Xinlei Chen
@endernewton
Followers
2K
Following
144
Statuses
46
RT @_rohitgirdhar_: Super excited to share some recent work that shows that pure, text-only LLMs, can see and hear without any training! Ou…
0
39
0
RT @s_scardapane: *On the Surprising Effectiveness of Attention Transfer for Vision Transformers* by @tydsh @BeidiChen @pathak2206 @enderne…
0
36
0
@tokenpilled65B Also -- didn't realize your ID starts with `token` and ends with xxB -- sounds like you are destined for tokenization scaling @tokenpilled65B :P
0
0
4
RT @shiryginosar: New paper! A SSL object-centric 2.1D image representation using 3D Gaussians, extending MAE with a Gaussian bottleneck. W…
0
61
0
RT @liuzhuang1234: How far is an LLM from not only understanding but also generating visually? Not very far! Introducing MetaMorph---a mu…
0
130
0
RT @alexlioralexli: I'm presenting our #NeurIPS2024 work on Attention Transfer today! Key finding: Pretrained representations aren't essen…
0
20
0
RT @LiruiWang1: HPT will be presented at Neurips in Vancouver East Exhibit Hall A-C #4210 on Thursday at 11 next week! Unfortunately, I can…
0
3
0
I am looking for an intern to do research together next summer. Possible topics: representation learning, network architecture, and in general understanding what's going on :P. Please apply ( and email me (xinleic@meta.com) if interested.
10
42
447
1
0
2
0
0
1
1
0
1
0
0
3