Search Results for author: Tianlin Liu

Found 16 papers, 7 papers with code

Direct Language Model Alignment from Online AI Feedback

no code implementations7 Feb 2024 Shangmin Guo, Biao Zhang, Tianlin Liu, Tianqi Liu, Misha Khalman, Felipe Llinares, Alexandre Rame, Thomas Mesnard, Yao Zhao, Bilal Piot, Johan Ferret, Mathieu Blondel

Moreover, responses in these datasets are often sampled from a language model distinct from the one being aligned, and since the model evolves over training, the alignment phase is inevitably off-policy.

Language Modelling

Routers in Vision Mixture of Experts: An Empirical Study

no code implementations29 Jan 2024 Tianlin Liu, Mathieu Blondel, Carlos Riquelme, Joan Puigcerver

Routers for sparse MoEs can be further grouped into two variants: Token Choice, which matches experts to each token, and Expert Choice, which matches tokens to each expert.

Language Modelling

GLIMPSE: Generalized Local Imaging with MLPs

1 code implementation1 Jan 2024 AmirEhsan Khorashadizadeh, Valentin Debarnot, Tianlin Liu, Ivan Dokmanić

Deep learning is the current de facto state of the art in tomographic imaging.

Sparsity-Constrained Optimal Transport

no code implementations30 Sep 2022 Tianlin Liu, Joan Puigcerver, Mathieu Blondel

The smoothness of the objectives increases as $k$ increases, giving rise to a trade-off between convergence speed and sparsity of the optimal plan.

Universal Approximation Under Constraints is Possible with Transformers

no code implementations ICLR 2022 Anastasis Kratsios, Behnoosh Zamanlooy, Tianlin Liu, Ivan Dokmanić

Many practical problems need the output of a machine learning model to satisfy a set of constraints, $K$.

Finding trainable sparse networks through Neural Tangent Transfer

1 code implementation ICML 2020 Tianlin Liu, Friedemann Zenke

Deep neural networks have dramatically transformed machine learning, but their memory and energy demands are substantial.

General Classification

Causally Denoise Word Embeddings Using Half-Sibling Regression

1 code implementation24 Nov 2019 Zekun Yang, Tianlin Liu

Distributional representations of words, also known as word vectors, have become crucial for modern natural language processing tasks due to their wide applications.

Causal Inference regression +2

Harnessing Slow Dynamics in Neuromorphic Computation

no code implementations28 May 2019 Tianlin Liu

We empirically show that, by harnessing slow dynamics, spiking neural networks on analog neuromorphic systems can gain non-trivial performance boosts on a battery of real-time signal processing tasks.

A Consistent Method for Learning OOMs from Asymptotically Stationary Time Series Data Containing Missing Values

no code implementations11 Aug 2018 Tianlin Liu

In the traditional framework of spectral learning of stochastic time series models, model parameters are estimated based on trajectories of fully recorded observations.

Time Series Time Series Analysis

Binary Compressive Sensing via Smoothed $\ell_0$ Gradient Descent

no code implementations30 Jan 2018 Tianlin Liu, Dae Gwan Lee

We present a Compressive Sensing algorithm for reconstructing binary signals from its linear measurements.

Compressive Sensing

Cannot find the paper you are looking for? You can Submit a new open access paper.