Razvan Pascanu

Computer Science · Physical Sciences

60h-index30.0kcitations212works0.72yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Domain Adaptation and Few-Shot Learning(59), Neural Networks and Applications(39), Reinforcement Learning in Robotics(36), Multimodal Machine Learning Applications(27), Advanced Neural Network Applications(23)

Publications212 total

pymc-devs/pytensor: rel-2.36.3
Zenodo (CERN European Organization for Nuclear Research)·2026Open Access
pymc-devs/pytensor: rel-2.36.2
Zenodo (CERN European Organization for Nuclear Research)·2026Open Access
MS-SSM: A Multi-Scale State Space Model for Efficient Sequence Modeling
arXiv (Cornell University)·2025Open Access
MS-SSM: A Multi-Scale State Space Model for Efficient Sequence Modeling
ArXiv.org·2025Open Access
pymc-devs/pytensor: rel-2.36.1
Zenodo (CERN European Organization for Nuclear Research)·2025Open Access
Fine-Tuned In-Context Learners for Efficient Adaptation
ArXiv.org·2025Open Access
Fine-Tuned In-Context Learners for Efficient Adaptation
arXiv (Cornell University)·2025Open Access
Optimizers Qualitatively Alter Solutions And We Should Leverage This
arXiv (Cornell University)·2025Open Access
RAT: Bridging RNN Efficiency and Attention Accuracy via Chunk-based Sequence Modeling
arXiv (Cornell University)·2025Open Access
How Overconfidence in Initial Choices and Underconfidence Under Criticism Modulate Change of Mind in Large Language Models
ArXiv.org·2025Open Access
Meta-learning how to Share Credit among Macro-Actions
arXiv (Cornell University)·2025Open Access
MesaNet: Sequence Modeling by Locally Optimal Test-Time Training
arXiv (Cornell University)·2025Open Access
Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization
arXiv (Cornell University)·2025Open Access
Plasticity as the Mirror of Empowerment
arXiv (Cornell University)·2025Open Access
On the generalization of language models from in-context learning and finetuning: a controlled study
arXiv (Cornell University)·2025Open Access
LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities
arXiv (Cornell University)·2025Open Access
Hadamard product in deep learning: Introduction, Advances and Challenges
arXiv (Cornell University)·2025Open Access
Hadamard Product in Deep Learning: Introduction, Advances and Challenges
IEEE Transactions on Pattern Analysis and Machine Intelligence·2025· 16 cited
NoProp: Training Neural Networks without Full Back-propagation or Full Forward-propagation
arXiv (Cornell University)·2025Open Access
How do language models learn facts? Dynamics, curricula and hallucinations
arXiv (Cornell University)·2025Open Access
page 1 of 11Next →

Frequent Co-authors

Yoshua Bengio(22), Raia Hadsell(12), Peter Battaglia(10), Çaǧlar Gülçehre(9), Oriol Vinyals(8), Guillaume Desjardins(7), Nicolas Heess(7), Andrei A. Rusu(6), Yujia Li(6), Koray Kavukcuoglu(6), Frédéric Bastien(5), Pascal Lamblin(5), David Warde-Farley(5), Kyunghyun Cho(5), David Reichert(5), James Kirkpatrick(4), Victor Bapst(4), David Raposo(4), Adam Santoro(4), Daan Wierstra(4)