Yearly
Weekly
Daily
Reading list
Links 25
Score: 0.9156188206792982
User feedback: None
Out links: 290926 Raw text: 290926https://arxiv.org/pdf/2302.13861.pdf
Differentially Private Diffusion Models Generate Useful Synthetic Images Sahra Ghalebikesabi1,+ , Leonard Berrada2 , Sven Gowal2 , Ira Ktena2 , Robert Stanforth2 , Jamie Hayes2 , Soham De2 , Samuel L. Smith2 , Olivia Wiles2 and Borja Balle2 arXiv:2302.13861v1 [cs.LG] 27 Feb 2023 1 University of Ox...
Score: 0.902011208960867
User feedback: None
Out links: 291713 Raw text: 291713https://arxiv.org/pdf/2404.02258.pdf
Mixture-of-Depths: Dynamically allocating compute in transformer-based language models David Raposo1* , Sam Ritter1 , Blake Richards1,2 , Timothy Lillicrap1 , Peter Conway Humphreys1 and Adam Santoro1* arXiv:2404.02258v1 [cs.LG] 2 Apr 2024 1 Google DeepMind, 2 McGill University & Mila, * Equal Con...
Score: 0.8026047727432333
User feedback: None
Out links: 430494 Raw text: 430494https://proceedings.mlr.press/v202/shen23f/shen23f.pdf
Auxiliary Modality Learning with Generalized Curriculum Distillation Yu Shen 1 Xijun Wang 1 Peng Gao 1 Ming C. Lin 1 Abstract cars, but it’s reasonable to equip a few developer’s cars with Lidar for training. However, this specific type of learning task, i.e., ”test with fewer modalities than dur...
Score: 0.796568117325422
User feedback: None
Out links: 430504 Raw text: 430504https://proceedings.mlr.press/v202/kang23b/kang23b.pdf
Beyond Reward: Offline Preference-guided Policy Optimization Yachen Kang 1 2 Diyuan Shi 2 Jinxin Liu 2 Li He 2 Donglin Wang 2 Abstract 1. Introduction This study focuses on the topic of offline preference-based reinforcement learning (PbRL), a variant of conventional reinforcement learning that ...
Score: 0.7839570108493173
User feedback: None
Out links: 783765 Raw text: 783765https://gwern.net/doc/www/arxiv.org/183b65de0506f31cdf62cef9a5efbd0fde29afcb.pdf
CPM: A Large-scale Generative Chinese Pre-trained Language Model Zhengyan Zhang, Xu Han, Hao Zhou, Pei Ke, Yuxian Gu, Deming Ye, Yujia Qin, Yusheng Su, Haozhe Ji, Jian Guan, Fanchao Qi, Xiaozhi Wang, Yanan Zheng, Guoyang Zeng, Huanqi Cao, Shengqi Chen, Daixuan Li, Zhenbo Sun, Zhiyuan Liu† , Minlie H...
Score: 0.7834878665094938
User feedback: None
Out links: 430533 Raw text: 430533https://proceedings.mlr.press/v202/novikov23a/novikov23a.pdf
Few-bit Backward: Quantized Gradients of Activation Functions for Memory Footprint Reduction Georgii Novikov 1 2 Daniel Bershatsky 1 Julia Gusak 1 * Alex Shonenkov Denis Dimitrov 2 Ivan Oseledets 1 2 Abstract Memory consumed by the model during training (except intermediate tensors) can be split ...
Score: 0.7833411730598016
User feedback: None
Out links: 430585 Raw text: 430585https://proceedings.mlr.press/v202/wu23k/wu23k.pdf
Understanding INT4 Quantization for Language Models: Latency Speedup, Composability, and Failure Cases Xiaoxia Wu * 1 Cheng Li * 1 Reza Yazdani Aminabadi 1 Zhewei Yao 1 Yuxiong He 1 1. Introduction Abstract As pre-trained large language models (LLMs) (Vaswani et al., 2017) such as BERT (Tenney e...
Score: 0.7827254342133503
User feedback: None
Out links: 783887 Raw text: 783887https://gwern.net/doc/www/pdfs.semanticscholar.org/c0ac26d3f1e7cd328a547800f46cbd57fdb7087e.pdf
Psychologica Belgica 2010, 50-3&4, 245-276. DOES WORKING MEMORY TRAINING GENERALIZE? Zach SHIPSTEAD, Thomas S. REDICK, & Randall W. ENGLE Georgia Institute of Technology Recently, attempts have been made to alter the capacity of working memory (WMC) through extensive practice on adaptive working me...
