Sign in

Roy

@roymiles.bsky.social
629 followers 252 following 28 posts

Research Scientist @Noah's Ark Lab, Huawei PhD Imperial College London roymiles.github.io Working on multi-modality and efficient ML

PostsRepliesMedia
Roy @roymiles.bsky.social · 09/12/2024
forgot the hashtag #neurips2024 😅
010
Roy @roymiles.bsky.social · 09/12/2024
Hey! I will be at NeurIPS @neuripsconf.bsky.social this week (friday 13th) presenting our paper VeLoRA. tldr; simple method for compressing gradients with a coarse reconstruction during the backwards pass. Significant memory reductions while being complimentary to LoRA! github.com/roymiles/VeL...
160
Roy @roymiles.bsky.social · 28/11/2024
Added!
000
Roy @roymiles.bsky.social · 28/11/2024
Added!
000
Roy @roymiles.bsky.social · 28/11/2024
Hey! I have added you
010
Roy @roymiles.bsky.social · 28/11/2024
Added!
000
Roy @roymiles.bsky.social · 28/11/2024
Hey! I have added you
010
Roy @roymiles.bsky.social · 28/11/2024
Hey! I have added you
100
Roy @roymiles.bsky.social · 28/11/2024
Cool! I have added you
010
Roy @roymiles.bsky.social · 28/11/2024
Of course! I have added you now
100
Roy @roymiles.bsky.social · 27/11/2024
Cool! I have added you.
100
Roy @roymiles.bsky.social · 27/11/2024
Haha I wasn't really thinking about it like that. In either case I have added you to this one too.
020
Roy @roymiles.bsky.social · 27/11/2024
Added you in 😁
010
Roy @roymiles.bsky.social · 27/11/2024
Hey, I have added you! oops yea I did see that one. Perhaps this one can be a bit more broader with other modalities.
220
Roy @roymiles.bsky.social · 27/11/2024
Added both of you!
010
Roy @roymiles.bsky.social · 27/11/2024
Added!
000
Roy @roymiles.bsky.social · 27/11/2024
Cool, added!
010
Roy @roymiles.bsky.social · 27/11/2024
Hey! Yea yours probably overlaps a lot 😅 I have added you and will add some others from there too.
010
Roy @roymiles.bsky.social · 27/11/2024
Sweet, I have added you!
010
Roy @roymiles.bsky.social · 27/11/2024
I made a starter pack for people working or interested in multi-modality learning. It would be good to add lots more people so do comment and I'll add! go.bsky.app/97fAH2N
15206
Reposted by Roy
Benedikt Kolbeinsson @handle.invalid · 27/11/2024
Our BMVC poster is today! Knowledge distillation can work in cross-task settings and even with a randomly initialised teacher! Our inverted projection decomposes into knowledge transfer and spectral regularisation, enabling teacher-free distillation with improvements on ImageNet-1K at no extra cost
arxiv.org
073
Roy @roymiles.bsky.social · 23/11/2024
Hey, this is great and relevant for me. Would love to join if there is still space!
110
Roy @roymiles.bsky.social · 22/11/2024
This is really great thanks! Could I be added to the AI starter pack too 😅?
020
Roy @roymiles.bsky.social · 22/11/2024
Would be great to be added too!
010
Roy @roymiles.bsky.social · 22/11/2024
Some related work worth checking out if you find this cool. mbaradad.github.io/shaders21k/ - learning good visual features from procedurally generated images. arxiv.org/abs/2403.14494 - distillation from randomly weighted teachers.
020
Roy @roymiles.bsky.social · 21/11/2024
Sounds great! Would love to join if there is space.
000
Roy @roymiles.bsky.social · 21/11/2024
p.s. please add me to any starter packs! 😁
100
Roy @roymiles.bsky.social · 21/11/2024
Hi Bluesky! I'm currently working on multi-modality learning and efficient ML (mobile devices). Hoping to regularly post about any interesting topics I find cool (ai, maths, physics). Looking forward to seeing how this platforms grows and meeting you all!
130
Roy @roymiles.bsky.social · 20/11/2024
Hi Kostas! Could you add me as well? :D
010