VultronRetriever family of models released on HuggingFace![R]
Thrilled to announce the VultronRetriever family of models, which were announced during Raise Summit Paris and demonstrated running Q&A and embedding documents on the iPhone, fully…
Latest
Withdraw from ACL ARR and resubmit to a workshop? [D]
Hey guys, I received mediocre scores for my EMNLP paper during the May ACL ARR cycle: 2.5/3, 3/4, 2.5/4. The paper is in the Interpretability track.…
Predicting human preference for generated image pairs using HPSv3 [P]
Hey! I'm looking for ways to predict human preference for a project I'm building. (imagebench.ai) I've tryed HPSv3, https://github.com/MizzenAI/HPSv3 and made post about it here: https://imagebench.ai/blog/does-the-score-match-your-eye…
How does *ACL conferences acceptance work [D]
Even after getting ARR reviews and a meta review, how is the acceptance decided at the *ACL venues, because I have seen meta review 3.5 getting…
multiple linear regression in scratch [P]
i made a multiple linear regression trainer that can be used with custom data in scratch nothing more to say, the impressive part is the scratch…
Why doesn’t the ML research community limit the number of submissions per author? [D]
I am currently working across multiple research communities, and I've noticed that the ML community is struggling with a massive volume of submissions, which is affecting…
Please help me understand figure on subspace similarity in LoRA paper. [D]
I am studying the LoRA paper and have trouble understanding this figure. The function essentially measures how much of the subspace spanned by the top i…
How should I approach training this specific ML model for my startup project [D]
So, I am working on this startup project with pretty low budget and one of the features is sentiment analysis based on political news, x posts…
Hyperparameter tuning approach question [R]
I am doing some work with cell type classification, where I have 4.3 million cells and 512 features (condensed embeddings from the encoder of a transformer).…
Talos-XII: hand-written autograd + small RL/MLP stack in Rust, applied to gacha probability modeling (no tch-rs/ndarray/PyTorch) — looking for benchmark help on ARM/AVX-512/GPU [P]
What it is Talos-XII is a CLI simulator for the gacha system in Arknights: Endfield. Rather than sampling from a static probability table, it trains a…