Search Results for author: Ishaan Gulrajani

Found 11 papers, 10 papers with code

Likelihood-Based Diffusion Language Models

1 code implementation30 May 2023 Ishaan Gulrajani, Tatsunori B. Hashimoto

On the algorithmic front, we introduce several methodological improvements for the maximum-likelihood training of diffusion language models.

Language Modelling

AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback

1 code implementation22 May 2023 Yann Dubois, Xuechen Li, Rohan Taori, Tianyi Zhang, Ishaan Gulrajani, Jimmy Ba, Carlos Guestrin, Percy Liang, Tatsunori B. Hashimoto

As a demonstration of the research possible in AlpacaFarm, we find that methods that use a reward model can substantially improve over supervised fine-tuning and that our reference PPO implementation leads to a +10% improvement in win-rate against Davinci003.

Instruction Following

Diffusion-LM Improves Controllable Text Generation

1 code implementation27 May 2022 Xiang Lisa Li, John Thickstun, Ishaan Gulrajani, Percy Liang, Tatsunori B. Hashimoto

Controlling the behavior of language models (LMs) without re-training is a major open problem in natural language generation.

Language Modelling Text Generation

Towards GAN Benchmarks Which Require Generalization

no code implementations ICLR 2019 Ishaan Gulrajani, Colin Raffel, Luke Metz

For many evaluation metrics commonly used as benchmarks for unconditional image generation, trivially memorizing the training set attains a better score than models which are considered state-of-the-art; we consider this problematic.

Image Generation Memorization +1

Invariant Risk Minimization

14 code implementations5 Jul 2019 Martin Arjovsky, Léon Bottou, Ishaan Gulrajani, David Lopez-Paz

We introduce Invariant Risk Minimization (IRM), a learning paradigm to estimate invariant correlations across multiple training distributions.

Domain Generalization Image Classification +1

GANSynth: Adversarial Neural Audio Synthesis

5 code implementations ICLR 2019 Jesse Engel, Kumar Krishna Agrawal, Shuo Chen, Ishaan Gulrajani, Chris Donahue, Adam Roberts

Efficient audio synthesis is an inherently difficult machine learning task, as human perception is sensitive to both global structure and fine-scale waveform coherence.

Audio Generation

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