Search Results for author:
Found 8 papers, 2 papers with code
SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors
Extensive experiments on language and vision benchmarks show that SVFT recovers up to 96% of full fine-tuning performance while training only 0. 006 to 0. 25% of parameters, outperforming existing methods that only recover up to 85% performance using 0. 03 to 0. 8% of the trainable parameter budget.
Put Myself in Your Shoes: Lifting the Egocentric Perspective from Exocentric Videos
We investigate exocentric-to-egocentric cross-view translation, which aims to generate a first-person (egocentric) view of an actor based on a video recording that captures the actor from a third-person (exocentric) perspective.
On a Foundation Model for Operating Systems
This paper lays down the research agenda for a domain-specific foundation model for operating systems (OSes).
DataComp: In search of the next generation of multimodal datasets
Multimodal datasets are a critical component in recent breakthroughs such as Stable Diffusion and GPT-4, yet their design does not receive the same research attention as model architectures or training algorithms.
Robust Compressed Sensing MR Imaging with Deep Generative Priors
The CSGM framework (Bora-Jalal-Price-Dimakis'17) has shown that deep generative priors can be powerful tools for solving inverse problems.
Compressed Sensing with Invertible Generative Models and Dependent Noise
We study image inverse problems with invertible generative priors, specifically normalizing flow models.
Compressed Sensing with Approximate Priors via Conditional Resampling
We characterize the measurement complexity of compressed sensing of signals drawn from a known prior distribution, even when the support of the prior is the entire space (rather than, say, sparse vectors).
Approximate Probabilistic Inference with Composed Flows
We study the problem of probabilistic inference on the joint distribution defined by a normalizing flow model.
