Scholar
Tianlin Liu
Google Scholar ID: 1bbQjM4AAAAJ
Google DeepMind
machine learning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
1,024
H-index
14
i10-index
14
Publications
20
Co-authors
51
list available
Contact
CV
Open ↗
Twitter
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
7 items
Autoregressive Language Models are Secretly Energy-Based Models: Insights into the Lookahead Capabilities of Next-Token Prediction
2025
Cited
0
Loss Functions and Operators Generated by f-Divergences
2025
Cited
0
Joint Learning of Energy-based Models and their Partition Function
2025
Cited
0
Adaptive Methods through the Lens of SDEs: Theoretical Insights on the Role of Noise
arXiv.org · 2024
Cited
1
GLIMPSE: Generalized Local Imaging with MLPs
arXiv.org · 2024
Cited
1
CEMSSL: Conditional Embodied Self-Supervised Learning is All You Need for High-precision Multi-solution Inverse Kinematics of Robot Arms
IEEE International Conference on Acoustics, Speech, and Signal Processing · 2023
Cited
0
Embodied Self-Supervised Learning (EMSSL) with Sampling and Training Coordination for Robot Arm Inverse Kinematic Model Learning
International Conference on Development and Learning · 2023
Cited
2
Resume (English only)
Academic Achievements
2024: Paper on decoding-time realignment of language models accepted as Spotlight at ICML 2024
2024: Paper on evaluating routers in vision mixture-of-experts accepted by TMLR
2024: Paper on benchmarking wave-propagation PDE solvers accepted by TMLR
2023: Blog post replicating OpenAI’s first RLHF paper selected as Spotlight in ICLR 2024 blog track
2023: Paper on sparsity-constrained optimal transport accepted as Spotlight at ICLR 2023
2022: Paper on multiscale convolutional dictionary learning published in IEEE Transactions on Computational Imaging
2022: Paper on universal approximation under constraints accepted as Spotlight at ICLR 2022
2020: Paper on training sparse neural networks accepted at ICML 2020
2019: Paper on word vector denoising accepted at AAAI 2020
2019: Paper on training spiking neural networks for neuromorphic hardware was a Best Paper Finalist at IEEE NER 2019
Co-authors
51 total
Mathieu Blondel
Google
Ivan Dokmanić
Associate Professor, Department of Mathematics and Computer Science, University of Basel
Shangmin Guo
University of Edinburgh
Co-author 4
Johan Ferret
Research Scientist, Google DeepMind
Biao Zhang
Google
Tianqi Liu
Google DeepMind
Lyle Ungar
University of Pennsylvania
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up