-
- [ ] [[2202.12837] Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://arxiv.org/abs/2202.12837)
# [2202.12837] Rethinking the Role of Demonstrations: What Makes In-…
-
## 一言でいうと
クラス分類のタスクについて、マルチタスク＋半教師ありを組み合わせた手法の提案。各タスクでラベル情報をEncodeした空間を共通で持ち、そこから各タスクに応じたラベルの予測を行う(主タスク)。同時にこのラベル空間を元にラベルなしデータへのラベルづけを行い、本体側の予測と比較する(補助タスク)
をLSTMでencodingして，履歴を活かしたranking及びsuggestionを行なっている
- multi-task neural …
-
GaVaMoE: Gaussian-Variational Gated Mixture of Experts for Explainable Recommendation
https://arxiv.org/abs/2410.11841
-
## ReID survey
* Awesome ReID https://github.com/bismex/Awesome-person-re-identification
* [Deep Learning for Person Re-identification: A Survey and Outlook](https://arxiv.org/abs/2001.04193)
## PA…
-
-
Since the XGBoost 1.6, we have been working on having multi-output support for the tree model. In 2.0, we will have the initial implementation for the vector-leaf-based multi-output model. This issue …
-
Hi @danielhanchen
I am trying to fine-tune gemma2-2b for my task following the guidelines of the continued finetuning in unsloth. Howver, I am facing OOM while doing so. My intent is to train gemm…
-