📢 Introducing our #ECCV2024 work, COCO-ReM (COCO Refined Masks), for more reliable benchmarking of object detectors, crucial for the future of object detection research.
Paper: https://t.co/Ef1t8ORbVo
Code: https://t.co/Ef1t8ORbVo
Website: https://t.co/MGSZuxv1cr
Announcing RefCOCO-M, a refreshed RefCOCO with pixel-accurate masks and the problematic prompts removed. Better data for better evaluation.
https://t.co/BqayflYv2v
📢 Introducing our #ECCV2024 work, COCO-ReM (COCO Refined Masks), for more reliable benchmarking of object detectors, crucial for the future of object detection research.
Paper: https://t.co/Ef1t8ORbVo
Code: https://t.co/Ef1t8ORbVo
Website: https://t.co/MGSZuxv1cr
I came on an H1B “specialty occupation” visa and there’s no way I could have afforded a $100K fee. The US has just made it virtually impossible for people like me to come here
🚨 #MLRC2025 Announcing the best and outstanding paper awards!
Best paper award goes to https://t.co/72tKS22EoQ
Congratulations! 🎉🎉 Full list of accepted papers at https://t.co/6ab3SMpEm0
LLM post-training requires a reward model for preference alignment.
But is it necessary?
In our new preprint, we show that the language model is itself a preference classifier & reward model isn't needed.
We can self-improve a model by using its own feedback!
Had an excellent time presenting our paper at #ECCV2024.
Thanks to all the kind people who took interest.
A special thanks to my co authors who made everything possible @ShwetaSingh952@praeclarumjj@humphrey_shi@jcjohnss@kdexd
Data, Code, Paper on https://t.co/MGSZuxutmT
A method to refine and correct labels in your dataset!! A very useful poster and great work done by @ionydv and @iitroorkee! Happy to see a presentation from 🇮🇳❤️ #ECCV2024
Excited to present our work at #ECCV2024 in Poster Session 5 on 3rd Oct, Thursday from 10:30am-12:30pm at Poster #140. Do Visit!
Project website: https://t.co/MGSZuxutmT
Conference Page: https://t.co/zIoBag6ZUV
Code: https://t.co/fw9UtA4EPh