Itamar Avitan
@avitanit.bsky.social
📤 26
đź“Ą 55
đź“ť 11
PhD candidate at Ben-Gurion University.
pinned post!
Excited to share my first paper: Model–Behavior Alignment under Flexible Evaluation: When the Best-Fitting Model Isn’t the Right One (NeurIPS 2025). link below.
4 months ago
1
18
6
reposted by
Itamar Avitan
Lukas Muttenthaler
5 months ago
🥳 I am incredibly humbled and grateful to share that our work, "Aligning machine and human visual representations across abstraction levels," has been published today in
@nature.com
⬇️
add a skeleton here at some point
0
21
5
reposted by
Itamar Avitan
herrick fung
5 months ago
No two humans behave exactly alike. But what about neural networks? We found early evidence that human-like individual differences in behavior emerge from networks trained with different initializations. Here’s a peek at our results—to be presented at UniReps & DBM @NeurIPS. Full paper on the way!
loading . . .
Human-like individual differences emerge from random weight initializations in neural networks
Much of AI research targets the behavior of an average human, a focus that traces to Turing's imitation game. Yet, no two human individuals behave exactly alike. In this study, we show that artificial...
https://www.biorxiv.org/content/10.1101/2025.10.25.684448v1
2
11
4
Presenting our
#NeurIPS2025
work on model–behavior alignment today. Could we even recognize the “right” model of behavior under flexible evaluation? Come chat about DNNs & human visual preception! Hall C-E #2010 Friday (today!) 4:30 – 7:30 PM
neurips.cc/virtual/2025...
loading . . .
NeurIPS Poster Model–Behavior Alignment under Flexible Evaluation: When the Best-Fitting Model Isn’t the Right OneNeurIPS 2025
https://neurips.cc/virtual/2025/loc/san-diego/poster/116404
4 months ago
0
3
2
Excited to share my first paper: Model–Behavior Alignment under Flexible Evaluation: When the Best-Fitting Model Isn’t the Right One (NeurIPS 2025). link below.
4 months ago
1
18
6
you reached the end!!
feeds!
log in
