Apple is presenting new research at the annual conference on Neural Information Processing Systems (NeurIPS), which takes place in-person in both Mexico City, Mexico, from November 30 – December 5, and San Diego, California, from December 2 – 7. We are proud to again sponsor the multi-track interdisciplinary conference, which brings together the scientific and industrial research communities surrounding Machine Learning. Below is an overview of Apple’s participation at NeurIPS 2025.
Jump to a section:
Stop by the Apple booth #1103 in the San Diego Convention Center during exhibition hours. All times listed in PST (San Diego local-time):
- Tuesday, December 2, 12:00 PM – 8:00 PM
- Wednesday, December 3, 9:00 AM – 5:00 PM
- Thursday, December 4, 9:00 AM – 5:00 PM
- Friday, December 5, 9:00 AM – 12:00 PM
Schedule
Sunday, November 30
- WORKSHOP (NEURIPS CDMX – MEXICO CITY)
- Where Did the Reasoning Go Wrong? A Bench-Mark of Puzzle-Based Visual Tasks With CoT Error Detection
- 11:00 AM – 6:00 PM, NeurIPS 2025 Workshop on Socially Responsible and Trustworthy Foundation Models, Don Alberto 1
- Yusu Qian, Cheng Wan (Cornell University), Chao Jia, Yinfei Yang, Qingyu Zhao (Cornell University), Zhe Gan
Tuesday, December 2
- AFFINITY WORKSHOP
- Women in Machine Learning (WiML)
- 8:00 AM – 5:00 PM, Upper Level Ballroom 20CD
- Richa Dixit, Maartje ter Hoeve and Shruti Palaskar will represent Apple at the WiML mentor roundtable session (12:00 PM – 1:30 PM), during the workshop.
- AFFINITY WORKSHOP
- LatinX in AI (LXAI)
- 9:00 AM – 5:00 PM, Upper Level Room 33ABC
- Lucas Monteiro Paes and Carlos Pareja will represent Apple at the LXAI Mentoring Hour (1:45 PM – 2:45 PM) during the workshop.
Wednesday, December 3
- POSTER
- The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
- 11:00 AM – 2:00 PM, #1914, Poster Session 1, Exhibit Hall C,D,E
- Parshin Shojaee, Iman Mirzadeh, Keivan Alizadeh Vahid, Samy Bengio, Max Horton, Mehrdad Farajtabar
- POSTER
- UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation
- 11:00 AM – 2:00 PM, #4900, Poster Session 1, Exhibit Hall C,D,E
- Rui Tian, Mingfei Gao, Mingze Xu, Jimmy Hu, Jiasen Lu, Zuxuan Wu (Fudan University), Yinfei Yang, Afshin Dehghan
- POSTER
- Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based Models
- 4:30 PM – 7:30 PM, #2506, Poster Session 2, Exhibit Hall C,D,E
- Louis Béthune, David Vigouroux (IRT Saint-Exupery), Yilun Du (Harvard University), Rufin VanRullen (CNRS), Thomas Serre (Brown University), Victor Boutin (CNRS)
- POSTER
- Models That Prove Their Own Correctness
- 4:30 PM – 7:30 PM, #1304, Poster Session 2, Exhibit Hall C,D,E
- Noga Amit (UC Berkeley), Shafi Goldwasser (UC Berkeley), Orr Paradise (UC Berkeley), Guy Rothblum
Thursday, December 4
- AFFINITY WORKSHOP
- Queer in AI
- 9:00 AM – 5:00 PM, Upper Level Room 32AB
- Lauren Araujo and Kevin Miao will represent Apple at the Sponsor Meet & Greet Session (1:30 PM – 2:00 PM) during the workshop.