Score: 0.7752549865688942
User feedback: None
Out links: 10593305 Raw text: 10593305https://www.cs.toronto.edu/~fleet/research/Papers/video-DMs-2022.pdf
arXiv:2204.03458v2 [cs.CV] 22 Jun 2022 Video Diffusion Models Jonathan Ho∗ [email protected] Tim Salimans∗ [email protected] Alexey Gritsenko [email protected] William Chan [email protected] Mohammad Norouzi [email protected] David J. Fleet [email protected] Abstract Gene...
Score: 0.7696849801451922
User feedback: None
Out links: 430597 Raw text: 430597https://proceedings.mlr.press/v202/castanet23a/castanet23a.pdf
Stein Variational Goal Generation for adaptive Exploration in Multi-Goal Reinforcement Learning Nicolas Castanet 1 Olivier Sigaud 1 Sylvain Lamprier 2 Abstract goal distribution is unknown at train time, which means discovering the space of valid goals by experience, and optimizing success covera...
Score: 0.7682773816331065
User feedback: None
Out links: 783770 Raw text: 783770https://gwern.net/doc/dual-n-back/2016-lindelov.pdf
NEUROPSYCHOLOGICAL REHABILITATION, 2016 http://dx.doi.org/10.1080/09602011.2016.1141692 Training and transfer effects of N-back training for braininjured and healthy subjects Jonas Kristoffer Lindeløv, Jonas Olsen Dall, Casper Daniel Kristensen, Marie Holt Aagesen, Stine Almgren Olsen, Therese Ruud...
Score: 0.7661532920861701
User feedback: None
Out links: 290813 Raw text: 290813https://arxiv.org/pdf/2308.10888.pdf
Unlocking Accuracy and Fairness in Differentially Private Image Classification Leonard Berrada*,1 , Soham De*,1 , Judy Hanwen Shen*,2,† , Jamie Hayes1 , Robert Stanforth1 , David Stutz1 , Pushmeet Kohli1 , Samuel L. Smith1 and Borja Balle1 * Equal contributions, 1 Google DeepMind, London, UK, 2 Comp...
Score: 0.7652266605477844
User feedback: None
Out links: 430578 Raw text: 430578https://proceedings.mlr.press/v202/skalse23a/skalse23a.pdf
Invariance in Policy Optimisation and Partial Identifiability in Reward Learning Joar Skalse * 1 2 Matthew Farrugia-Roberts * 3 Stuart Russell 4 Alessandro Abate 1 Adam Gleave 5 Abstract jectories (Christiano et al., 2017), and many others (Jeon et al., 2020). These algorithms can learn a reward ...
Score: 0.7650731492292728
User feedback: None
Out links: 430545 Raw text: 430545https://proceedings.mlr.press/v202/che23b/che23b.pdf
Fast Federated Machine Unlearning with Nonlinear Functional Theory Tianshi Che 1 Yang Zhou 1 Zijie Zhang 1 Lingjuan Lyu 2 Ji Liu 3 Da Yan 4 Dejing Dou 5 Jun Huan 6 6 Abstract the accuracy of the ML model on remaining data (Cao & Yang, 2015; Golatkar et al., 2020a; Shibata et al., 2021; Ginart et ...
Score: 0.7641061169162754
User feedback: None
Out links: 430564 Raw text: 430564https://proceedings.mlr.press/v202/xiong23a/xiong23a.pdf
Universal Morphology Control via Contextual Modulation Zheng Xiong 1 Jacob Beck 1 Shimon Whiteson 1 Abstract the high sample complexity of RL, the currently dominant paradigm of learning a new policy from scratch for each robot morphology is not scalable, and universal controllers that can genera...
Score: 0.7627255830754874
User feedback: None
Out links: 430565 Raw text: 430565https://proceedings.mlr.press/v202/lu23g/lu23g.pdf
Learning Dense Correspondences between Photos and Sketches Xuanchen Lu 1 Xiaolong Wang 1 Judith E. Fan 1 2 Figure 1: We propose a self-supervised method for learning the dense correspondence between sketches and photos. For each photo-sketch pair, we show the annotated keypoints from our benchmark ...
Score: 0.7570322083268206
User feedback: None
Out links: 430559 Raw text: 430559https://proceedings.mlr.press/v202/zandieh23a/zandieh23a.pdf
KDEformer: Accelerating Transformers via Kernel Density Estimation Amir Zandieh 1 Insu Han * 2 Majid Daliri * 3 Amin Karbasi 2 Abstract because naïve exact computation of their attention layers incurs quadratic (in sequence length) runtime and memory complexities. This can inhibit the training of...
