Lukas Cavigelli

3 papers · 2017–2026 · 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 ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird 🧭 Keyword Pioneer

Venues

NeurIPS (2) ACL (1)

Top co-authors

Luc V Gool (1) Luc V. Gool (1) Fabian Mentzer (1) Niklas Roemer (1) Eirikur Agustsson (1) Luca Benini (1) Jiawei Zhuang (1) Michele Marzollo (1) Lorenz K Muller (1) Niklas Zwingenberger (1)

Research topics

Artificial Intelligence (2) Core AI (2) Deep Learning (1) Machine Learning (1) Reinforcement Learning (1) Application Areas (1) Learning Types (1) Methods (1) Models (1) Optimization & Theory (1)

Keywords

neural network compression (1) representation learning (1) image compression (1) adaptive sampling (1) importance sampling (1) vector quantization (1) real-time rendering (1) inference acceleration (1) speculative decoding (1) draft model (1) n-gram matching (1) large language model (1) monte carlo path tracing (1) neural denoiser (1) compressible representation (1)

Papers

SSSD: Simply-Scalable Speculative Decoding ACL 2026 RL-based Stateful Neural Adaptive Sampling and Denoising for Real-Time Path Tracing NeurIPS 2023 Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations NeurIPS 2017