Luca Biggio

7 papers · 2021–2025 · 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 🗺️ Taxonomy Completionist (16) 🐣 Hot Topic Early Bird 👑 Triple Crown

Venues

ICML (4) NeurIPS (2) ICLR (1)

Top co-authors

Aurelien Lucchi (4) Lorenzo Noci (2) Antonio Orvieto (2) Sotiris Anagnostidis (2) Thomas Hofmann (2) Tommaso Bendinelli (2) Frank Norbert Proske (1) Alexander Neitz (1) Dario Pavllo (1) Pierre-Alexandre Kamienny (1)

Research topics

Machine Learning (6) Artificial Intelligence (5) Deep Learning (5) Core AI (5) Core Methods (4) Architectures (3) Optimization & Theory · Machine Learning (3) Optimization & Theory · Deep Learning (2) Learning Types (1) Techniques (1)

Keywords

transformer architecture (1) stochastic gradient descent (1) autoregressive transformer (1) self-attention mechanism (1) conditional generation (1) sharpness-aware minimization (1) deep learning (1) prior knowledge (1) model pruning (1) softmax (1) signal propagation (1) deep learning model (1) stochastic differential equation (1) gradient vanishing (1) inference efficiency (1) embedding dimension (1) symbolic regression (1) flat minima (1) equation discovery (1) search algorithm (1)

Papers

Counting in Small Transformers: The Delicate Interplay between Attention and Feed-Forward Layers ICML 2025 An SDE for Modeling SAM: Theory and Insights ICML 2023 Controllable Neural Symbolic Regression ICML 2023 Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers NeurIPS 2023 FIGARO: Controllable Music Generation using Learned and Expert Features ICLR 2023 Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse NeurIPS 2022 Neural Symbolic Regression that scales ICML 2021