Ziming Liu @lzm_mlsys

PhD Candidate at SoC,@NUSingapore, advised by @YangYou1991. Working on efficient ML system and algorithms. Past:@MSFTResearch @BytedanceTalk @HPCAITech maruyamaaya.github.io Singapore Joined January 2023

Tweets

17
Followers

97
Following

55
Likes

10

Victor.Kai Wang @VictorKaiWang1

3 months ago

Customizing Your LLMs in seconds using prompts🥳! Excited to share our latest work with @HPCAILab, @VITAGroupUT, @k_schuerholt, @YangYou1991, @mmbronstein, @damianborth : Drag-and-Drop LLMs(DnD). 2 features: tuning-free, comparable or even better than full-shot tuning.(🧵1/8)

5 75 108 16K 58

Download Video

Yang You @YangYou1991

7 months ago

RAS yields over 2x the acceleration with almost no image quality loss! Nice work and congrats!

Ziming Liu @lzm_mlsys

7 months ago

RAS yields over 2x the acceleration with almost no image quality loss! Nice work and congrats!

6 41 188 18K 104

Download Video

0 2 8 2K 2

Victor.Kai Wang @VictorKaiWang1

8 months ago

Generating ~200 million parameters in just minutes! 🥳 Excited to share our work with @MTDovent , @heisejiasuo96 , and @YangYou1991: 'Recurrent Diffusion for Large-Scale Parameter Generation' (RPG for short). Example: Obtain customized models using prompts (see below). (🧵1/8)

4 88 287 43K 222

Download Video

Shijie Wang @ShijieWang20

9 months ago

How can we better animate images solely following text descriptions? We present Motion Focal Loss (MotiF) (arxiv.org/abs/2412.16153) to better align motions with text descriptions in text-image-to-video (TI2V) task and release TI2V-Bench, a comprehensive TI2V benchmark. (1/n)

6 11 54 6K 22

Download Video

Yang Luo @YangL_7

9 months ago

Training-free Video Enhancement: Achieved 🎉 Nice work with @oahzxl @shaowenqi126301 @VictorKaiWang1 @VITAGroupUT @YangYou1991 et al. Non-trivial enhancement, training-free, and plug-and-play 🥳 Blog: oahzxl.github.io/Enhance_A_Vide… (🧵1/6)

9 86 254 45K 175

Download Video

Together AI @togethercompute

2 years ago

We are excited that @Leon75421958 is joining the stellar Together AI Research team as VP Frontier Technologies. Leon has driven LLM ecosystem innovations such as Deepspeed and Project Brainwave. Leon will help our mission to build the fastest cloud for generative AI.

5 5 31 7K 1

Download Image

Ziming Liu @lzm_mlsys

2 years ago

Really enjoyed chipping in on this project. It's been awesome!😃

Yang You @YangYou1991

2 years ago

Really enjoyed chipping in on this project. It's been awesome!😃

5 67 320 89K 201

Download Image

0 0 3 108 0

Ziming Liu @lzm_mlsys

2 years ago

I would like to introduce our paper about Pipeline Parallelism that has been accepted by SC23. We proposed a new pipeline parallelism scheme that reduces the bubble ratio and increases the model training throughput. The full paper is available at arxiv.org/abs/2308.15762.