Marco Bondaschi

5 papers · 2024–2025 · 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 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (15)

Venues

NeurIPS (3) ICLR (1) ICML (1)

Top co-authors

Ashok Vardhan Makkuva (5) Michael Gastpar (5) Hyeji Kim (4) Adway Girish (3) Alliot Nagle (3) Martin Jaggi (2) Chanakya Ekbote (1) Kannan Ramchandran (1) Nived Rajaraman (1) Thijs Vogels (1)

Research topics

Machine Learning (4) Optimization & Theory · Machine Learning (4) Artificial Intelligence (3) Deep Learning (3) Architectures (3) Core AI (3) Natural Language Processing (2) Generation (2) Application Areas (1) Optimization & Theory · Deep Learning (1) Resources & Methods (1)

Keywords

markov chain (2) local minimum (2) large language model (2) in-context learning (2) loss landscape (1) compression scheme (1) rate distortion (1) learning dynamics (1) induction head (1) next-token prediction (1) parameter initialization (1) global minimum (1) prompt compression (1) token-level compression (1) black-box model (1) layer normalization (1) wireless channel (1) markov process (1) low-rank structure (1) rate-distortion theory (1)

Papers

Attention with Markov: A Curious Case of Single-layer Transformers ICLR 2025 Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models NeurIPS 2024 LASER: Linear Compression in Wireless Distributed Optimization ICML 2024 Local to Global: Learning Dynamics and Effect of Initialization for Transformers NeurIPS 2024 Transformers on Markov data: Constant depth suffices NeurIPS 2024