EMNLP vs AACL commitment: Meta 3.5, reviews 3/3/4, what to do?[D]
I'm trying to decide whether to commit my ARR May 2026 paper to EMNLP or AACL. (first time solo independent author). Final reviews after rebuttal (OA/Confidence/Excitement…
Latest
How Symmetric Are the Insides of a Go Network? [R]
I just now posted a small research / ML interp study on symmetries inside the neural nets for an open source Go-playing program that I maintain…
[D] Simple Questions Thread
Please post your questions here instead of creating a new thread. Encourage others who create new posts for questions to post here instead! Thread will stay…
Github repo to learn the OPD/OPSD and how they perform compared to GRPO, on a consumer grade GPU [P]
I am trying to learn concepts like On Policy Distillation (OPD), On Policy Self Distillation (OPSD) and how do they compare to RL algorithms like GRPO.…
VLMs can score well on benchmarks, while silently erasing meaningful terms and including hallucinate bias [P]
While working with VLMs for report generation on chest x-rays (RRG), we noticed that evaluation metrics are flawed. Flawed in a sense where they rewarded repetitive…
ARR May Meta Review[D]
This time we have seen the worst meta reviews...may be people are unintersted to do reviews...in my case they did not acknowledge the report at all…
What should we do for EMNLP commitment deadline? [R]
We received the reviews, but they don't mention whether we should submit a revised version. Should we prepare one? I also couldn't find anywhere to upload…
Meta score EMNLP 2026 [D]
Any one got meta score 2.5 (borderline finding) and still accepted to findings previously?? In my case meta review didnot acknowledge the reporting against a wrong…
I have trained a model to predict my blood sugar [P]
It's an encoder-only transformer that consumes past(blood glucose + carbs + insulin) and future(carbs + insulin) and predicts future blood glucose for the next 2 hours.…
Detecting *whether* text exists in an image? [D]
Hi, I was looking to be able to very quickly detect *whether* text exists in an image (binary classification). Being a simple-ish task, there isn't substantial…