Apple is sponsoring the Neural Information Processing Systems (NeurIPS) conference, which will be held in person from December 10 to 16 in New Orleans, Louisiana. NeurIPS is a global conference focused on promoting the exchange of research on neural information processing systems in their biological, technological, mathematical and theoretical aspects. Below is the schedule of workshops and events sponsored by Apple at NeurIPS 2023.
Schedule
Sunday December 10
Monday December 11
- WORKSHOP
- ai – Opens in a new window” class=”icon icon-after icon-external” rel=”noopener nofollow”>Black in ai
- 8:15 am – 3:30 pm CST, rooms R02-R05
- WORKSHOP
- ai – Opens in a new window” class=”icon icon-after icon-external” rel=”noopener nofollow”>LatinX in ai
- 8:15 am – 3:30 pm CST, room 217-219
- Miguel Angel Bautista Martin will be participating in the mentoring hour as a mentor.
- WORKSHOP
- ai – Opens in a new window” class=”icon icon-after icon-external” rel=”noopener nofollow”>Queer in ai
- 9:30 am – 3:30 pm CST, rooms R06-R09
- WORKSHOP
- Women in machine learning
- 8:00 am – 3:30 pm CST, Great Hall
- Derek Smith will host a roundtable on internships at Apple.
Tuesday December 12
Wednesday December 13
- POSTER
- DeepPCR: parallelization of sequential operations in neural networks
- 5:00 – 7:00 pm CST in the Great Hall and Hall B1+B2 #1009
- Federico Danieli, Miguel Sarabia del Castillo, Pau Rodriguez,
- POSTER
- 4M: Massively Multimodal Masked Modeling
- 5:00-7:00 pm CST in the Great Hall and Hall B1+B2 #1022
- David Mizrahi, Mingfei Gao, Afshin Dehghan, Roman Bachmann, Oğuzhan Fatih Kar, Teresa Yeo, Amir Zamir
- POSTER
- Adaptive weight decay
- 5:00 – 7:00 pm CST in the Great Hall and Hall B1+B2 #721
- Mohammad Amin Ghiasi, Ali Shafahim Reza Ardekani
Thursday December 14
Friday December 15
- WORKSHOP
- DistShift
- 9:00 am – 5:00 pm CST, rooms R06-R09
- TiC-CLIP: Continuous training of CLIP models
- Saurabh Garg, Hadi Pour Ansari, Mehrdad Farajtabar, Sachin Mehta, Raviteja Vemulapalli, Oncel Tuzel, Vaishaal Shankar, Fartash Faghri
Saturday December 16
- WORKSHOP
- ai and Biology – Opens in a new window” class=”icon icon-after icon-external” rel=”noopener nofollow”>Generative ai and biology
- Generation of molecular conformers with multiple diffusion fields
- Yuyang Wang, Ahmed Elhag, Navdeep Jaitly, Josh Susskind, Miguel Ángel Bautista Martín
- 6:15 am, Room 265 – 268
- WORKSHOP
- Theory and practice of self-supervised learning
- Start your own variation
- Polina Turishcheva, Jason Ramapuram, Sinead Williamson, Dan Busbridge, Eeshan Gunesh Dhekane, Russ Webb
- 12:00 – 1:00 pm CST and 4:15 – 5:30 pm CST, room 217-219
Accepted articles
4M: Massively Multimodal Masked Modeling
David Mizrahi, Mingfei Gao, Afshin Dehghan, Roman Bachmann, Oğuzhan Fatih Kar, Teresa Yeo, Amir Zamir
Adaptive weight decay
Amin Ghiasi, Ali Shafahi, Reza Ardekani
Agnostic learning of single-index models using omnipredictors
Aravind Gollakota, Parikshit Gopalan, Adam R. Klivans, Konstantinos Stavropoulos
PLANNER: Diversified paragraph generation using the latent language diffusion model
Yizhe Zhang, Jiatao Gu, Zhuofeng Wu, Shuangfei Zhai, Josh Susskind, Navdeep Jaitly
PDP: All you need is parameterless differentiable pruning
Minsik Cho, Saurabh Adya, Devang Naik
Trade agnostic learning or characterize omniprediction using multi-calibration
Parikshit Gopalan, Michael P. Kim, Omer Reingold
Work accepted in the workshop
ReLU Strikes Back: Exploiting Activation Sparsity in a Large Language Model
Iman Mirzadeh, Keivan Alizadeh, Sachin Mehta, Carlo C Del Mundo, Oncel Tuzel, Golnoosh Samei, Mohammad Rastegari, Mehrdad Farajtabar
SAM-CLIP: Merging Vision Foundation models towards semantic and spatial understanding
Haoxiang Wang, Pavan Kumar Anasosalu Vasu, Fartash Faghri, Raviteja Vemulapalli, Mehrdad Farajtabar, Sachin Mehta, Mohammad Rastegari, Oncel Tuzel, Hadi Pouransari
What algorithms can transformers learn? A study on length generalization
Hattie Zhou, Omid Saremi, Etai Littwin, Arwen Bradley, Noam Razin, Josh Susskind, Samy Bengio, Preetum Nakkiran
Population
Personal voice on device for accessibility
Training on-device machine learning models is a key research area we focus on. In this demo, we'll share how we apply text-to-speech adaptation technology to Apple devices to create a personal voice with a limited number of recordings so that people at risk of voice loss can store and use it. in live speech when they cannot speak.
Consecutive Siri requests
Siri-Directed Voice Detector (SDSD) runs entirely on the device. It uses acoustic information, automatic speech recognition system and lexical information to decide whether an expression is directed to Siri or not. With this feature, Siri listens to the user's speech for a subsequent request, while responding to the previous request.
All NeurIPS attendees are invited to stop by the Apple booth (booth number 1103, located in Hall C and D of the Ernest N. Morial Convention Center in New Orleans) to experience these demos in person.
Thanks
Samy Bengio is a member of the NeurIPS Council 2023.
Marian Stewart Bartlett is the treasurer of NeurIPS 2023.
Alexander Toshev, Kunal Talwar, Navdeep Jaitly, Pierre Ablin, Preetum Nakkiran, Shuangfei Zhai, Vaishaal Shankar, Vitaly Feldman and Yizhe Zhang are the NeurIPS 2023 Area Chairs.
Marco Cuturi and Samy Bengio are the Senior Area Chairs of NeurIPS 2023.
Audra McMillan is a NeurIPS 2023 ethics reviewer.
Tatiana Likhomanenko and Oncel Tuzel are Chairs of the NeurIPS 2023 Benchmarks and Datasets Area.
Aravind Gollakota, Arno Blaas, Barry Theobald, Bhavika Devnani, Bogdan Mazoure, Enrico Fini, Etai Littwin, Hilal Asi, Jason Ramapuram, Lyndon Duong, Miguel Sarabia, Pau Rodriguez, Rahul Sunil Bhalerao, Richard Bai, Skyler Seto, Tatiana Likhomanenko, Vimal Thilak and Xavi Suau are NeurIPS 2023 reviewers.
