Vahid Behzadan
@behzadan.bsky.social
Professionally curious about the science of making bad decisions; AI safety and security researcher; Assistant Professor of CS and Data Science & Director of the Secure and Assured Intelligent Learning (SAIL) lab @ University of New Haven.
Reposted by Vahid Behzadan
I have converted a portion of my NLP Online Masters course to blog form. This is the progression I present that takes one from recurrent neural network to seq2seq with attention to transformer. mark-riedl.medium.com/transformers...
Transformers: Origins
An unofficial origin story of the transformer neural network architecture.
mark-riedl.medium.com
November 26, 2024 at 2:15 AM
I have converted a portion of my NLP Online Masters course to blog form. This is the progression I present that takes one from recurrent neural network to seq2seq with attention to transformer. mark-riedl.medium.com/transformers...
Reposted by Vahid Behzadan
Neurips reviews are now publicly available.
Don't forget to check out Open RL benchmark, very useful when implementing algorithms or checking performance/impact of hyperparameters.
openreview.net/forum?id=ZDv...
Don't forget to check out Open RL benchmark, very useful when implementing algorithms or checking performance/impact of hyperparameters.
openreview.net/forum?id=ZDv...
Open RL Benchmark: Comprehensive Tracked Experiments for...
In many Reinforcement Learning (RL) papers, learning curves are useful indicators to measure the effectiveness of RL algorithms. However, the complete raw data of the learning curves are rarely...
openreview.net
November 14, 2024 at 11:01 AM
Neurips reviews are now publicly available.
Don't forget to check out Open RL benchmark, very useful when implementing algorithms or checking performance/impact of hyperparameters.
openreview.net/forum?id=ZDv...
Don't forget to check out Open RL benchmark, very useful when implementing algorithms or checking performance/impact of hyperparameters.
openreview.net/forum?id=ZDv...
Reposted by Vahid Behzadan
I’m pretty excited about this one!
ALTA is A Language for Transformer Analysis.
Because ALTA programs can be compiled to transformer weights, it provides constructive proofs of transformer expressivity. It also offers new analytic tools for *learnability*.
arxiv.org/abs/2410.18077
ALTA is A Language for Transformer Analysis.
Because ALTA programs can be compiled to transformer weights, it provides constructive proofs of transformer expressivity. It also offers new analytic tools for *learnability*.
arxiv.org/abs/2410.18077
ALTA: Compiler-Based Analysis of Transformers
We propose a new programming language called ALTA and a compiler that can map ALTA programs to Transformer weights. ALTA is inspired by RASP, a language proposed by Weiss et al. (2021), and Tracr (Lin...
arxiv.org
October 24, 2024 at 3:31 AM
I’m pretty excited about this one!
ALTA is A Language for Transformer Analysis.
Because ALTA programs can be compiled to transformer weights, it provides constructive proofs of transformer expressivity. It also offers new analytic tools for *learnability*.
arxiv.org/abs/2410.18077
ALTA is A Language for Transformer Analysis.
Because ALTA programs can be compiled to transformer weights, it provides constructive proofs of transformer expressivity. It also offers new analytic tools for *learnability*.
arxiv.org/abs/2410.18077
Reposted by Vahid Behzadan
AI Safety Events and Training: 2024 Week 46 update
aisafetyeventsandtraining.substack.com/p/ai-safety-...
aisafetyeventsandtraining.substack.com/p/ai-safety-...
AI Safety Events and Training: 2024 Week 46 update
This is a weekly newsletter listing newly announced AI safety events and training programs.
aisafetyeventsandtraining.substack.com
November 15, 2024 at 2:17 AM
AI Safety Events and Training: 2024 Week 46 update
aisafetyeventsandtraining.substack.com/p/ai-safety-...
aisafetyeventsandtraining.substack.com/p/ai-safety-...
Reposted by Vahid Behzadan
This was seven years ago. I think about this often.
November 14, 2024 at 6:58 AM
This was seven years ago. I think about this often.
Reposted by Vahid Behzadan
I will be at #EMNLP2024! My student 𝙁𝙖𝙩𝙚𝙢𝙚 𝙃𝙖𝙨𝙝𝙚𝙢𝙞 𝘾𝙝𝙖𝙡𝙚𝙨𝙝𝙩𝙤𝙧𝙞 will present "On Evaluating Explanation Utility for Human-AI Decision Making in NLP" in the poster session on 𝗪𝗲𝗱𝗻𝗲𝘀𝗱𝗮𝘆 𝟭𝟬:𝟯𝟬𝗮𝗺: arxiv.org/abs/2407.03545 1/
On Evaluating Explanation Utility for Human-AI Decision Making in NLP
Is explainability a false promise? This debate has emerged from the insufficient evidence that explanations help people in situations they are introduced for. More human-centered, application-grounded...
arxiv.org
November 9, 2024 at 6:07 PM
I will be at #EMNLP2024! My student 𝙁𝙖𝙩𝙚𝙢𝙚 𝙃𝙖𝙨𝙝𝙚𝙢𝙞 𝘾𝙝𝙖𝙡𝙚𝙨𝙝𝙩𝙤𝙧𝙞 will present "On Evaluating Explanation Utility for Human-AI Decision Making in NLP" in the poster session on 𝗪𝗲𝗱𝗻𝗲𝘀𝗱𝗮𝘆 𝟭𝟬:𝟯𝟬𝗮𝗺: arxiv.org/abs/2407.03545 1/
Reposted by Vahid Behzadan
The AI Interdisciplinary Institute at the University of Maryland (AIM) is hiring
40 new faculty members
in all areas of AI, particularly:
- accessibility,
- sustainability,
- social justice, and
- learning;
building on computational, humanistic, or social scientific approaches to AI.
