Main

processing priority

3

site type

0 (generic, awaiting analysis)

review version

11

html import

20 (imported)

Events

first seen date

2024-11-11 03:11:45

expired found date

-

created at

2024-11-11 03:11:45

updated at

2024-11-11 03:11:45

Domain name statistics

length

20

crc

18336

tld

86

nm parts

0

nm random digits

0

nm rare letters

0

Connections

is subdomain of id

87719371 (github.io)

previous id

0

replaced with id

0

related id

-

dns primary id

0

dns alternative id

0

lifecycle status

0 (unclassified, or currently active)

Subdomains and pages

deleted subdomains

0

page imported products

0

page imported random

0

page imported parking

0

Error counters

count skipped due to recent timeouts on the same server IP

0

count content received but rejected due to 11-799

0

count dns errors

0

count cert errors

0

count timeouts

0

count http 429

0

count http 404

0

count http 403

0

count http 5xx

0

next operation date

-

Server

server bits

server ip

-

Mainpage statistics

mp import status

20

mp rejected date

-

mp saved date

-

mp size orig

22305

mp size raw text

4824

mp inner links count

0

mp inner links status

1 (no links)

Open Graph

title

Align-Prop

description

We propose AlignProp, a method that uses reward backpropogation for the alignment of large-scale text-to-image diffusion models.

site name

author

updated

2026-01-25 04:25:29

raw text

Align-Prop Aligning Text-to-Image Diffusion Models with Reward Backpropagation Mihir Prabhudesai 1 , Anirudh Goyal 2 , Deepak Pathak 1 , Katerina Fragkiadaki 1 1 Carnegie Mellon University, 2 Google DeepMind Paper Code Your browser does not support the video tag. AlignProp is a direct backpropagation-based approach to finetune text-to-image diffusion models for desired reward function. Above we show finetuning results for various reward functions. Abstract Text-to-image diffusion models have recently emerged at the forefront of image generation, powered by very large-scale unsupervised or weakly supervised text-to-image training datasets. Due to the unsupervised training, controlling their behavior in downstream tasks, such as maximizing human-perceived image quality, image-text alignment, or ethical image generation, is difficult. Recent works finetune diffusion models to downstream reward functions using vanilla reinf...

Text analysis

redirect type

0 (-)

block type

0 (no issues)

detected language

1 (English)

category id

AI [en] (229)

index version

2025123101

spam phrases

0

Text statistics

text nonlatin

1

text cyrillic

0

text characters

3819

text words

644

text unique words

315

text lines

58

text sentences

28

text paragraphs

5

text words per sentence

23

text matched phrases

10

text matched dictionaries

2

RSS

rss path

rss status

1 (priority 1 already searched, no matches found)

rss found date

-

rss size orig

0

rss items

0

rss spam phrases

0

rss detected language

0 (awaiting analysis)

inbefore feed id

-

inbefore status

0 (new)

Sitemap

sitemap path

sitemap status

1 (priority 1 already searched, no matches found)

sitemap review version

2

sitemap urls count

0

sitemap urls adult

0

sitemap filtered products

0

sitemap filtered videos

0

sitemap found date

-

sitemap process date

-

sitemap first import date

-

sitemap last import date

-