刚刚,ICLR 2025会议的论文盲审结果已经出了,其中平均分是4.76,最高分是9[1]。 而拿下最高的分的论文就是ControlNet作者的工作IC-Light,IC-Light共有4个审稿人审稿,其中两个审稿人直接给了满分(10分),而另外两个审稿人也给了高分(8分)[2]: ControlNet这个工作已经被大家熟知,它也获得ICCV 2023马尔奖(最佳...
Results show that EDGE achieves 7.3% improvement on the ROC-AUC score over the best baseline. 16. Has it really improved? Knowledge graph based separation and fusion for recommendation Ratings: 3, 3, 3 openreview.net/forum? In this paper we study the knowledge graph (KG) based recommendation...
such a strategy often introduces false-positive noises. Existing approaches about de-noising recommendation mainly focus on positive instances while ignoring the noise in the large amount of sampled negative feedback. In this paper, we propose a meta...
This is the PyTorch implementation for ICLR 2023 paper "FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning". This paper also wins a Best Paper Award 🏆 at ECCV 2022 AROW Workshop. [openreview] | [arXiv] | [workshop slides] Requirements Python >= 3.7.10 PyT...
3. **OctoCoder** (StarCoder) / **OctoGeeX** (CodeGeeX2): "OctoPack: Instruction Tuning Code Large Language Models" [2023-08] [ICLR 2024 Spotlight] [[paper](https://arxiv.org/abs/2308.07124)] [[repo](https://github.com/bigcode-project/octopack)] 4. "At Which Training Stage Does...
CVPR ICML ICLR这种级别的，AAAI就算了，如果只有一篇的话best /outstanding paper应该也行吧，能发这种...
说个冷笑话，然后你有十篇A会，其中还有一篇best paper，清华很愿意给你一个机会 但二本会拒绝你，...
We evaluate the novel clustering algorithm on various datasets with different properties using different embedding-based and cross-attention–based models. We compare the clustering algorithm’s performance with the two best performing baselines (see thepaperfor more details): ...
This paper first theoretically justifies that the model gradient error matters in the policy optimization phase. Specifically, the bias of the estimated policy gradient is not only introduced by the prediction error of the learned model but also introduced by the gradient error of the learned model...
This paper first theoretically justifies that the model gradient error matters in the policy optimization phase. Specifically, the bias of the estimated policy gradient is not only introduced by the prediction error of the learned model but ...