Alex Vitvitskyi

5 papers · 2020–2025 · 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 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11) ❓ The Questioner (2)

Venues

ICLR (2) ICML (2) NeurIPS (1)

Top co-authors

Petar Veličković (3) Steven Kapturowski (3) Charles Blundell (2) Razvan Pascanu (2) Pablo Sprechmann (2) Bilal Piot (2) Federico Barbero (2) Adrià Puigdomènech Badia (2) Daniel Guo (1) João G.M. Araújo (1)

Research topics

Machine Learning (3) Artificial Intelligence (2) Deep Learning (2) Architectures (2) Core AI (2) Optimization & Theory (2) Natural Language Processing (1) Reinforcement Learning (1) Applications (1) Learning Types (1) Methods (1) Resources & Methods (1) Techniques (1)

Keywords

deep reinforcement learning (1) reinforcement learning (1) information bottleneck (1) self-supervised learning (1) attention mechanism (1) episodic memory (1) neural network model (1) signal propagation (1) mixing time (1) semantic information (1) atari game (1) exploration strategy (1) representation collapse (1) intrinsic reward (1) exploratory policy (1) frequency analysis (1) human benchmark (1) policy parameterization (1) large language model (1) directed exploration (1)

Papers

Round and Round We Go! What makes Rotary Positional Encodings useful? ICLR 2025 What Makes a Good Feedforward Computational Graph? ICML 2025 Transformers need glasses! Information over-squashing in language tasks NeurIPS 2024 Agent57: Outperforming the Atari Human Benchmark ICML 2020 Never Give Up: Learning Directed Exploration Strategies ICLR 2020