>
40 new faculty members
in all areas of AI, particularly:
- accessibility,
- sustainability,
- social justice, and
- learning;
building on computational, humanistic, or social scientific approaches to AI.
>
November 13, 2024 at 12:38 PM
The AI Interdisciplinary Institute at the University of Maryland (AIM) is hiring
40 new faculty members
in all areas of AI, particularly:
- accessibility,
- sustainability,
- social justice, and
- learning;
building on computational, humanistic, or social scientific approaches to AI.
>
40 new faculty members
in all areas of AI, particularly:
- accessibility,
- sustainability,
- social justice, and
- learning;
building on computational, humanistic, or social scientific approaches to AI.
>
Reposted by Vahid Behzadan
Schmidt Sciences is outlining the timeline for a new program to support research at the intersection of artificial intelligence and the humanities. Open call for proposals to come Dec 15. www.schmidtsciences.org/humanities-a...
Humanities and AI Virtual Institute - Schmidt Sciences
www.schmidtsciences.org
November 13, 2024 at 6:00 PM
Schmidt Sciences is outlining the timeline for a new program to support research at the intersection of artificial intelligence and the humanities. Open call for proposals to come Dec 15. www.schmidtsciences.org/humanities-a...
Reposted by Vahid Behzadan
This one is a study on voting-based evaluation to comparisons of models in LMSYS Chatbot Arena leaderboard, by independent researcher Nick Ryan. Simulations show that two Condorcet-consistent methods (Copeland and Ranked Pairs) can be robust to uncertain/noisy evals.
nickcdryan.com/2024/09/06/u...
nickcdryan.com/2024/09/06/u...
November 13, 2024 at 10:23 AM
This one is a study on voting-based evaluation to comparisons of models in LMSYS Chatbot Arena leaderboard, by independent researcher Nick Ryan. Simulations show that two Condorcet-consistent methods (Copeland and Ranked Pairs) can be robust to uncertain/noisy evals.
nickcdryan.com/2024/09/06/u...
nickcdryan.com/2024/09/06/u...
Reposted by Vahid Behzadan
Honestly very disappointed since joining BlueSky, this is not the weather app I was hoping for
November 13, 2024 at 9:34 PM
Honestly very disappointed since joining BlueSky, this is not the weather app I was hoping for
Reposted by Vahid Behzadan
How Far is Video Generation from World Model: A Physical Law Perspective https://arxiv.org/abs/2411.02385v1 #AI #video
November 10, 2024 at 1:30 AM
How Far is Video Generation from World Model: A Physical Law Perspective https://arxiv.org/abs/2411.02385v1 #AI #video
Reposted by Vahid Behzadan
NSF makes you say who you got conflicts (coauthored) with. We (really just Jordan Matelsky) just built you a tool for that. Literally one click: bib.experiments.kordinglab.com/nsf-coa
NSF COA | Jordan Matelsky
bib.experiments.kordinglab.com
November 11, 2024 at 8:11 PM
NSF makes you say who you got conflicts (coauthored) with. We (really just Jordan Matelsky) just built you a tool for that. Literally one click: bib.experiments.kordinglab.com/nsf-coa
Reposted by Vahid Behzadan
New York Theory Day finally returns on December 6, 2024, after being put on hiatus during COVID.
Will be held at @nyutandon.bsky.social in Brooklyn. Registration is free!
Ft stellar speakers Amir Abboud, Sanjeev Khanna, Rotem Oshman, and
Ron Rothblum!
sites.google.com/view/nyctheo...
Will be held at @nyutandon.bsky.social in Brooklyn. Registration is free!
Ft stellar speakers Amir Abboud, Sanjeev Khanna, Rotem Oshman, and
Ron Rothblum!
sites.google.com/view/nyctheo...
November 14, 2024 at 1:06 AM
New York Theory Day finally returns on December 6, 2024, after being put on hiatus during COVID.
Will be held at @nyutandon.bsky.social in Brooklyn. Registration is free!
Ft stellar speakers Amir Abboud, Sanjeev Khanna, Rotem Oshman, and
Ron Rothblum!
sites.google.com/view/nyctheo...
Will be held at @nyutandon.bsky.social in Brooklyn. Registration is free!
Ft stellar speakers Amir Abboud, Sanjeev Khanna, Rotem Oshman, and
Ron Rothblum!
sites.google.com/view/nyctheo...