- POSTER
- Enabling Differentially Private Federated Learning for Speech Recognition: Benchmarks, Adaptive Optimizers, and Gradient Clipping
- 11:00 AM – 2:00 PM, #114, Poster Session 3, Exhibit Hall C,D,E
- Martin Pelikan, Shams Azam, Vitaly Feldman, Jan “Honza” Silovsky, Kunal Talwar, Christopher G. Brinton (Purdue University), Tatiana Likhomanenko
- POSTER
- Flexible Language Modeling in Continuous Space with Transformer-based Autoregressive Flows
- 11:00 AM – 2:00 PM, #5306, Poster Session 3, Exhibit Hall C,D,E
- Ruixiang Zhang, Shuangfei Zhai, Jiatao Gu, Yizhe Zhang, Josh Susskind, Navdeep Jaitly, Miguel Angel Bautista, Huangjie Zheng, Tianrong Chen
- SPOTLIGHT POSTER
- STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis
- 11:00 AM – 2:00 PM, #5318, Poster Session 3, Exhibit Hall C,D,E
- Jiatao Gu, Tianrong Chen, David Berthelot, Huangjie Zheng, Yuyang Wang, Ruixiang Zhang, Laurent Dinh, Miguel Angel Bautista, Josh Susskind, Shuangfei Zhai
- POSTER
- Scaling Laws for Optimal Data Mixtures
- 11:00 AM – 2:00 PM, #3414, Poster Session 3, Exhibit Hall C,D,E
- Mustafa Shukor, Louis Béthune, Dan Busbridge, David Grangier, Enrico Fini, Alaaeldin Mohamed Elnouby Ali, Pierre Ablin
- POSTER
- TADA: Improved Diffusion Sampling with Training-free Augmented Dynamics
- 11:00 AM – 2:00 PM, #3302, Poster Session 3, Exhibit Hall C,D,E
- Tianrong Chen, Huangjie Zheng, Jiatao Gu, David Berthelot, Josh Susskind, Shuangfei Zhai
- SPOTLIGHT POSTER
- Checklists Are Better Than Reward Models For Aligning Language Models
- 4:30 PM – 7:30 PM, #103, Poster Session 4, Exhibit Hall C,D,E
- Vijay Viswanathan (Carnegie Mellon University), Yanchao Sun, Shuang Ma (Meta), Xiang Kong, Meng Cao, Graham Neubig (Carnegie Mellon University), Tongshuang Wu (Carnegie Mellon University)
Friday, December 5
- SPOTLIGHT POSTER
- CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching
- 11:00 AM – 2:00 PM, #4200, Poster Session 5, Exhibit Hall C,D,E
- Chen Chen, Pengsheng Guo, Liangchen Song, Jiasen Lu, Rui Qian, Tsu-Jui Fu (Meta), Wei Liu, Yinfei Yang, Alex Schwing
- POSTER
- StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant
- 11:00 AM – 2:00 PM, #4617, Poster Session 5, Exhibit Hall C,D,E
- Haibo Wang (Fudan University), Brian Feng, Jeff Lai, Mingze Xu, Shiyu Li, Weifeng Ge (Fudan University), Afshin Dehghan, Meng Cao, Ping Huang
- POSTER
- Datasets, Documents, and Repetitions: The Practicalities of Unequal Data Quality
- 4:30 PM – 7:30 PM, #101, Poster Session 6, Exhibit Hall C,D,E
- Alex Fang (Stanford University), Hadi Pour Ansari, Matt Jordan (Ai2), Alexander Toshev, Vaishaal Shankar (Anthropic (work done when at Apple)), Ludwig Schmidt (Stanford University), Tom Gunter (Meta)
- POSTER
- LinEAS: End-to-end Learning of Activation Steering with a Distributional Loss
- 4:30 PM – 7:30 PM, #3604, Poster Session 6, Exhibit Hall C,D,E
- Pau Rodriguez Lopez, Michal Klein, Eleonora Gualdoni, Valentino Maiorca (Sapienza Università di Roma), Arno Blaas, Luca Zappella, Marco Cuturi, Xavier Suau Cuadros
Saturday, December 6
- WORKSHOP
- Building the Cognitive Network: Pillars of AI-Native Wireless ecosystem
- 8:00 AM – 5:00 PM, AI and ML for Next-Generation Wireless Communications and Networking (AI4NextG @ NeurIPS’25), Upper Level Room 10
- Supratik Bhattacharjee, Sharad Sambhwani
