Search Results for author:
Found 9 papers, 6 papers with code
Rethinking Patch Dependence for Masked Autoencoders
In this work, we re-examine inter-patch dependencies in the decoding mechanism of masked autoencoders (MAE).
LLM-grounded Video Diffusion Models
We show that LLMs are able to understand complex spatiotemporal dynamics from text alone and generate layouts that align closely with both the prompts and the object motion patterns typically observed in the real world.
Conformal Language Modeling
Translating this process to conformal prediction, we calibrate a stopping rule for sampling different outputs from the LM that get added to a growing set of candidates until we are confident that the output set is sufficient.
LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models
Our method significantly outperforms the base diffusion model and several strong baselines in accurately generating images according to prompts that require various capabilities, doubling the generation accuracy across four tasks on average.
PEOPL: Characterizing Privately Encoded Open Datasets with Public Labels
Allowing organizations to share their data for training of machine learning (ML) models without unintended information leakage is an open problem in practice.
AI Gone Astray: Technical Supplement
This study is a technical supplement to "AI gone astray: How subtle shifts in patient data send popular algorithms reeling, undermining patient safety."
Syfer: Neural Obfuscation for Private Data Release
We quantify privacy as the number of attacker guesses required to re-identify a single image (guesswork).
NeuraCrypt: Hiding Private Health Data via Random Neural Networks for Public Training
We propose to approximate this family of encoding functions through random deep neural networks.
Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning
Most successful information extraction systems operate with access to a large collection of documents.
