2025 Mechanisms of Projective Composition of Diffusion Models ICML 2025 Vanishing Gradients in Reinforcement Finetuning of Language Models ICLR 2024 What Algorithms can Transformers Learn? A Study in Length Generalization ICLR 2024 Cinematic-L1 Video Stabilization With a Log-Homography Model WACV 2021