- WORKSHOP
- CHAST: Attention Aided SISO OFDM Channel Estimation
- 8:00 AM – 5:00 PM, AI and ML for Next-Generation Wireless Communications and Networking (AI4NextG @ NeurIPS’25), Upper Level Room 10
- Mehmetcan Gok, John Zhou, Supratik Bhattacharjee, Huaning Niu, Sharad Sambhwani
- WORKSHOP
- CPEP: Contrastive Pose-EMG Pre-training Enhances Gesture Generalization on EMG signals
- 8:00 AM – 5:00 PM, Foundation Models for the Brain and Body Workshop, Upper Level Room 11AB
- Behrooz Mahasseni, Wenhui Cui (University of Southern California), Chris Sandino, Juri Minxha, Ellen Zippi, Ran Liu, Hadi Pour Ansari, Erdrin Azemi, Aman Verma, Anna Sedlackova
- WORKSHOP
- Learning the relative composition of EEG signals using pairwise relative shift pretraining
- 8:00 AM – 5:00 PM, Foundation Models for the Brain and Body Workshop, Upper Level Room 24ABC
- Chris Sandino, Sayeri Lala (Stanford University), Geeling Chau (California Institute of Technology), Melika Ayoughi (University of Amsterdam), Behrooz Mahasseni, Ellen Zippi, Ali Moin, Erdrin Azemi, Hanlin Goh
- WORKSHOP
- On Fitting Flow Models with Large Sinkhorn Couplings
- 8:00 AM – 5:00 PM, Structured Probabilistic Inference and Generative Modeling, Upper Level Ballroom 20C
- Marco Cuturi Cameto, Michal Klein, Seyed Alireza Mousavi Hosseini
- WORKSHOP
- Partial Parameter Updates for Efficient Distributed Training
- 8:00 AM – 5:00 PM, OPT 2025: Optimization for Machine Learning, Upper Level Ballroom 20A
- Anastasiia Filippova, Angelos Katharopoulos, Ronan Collobert, David Grangier
Sunday, December 7
- WORKSHOP
- Breaking Down Video LLM Benchmarks: Knowledge, Spatial Perception, or True Temporal Understanding?
- 8:00 AM – 5:00 PM, Evaluating the Evolving LLM Lifecycle: Benchmarks, Emergent Abilities, and Scaling, Upper Level Room 2
- Brian Feng, Jeff Lai, Shiyu Li, Zizhen Wang, Simon Wang, Ping Huang, Meng Cao
- WORKSHOP
- JointMMSafe: A Combinatorial Safety Benchmark for Multimodal Foundation Models
- 8:00 AM – 5:00 PM, Evaluating the Evolving LLM Lifecycle: Benchmarks, Emergent Abilities, and Scaling, Upper Level Room 2
- Shruti Palaskar, Leon Gatys, Mona Abdelrahman, Mar Jacobo, Larry Lindsey, Gunnar Lund, Yang Xu, Navid Shiee, Jeffrey Bigham, Charlie Maalouf, Joseph Yitan Cheng
- WORKSHOP
- PersonaTeaming: Exploring How Introducing Persona Can Improve Automated LLM Red-Teaming
- 8:00 AM – 5:00 PM, Evaluating the Evolving LLM Lifecycle: Benchmarks, Emergent Abilities, and Scaling, Upper Level Room 2
- Wesley Deng (Carnegie Mellon University, Sunnie S. Y. Kim, Akshita Jha, Ken Holstein (Carnegie Mellon University), Motahhare Eslami (Carnegie Mellon University), Lauren Wilcox, Leon Gatys
- WORKSHOP (CO-LOCATED AT NEURIPS SAN DIEGO)
- SimpleFold: Folding Proteins is Simpler than You Think
- 8:30 AM – 5:00 PM, Machine Learning in Structural Biology, UCSD Park & Market, 1100 Market St. San Diego, CA 92101
- Yuyang Wang, Navdeep Jaitly, Josh Susskind, Miguel Angel Bautista
Technical Demos
MLX
We demonstrate large model inference and training on device using MLX. MLX is a flexible array framework that is optimized for Apple silicon and brought to you by Apple machine learning research. It enables training and inference of arbitrarily complex models on Apple silicon powered devices with great brevity and flexibility.
