mechcoder @mechcoder

stay hydrated Amsterdam Joined January 2017

Tweets

177
Followers

458
Following

259
Likes

1K

Fantine Huot @fantinehuot

5 months ago

I’m presenting “Agents’ Room: Narrative Generation through Multi-step Collaboration” at the #ICLR2025 poster session at 3pm today. come chat about multi-agent systems for complex writing tasks! link: iclr.cc/virtual/2025/p… paper: arxiv.org/abs/2410.02603

1 1 6 210 0

Download Image

Ibrahim Alabdulmohsin | إبراهيم العبدالمحسن @ibomohsin

7 months ago

🔥Excited to introduce RINS - a technique that boosts model performance by recursively applying early layers during inference without increasing model size or training compute flops! Not only does it significantly improve LMs, but also multimodal systems like SigLIP. (1/N)

2 12 38 6K 21

Download Image

Ibrahim Alabdulmohsin | إبراهيم العبدالمحسن @ibomohsin

a year ago

Want your VLM to reflect the world's rich diversity 🌍? We’re very excited to share our recent research on this topic. TLDR: to build truly inclusive models that work for everyone, don’t filter by English, and check out our recommended evaluation benchmarks. (1/7)

3 28 139 56K 60

Download Image

Mathilde Caron @mcaron31

2 years ago

Happy to introduce GERALD - our new VLM that recognizes 6M+ entities, an exciting step towards Web-scale visual entity recognition! Predictions are simply made by auto-regressively decoding a code representing the entity name. Check out our CVPR24 paper: arxiv.org/abs/2403.02041

2 17 129 11K 36

Ibrahim Alabdulmohsin | إبراهيم العبدالمحسن @ibomohsin

2 years ago

Excited to share our #ICLR2024 paper, focused on reducing bias in CLIP models. We study the impact of data balancing and come up with some recommendations for how to apply it effectively. Surprising insights included! Here are 3 main takeaways.

3 23 88 17K 68

Download Image

mechcoder @mechcoder

2 years ago

Vision encoders pretrained with captioning can match or even outperform vision encoders trained contrastively when finetuned downstream! Check out our latest study lead by @mtschannen

Lucas Beyer (bl16) @giffmana

2 years ago

Vision encoders pretrained with captioning can match or even outperform vision encoders trained contrastively when finetuned downstream! Check out our latest study lead by @mtschannen

18 90 573 212K 299

Download Image

1 0 10 1K 1

Sharon Goldman @sharongoldman

2 years ago

More AI "doomer" pushback. Thanks to @kchonyc for talking to me for this one. venturebeat.com/ai/top-ai-rese…

21 98 412 100K 77

Accepted papers at TMLR @TmlrPub

2 years ago

Dual PatchNorm Manoj Kumar, Mostafa Dehghani, Neil Houlsby. Action editor: Yunhe Wang. openreview.net/forum?id=jgMqv… #layernorm #layernorms #patchnorm

1 8 19 5K 1

Mostafa Dehghani @m__dehghani

3 years ago

1/ There is a huge headroom for improving capabilities of our vision models and given the lessons we've learned from LLMs, scaling is a promising bet. We are introducing ViT-22B, the largest vision backbone reported to date: arxiv.org/abs/2302.05442