Meihua Dang
@meihuadang
Followers
584
Following
138
Media
1
Statuses
16
Ph.D student @StanfordAILab | Previous M.S. student @UCLA StarAI Lab
Los Angeles, CA
Joined March 2017
Don't wanna be here?
Send us removal request.
Explore trending content on Musk Viewer
SEND 21 BACK TO THE NOVEL
• 42155 Tweets
#BABA抜き最弱王決定戦
• 36545 Tweets
Knights
• 23587 Tweets
#三枝明那3DLIVE
• 22490 Tweets
Let's Join NuNew1stCon
• 21765 Tweets
ソロライブ
• 16779 Tweets
ドラえもんズ
• 13884 Tweets
Ollie
• 11717 Tweets
マッサマン
• 11712 Tweets
山田涼介
• 10256 Tweets
Excited to share that the checkpoints are online at 🤗 HuggingFace. Feel free to check it out!
SDXL-DPO:
SD1.5-DPO:
Excited to announce DPO has gone multi-modal! New paper out on RLHF for text-to-image diffusion models! We obtain large-scale state of the art results with 70% win rates against Stable Diffusion XL on human evals! Deep dive below 🧵
11
86
484
26
115
573
Our paper "Sparse Probabilistic Circuits via Pruning and Growing" was selected as Oral at
#NeurIPS2022
. Check here , or at poster session 3
#904
.
Can we scale up probabilistic circuits simply by increasing model sizes? 1/2
2
8
55
We propose a model pruning technique leveraging the probabilistic semantics of parameters; our approach can prune 97% of the model parameters without hurting performance, and based on which we are able to effectively learn large yet sparse probabilistic circuits. 3/3
1
0
4
We show that PC training performance plateaus as model size increases; most capacity in existing large PC structures is wasted: fully-connected parameter layers are only sparsely used. 2/3
1
0
3
@SCarbain
You are right. We train the model from the paired dataset end-to-end. One benefit of this method is that we don’t require a reward function e.g. PickScore.
1
0
0
@HorridWeasell
Just realized I had a typo, can you try with `guidance_scale=5`, the default one. Also updated the example code.
1
0
2
@tetraduzione
@martin_trapp
@guyvdb
@2020Pgm
As a follow up, PSDD also has strong determinism properties, which is used for logic constraints, but not needed for probabilistic circuits.
0
0
1