We will showcase image generation using a large difusion model on an iPad Pro equipped with an M5 chip, and highlight disributed Compute with MLX and Apple Silicon. Visitors can explore text and code generation leveraging a 1 trillion parameter model running in Xcode on a 4-Mac Studio M3 Ultra cluster, each equipped with 512 GB of unified memory.
FastVLM
FastVLM is a family of mobile-friendly vision language models, built using MLX. These models use a mix of CNN and Transformer architectures for vision encoding designed specifically for processing high-resolution images. Together, they demonstrate a strong approach that achieves an optimal balance between accuracy and speed.
Visitors can engage with FastVLM via a real-time visual question-and-answer demo on an iPhone 17 Pro Max.
Both MLX and FastVLM demos will be available at the Apple Booth during exhibition hours.
Main Venue-Accepted Papers
AuthorsChen Chen, Pengsheng Guo**, Liangchen Song, Jiasen Lu, Rui Qian, Xinze Wang, Tsu-Jui Fu**, Wei Liu**, Yinfei Yang, Alex Schwing
AuthorsVijay Viswanathan†, Yanchao Sun, Shuang Ma‡**, Xiang Kong, Meng Cao, Graham Neubig†, Tongshuang Wu†
AuthorsAlex Fang**†, Hadi Pouransari, Matt Jordan‡, Alexander Toshev, Vaishaal Shankar§**, Ludwig Schmidt†, Tom Gunter¶**
AuthorsZijing Ou†, Ruixiang Zhang, Yingzhen Li†
AuthorsMartin Pelikan*, Sheikh Shams Azam*, Vitaly Feldman, Jan “Honza” Silovsky, Kunal Talwar, Christopher G. Brinton†, Tatiana Likhomanenko*
AuthorsRuixiang Zhang, Shuangfei Zhai, Jiatao Gu, Yizhe Zhang, Huangjie Zheng, Tianrong Chen, Miguel Angel Bautista, Josh Susskind, Navdeep Jaitly
AuthorsLouis Béthune*, David Vigouroux†, Yilun Du‡, Rufin VanRullen§, Thomas Serre¶, Victor Boutin§*
AuthorsPengfei Zhao, Rongbo Luan, Wei Zhang, Peng Wu, Sifeng He
AuthorsOrtal Senouf†, Antoine Wehenkel, Cédric Vincent-Cuaz†, Emmanuel Abbé, Pascal Frossard†
AuthorsJiayuan Ye†**, Vitaly Feldman, Kunal Talwar
AuthorsPau Rodríguez‡, Michal Klein, Eleonora Gualdoni, Valentino Maiorca†**, Arno Blaas, Luca Zappella, Marco Cuturi, Xavier Suau‡
Models That Prove Their Own Correctness
Noga Amit (UC Berkeley), Shafi Goldwasser (UC Berkeley), Orr Paradise (UC Berkeley), Guy Rothblum
AuthorsJie An†**, De Wang, Pengsheng Guo, Jiebo Luo†, Alexander Schwing
AuthorsHilal Asi, Vitaly Feldman, Hannah Keller†**, Guy N. Rothblum, Kunal Talwar
AuthorsVitaly Feldman, Moshe Shenfeld†
AuthorsJustin Lazarow, Kai Kang, Afshin Dehghan
