dheeru dua Profile
dheeru dua

@ddua17

Followers
155
Following
251
Media
0
Statuses
32

Joined April 2014
Don't wanna be here? Send us removal request.
@ddua17
dheeru dua
4 months
RT @JonathanBerant: Hi ho!. New work: With amazing collabs @jacobeisenstein @jdjdhekchbdjd @adamjfisch @ddua17 @fan….
0
19
0
@ddua17
dheeru dua
2 years
RT @DrJimFan: I've been asked what's the biggest thing in 2024 other than LLMs. It's Robotics. Period. We are ~3 years away from the ChatGP….
0
347
0
@ddua17
dheeru dua
2 years
RT @yanaiela: What do you know, when you make comparable experiments, ICL and fine-tuning (FT) aren't that different!.We find that in- and….
0
4
0
@ddua17
dheeru dua
2 years
RT @zeqiuwu1: F in RLHF is overall preference, which conveys limited info🙁. We introduce Fine-Grained RLHF🚀and train LMs with explicit feed….
0
128
0
@ddua17
dheeru dua
2 years
RT @srush_nlp: Do we need Attention? (v0 : .Slides for a survey talk summarizing recent Linear RNN models with a fo….
0
173
0
@ddua17
dheeru dua
2 years
RT @_anthonychen: Under-rated is how hard it is to create datasets that stand the test of time. And DROP from my labmate @ddua17 has done j….
0
11
0
@ddua17
dheeru dua
2 years
RT @orionweller: 🚨 Negation misunderstanding in IR systems can lead to dire outcomes, as seen in the quoted Google Search example from 2021….
0
12
0
@ddua17
dheeru dua
2 years
RT @sameer_: This was a truly amazing year for #NLProc, and I tried my best to summarize it as well as I could. Thank for you the invitatio….
0
33
0
@ddua17
dheeru dua
3 years
RT @ChristophMolnar: A lot of machine learning research has detached itself from solving real problems, and created their own "benchmark-is….
0
661
0
@ddua17
dheeru dua
4 years
RT @annargrs: #NLPaperAlert: QA Dataset Explosion!🔥.A survey of 200+ QA/RC datasets proposing a taxonomy of formats & reasoning skills. Als….
0
69
0
@ddua17
dheeru dua
4 years
RT @Mitchnw: Sharing some takeaways from Learning Neural Network Subspaces, a fun project we learned a lot from and hopefully you can too.….
0
69
0
@ddua17
dheeru dua
4 years
RT @ProfFeynman: The difference between information and knowledge:
Tweet media one
0
4K
0
@ddua17
dheeru dua
4 years
RT @ProfFeynman: Equations that changed the world. 🧠
Tweet media one
0
2K
0
@ddua17
dheeru dua
4 years
RT @bneyshabur: Some people say that one shouldn't care about publication and the quality matters. However, the job market punishes those w….
0
181
0
@ddua17
dheeru dua
5 years
RT @twimlai: Today we continue the 2020 AI Rewind series, joined by @Sameer_ Singh, who helped us break down NLP in 2020 into 4 categories,….
0
10
0
@ddua17
dheeru dua
5 years
RT @alfcnz: This week we went through the second part of my lecture on latent variable 👻 energy 🔋 based models. 🤓. We've warmed up a little….
0
76
0
@ddua17
dheeru dua
5 years
RT @nlpmattg: Evaluating NLP Models via Contrast Sets. New work that is a collaboration between 26 people at 10 institutions (!). https://t….
0
79
0
@ddua17
dheeru dua
5 years
RT @TheGradient: 1/5 Self-Distillation loop (feeding predictions as new target values & retraining) improves test accuracy. But why? We sho….
0
187
0
@ddua17
dheeru dua
5 years
RT @pdasigi: #nlphighlights 105: Question Generation with @raosudha89. We discussed an overview of the settings in which you would want to….
0
12
0