Ruixiang Tang retweeted
.@RuixiangT and Yu-Neng (Allen) Chuang discuss "The Science of Detecting LLM-Generated Text" (bit.ly/48Nnqzb) and the challenge of adding watermarks to such text in an original video, bit.ly/4apzA2r
Ruixiang Tang retweeted
Should we choose to use LLMs or smaller finetuned models in practical use cases? Take a look at our survey arxiv.org/abs/2304.13712 , which covers NLU tasks, Generation tasks, Knowledge-intensive tasks, abilities regarding scaling, some miscellaneous and real-world tasks.
Our work is on The Daily Swig😀
portswigger.net/daily-swig/t…
3
Mitigating Gender Bias in Captioning Systems by Rxtang link.medium.com/fucuIv6RV7
4
Ruixiang Tang retweeted
AI Paper Summary Video
An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networks
Paper: arxiv.org/pdf/2006.08131.pdf
Summary by: Dott. Fabio Mardero (Data Scientist & Non-Life Actuarial Specialist)
Video: youtu.be/CkVGb2_LR1s
#DeepLearning #NeuralNetworks
Cool !!!
Excited to announce "BERTology Meets Biology: Interpreting Attention in Protein Language Models" including new tool for visualizing attention in 3D protein structure (1/5):
Paper: arxiv.org/abs/2006.15222
Blog: blog.einstein.ai/provis
Code: github.com/salesforce/provis
2
Ruixiang Tang retweeted
A recent work on Trojan Attack on Deep Nets, certainly I like the title :)
Paper: arxiv.org/pdf/2006.08131.pdf
Codes: github.com/trx14/TrojanNet