Sample and Map from a Single Convex Potential using Generative Moment Measures
Nina Vesseron (CREST-ENSAE), Louis Béthune, Marco Cuturi
AuthorsMustafa Shukor†, Louis Bethune, Dan Busbridge, David Grangier, Enrico Fini, Alaaeldin El-Nouby, Pierre Ablin
AuthorsJiatao Gu, Tianrong Chen, David Berthelot, Huangjie Zheng, Yuyang Wang, Ruixiang Zhang, Laurent Dinh, Miguel Angel Bautista, Josh Susskind, Shuangfei Zhai
AuthorsHaibo Wang‡‡, Bo Feng, Zhengfeng Lai, Mingze Xu, Shiyu Li, Weifeng Ge†, Afshin Dehghan, Meng Cao, Ping Huang
AuthorsTianrong Chen, Huangjie Zheng, David Berthelot, Jiatao Gu, Josh Susskind, Shuangfei Zhai
AuthorsParshin Shojaee*†, Iman Mirzadeh*, Keivan Alizadeh, Maxwell Horton, Samy Bengio, Mehrdad Farajtabar
AuthorsRui Tian, Mingfei Gao, Mingze Xu, Jiaming Hu, Jiasen Lu, Zuxuan Wu†, Yinfei Yang, Afshin Dehghan
Acknowledgements
Samy Bengio is a Board Member for NeurIPS.
Pierre Ablin, Samy Bengio, Ronan Collobert, Marco Cuturi, Satyen Kale, Kunal Talwar, and Sinead Williamson are Senior Area Chairs.
Byeongjoo Ahn, Hilal Asi, Sheikh Shams Azam, Miguel Ángel Bautista, Meng Cao, Fartash Faghri, Mehrdad Farajtabar, Vitaly Feldman, Nick Foti, Zhe Gan, Jiatao Gu, Devon Hjelm, Chun-Liang Li, Tatiana Likhomanenko, Alex Papangelis, Stephan Richter, Pau Rodriguez, Skyler Seto, Natalie Schluter, Josh Susskind, Oncel Tuzel, Erik Wijmans, Yinfei Yang, Shuangfei Zhai, Yizhe Zhang, and Huangjie Zheng are Area Chairs.
Yannick Assogba, Deepika Bablani, Vassilis Baltatzis, Sima Behpour, Louis Bethune, Arno Blaas, Jie Bu, Chacha Chen, Chen Chen, Tianrong Chen, Masha Fedzechkina Donaldson, Fahad Kamran, Parmeshwar Khurd, Han-Byul Kim, Sunnie S. Y. Kim, Michael Kirchhof, Colin Lea, Pingzhi Li, Xintong Li, Ran Liu, Said Medjkouh, Lucas Monteiro Paes, Robin Schmidt, Amitis Shidani, Parshin Shojaee, Andrew Silva, Kaitao Song, Andrew Szot, Xinyu Tang, Vimal Thilak, William Thong, Raviteja Vemulapalli, Yuyang Wang, Dehong Xu, Jiayuan Ye, and Xiyou Zhou are Reviewers.
Fartash Faghri is a Workshop Co-Organizer; Samy Bengio, Mehrdad Farajtabar, Oncel Ouzel, and Hadi Pour Ansari serve on the Workshop Advisory Board; Mohammadreza Armandpour, Louis Béthune, Cheng-Yu Hsieh, Chen Huang, Cem Koc, Iman Mirzadeh and Raviteja Vemulapalli are Workshop Reviewers for Workshop on Continual and Compatible Foundation Model Updates (CCFM) 2025.
Antoine Wehenkel is a Workshop Co-Organizer for Machine Learning and the Physical Sciences Workshop 2025.