Score: 0.7536874503241382
User feedback: None
Out links: 430528 Raw text: 430528https://proceedings.mlr.press/v202/liao23b/liao23b.pdf
Supervised Metric Learning to Rank for Retrieval via Contextual Similarity Optimization Christopher Liao 1 Theodoros Tsiligkaridis 2 Brian Kulis 1 Abstract There is extensive interest in metric learning methods for image retrieval. Many metric learning loss functions focus on learning a correct ra...
Score: 0.7517834817051614
User feedback: None
Out links: 290963 Raw text: 290963https://arxiv.org/pdf/2310.15454.pdf
Private Learning with Public Features Walid Krichene, Nicolas Mayoraz, Steffen Rendle, Shuang Song, Abhradeep Thakurta, and Li Zhang∗ arXiv:2310.15454v1 [cs.LG] 24 Oct 2023 Google Abstract We study a class of private learning problems in which the data is a join of private and public features. Th...
Score: 0.7507463294838759
User feedback: None
Out links: 430556 Raw text: 430556https://proceedings.mlr.press/v202/lin23d/lin23d.pdf
Text Generation with Diffusion Language Models: A Pre-training Approach with Continuous Paragraph Denoise Zhenghao Lin 1 2 3 Yeyun Gong 4 Yelong Shen 5 Tong Wu 6 2 Zhihao Fan 7 2 Chen Lin 1 3 Nan Duan 4 Weizhu Chen 5 Abstract which generate texts sequentially from left to right. However, RNNs suf...
Score: 0.745380064092582
User feedback: None
Out links: 430527 Raw text: 430527https://proceedings.mlr.press/v202/tran23a/tran23a.pdf
Fully Bayesian Autoencoders with Latent Sparse Gaussian Processes Ba-Hien Tran 1 Babak Shahbaba 2 Stephan Mandt 2 Maurizio Filippone 1 Abstract to a set of lower-dimensional latent codes and a decoder that maps the latent codes back to the observations. We present a fully Bayesian autoencoder mo...
Score: 0.7448615356184376
User feedback: None
Out links: 10593300 Raw text: 10593300https://www.cs.toronto.edu/~fleet/research/Papers/hdmlNIPS12.pdf
Hamming Distance Metric Learning Mohammad Norouzi† David J. Fleet† Ruslan Salakhutdinov†,‡ † Departments of Computer Science and Statistics‡ University of Toronto [norouzi,fleet,rsalakhu]@cs.toronto.edu Abstract Motivated by large-scale multimedia applications we propose to learn mappings from hig...
Score: 0.7435276358311191
User feedback: None
Out links: 430514 Raw text: 430514https://proceedings.mlr.press/v202/hong23a/hong23a.pdf
Multi-Task Off-Policy Learning from Bandit Feedback Joey Hong 1 Branislav Kveton 2 Manzil Zaheer 3 Sumeet Katariya 2 Mohammad Ghavamzadeh 4 Abstract Because we cannot explore beyond the logged dataset, it is important to use the logged data in the most statistically efficient way. One way of achi...
Score: 0.7429363091487914
User feedback: None
Out links: 290661 Raw text: 290661https://arxiv.org/pdf/2306.15447.pdf
Are aligned neural networks adversarially aligned? arXiv:2306.15447v2 [cs.CL] 6 May 2024 Nicholas Carlini1 , Milad Nasr1 , Christopher A. Choquette-Choo1 , Matthew Jagielski1 , Irena Gao2 , Anas Awadalla3 , Pang Wei Koh13 , Daphne Ippolito1 , Katherine Lee1 , Florian Tramèr4 , Ludwig Schmidt3 1 G...
Score: 0.7359891733601023
User feedback: None
Out links: 784031 Raw text: 784031https://gwern.net/doc/www/www.klingberglab.se/f7d3d88b1525c0107abdbaf4ec2cba356bdc217a.pdf
Developmental Science 12:1 (2009), pp 106 –113 DOI: 10.1111/j.1467-7687.2008.00745.x PAPER Blackwell Publishing Ltd Training and transfer effects of executive functions in preschool children Lisa B. Thorell,1 Sofia Lindqvist,2 Sissela Bergman Nutley,3 Gunilla Bohlin2 and Torkel Klingberg3 1. Depa...