NeurIPS 2025

12/2 (Tue) ～ 12/7 (Sun), 2025 at San Diego Convention Center, San Diego, US

The Thirty-nineth Annual Conference on Neural Information Processing Systems (NeurIPS 2025) is an interdisciplinary conference that brings together researchers in machine learning, neuroscience, statistics, optimization, computer vision, natural language processing, life sciences, natural sciences, social sciences, and other adjacent fields.

Sony is proud to be Platinum sponsor of NeurIPS 2025. We look forward to this year's exciting exhibition opportunities, featuring a variety of ways to connect with participants in person. Sony will exhibit and participate.

Contents: Sony's Technical Programs at NeurIPS 2025; Exhibition Booth; Event Report; Follow us on LinkedIn!; Sony Women in Technology Award with Nature; Career Information

Sony's Technical Programs at NeurIPS 2025

Posters - Main Track

** Spotlight Paper **
StelLA: Subspace Learning in Low-rank Adaptation using Stiefel Manifold

- Authors: Zhizhong Li (Sony AI), Sina Sajadmanesh (Sony AI), Jingtao Li (Sony AI), Lingjuan Lyu (Sony AI)
- Date/Time: [Mexico City Poster] December 5th (Fri) 11:00 — 14:00 (PST)
- Place: Foyer

< Link >
- [Poster] https://neurips.cc/virtual/2025/poster/119898
- [Paper] https://arxiv.org/abs/2510.01938

Dyn-O: Building Structured World Models with Object-Centric Representations

- Authors: Zizhao Wang, Kaixin Wang, Li Zhao, Peter Stone (The University of Texas at Austin, Sony AI), Jiang Bian
- Date/Time: [Poster Session 4] December 4th (Thu) 16:30 — 19:30 (PST)
- Place: Exhibit Hall C,D,E #216

< Link >
- [Poster] https://neurips.cc/virtual/2025/loc/san-diego/poster/117215
- [Paper] https://arxiv.org/abs/2507.03298

Enhancing 3D Reconstruction for Dynamic Scenes

- Authors: Jisang Han, Honggyu An, Jaewoo Jung, Takuya Narihira (Sony AI), Junyoung Seo, Kazumi Fukuda (Sony AI), Chaehyun Kim, Sunghwan Hong, Yuki Mitsufuji (Sony AI/Sony Group Corporation), Seungryong Kim
- Date/Time: [Poster Session 4] December 4th (Thu) 16:30 — 19:30 (PST)
- Place: Exhibit Hall C,D,E #4505

< Link >
- [Poster] https://neurips.cc/virtual/2025/poster/116068
- [Paper] https://arxiv.org/abs/2504.06264
- [Project Page] https://cvlab-kaist.github.io/DDUSt3R/

RLZero: Direct Policy Inference from Language Without In-Domain Supervision

- Authors: Harshit Sushil Sikchi, Siddhant Agarwal, Pranaya Jajoo, Samyak Parajuli, Caleb Chuck, Max Rudolph, Peter Stone (The University of Texas at Austin/Sony AI), Amy Zhang, Scott Niekum
- Date/Time: [Poster Session 6] December 5th (Fri) 16:30 - 19:30 (PST)
- Place: Exhibit Hall C,D,E #302

< Link >
- [Poster] https://neurips.cc/virtual/2025/loc/san-diego/poster/116874
- [Paper] https://arxiv.org/abs/2412.05718

Posters - D&B Track

Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia

- Authors: Chandler Smith, Marwa Abdulhai, Manfred Diaz, Marko Tesic, Rakshit S. Trivedi, Alexander Sasha Vezhnevets, Lewis Hammond, Jesse Clifton, Minsuk Chang, Edgar A. Duéñez-Guzmán, John P. Agapiou, Jayd Matyas, Danny Karmon, Dylan Hadfield-Menell, Natasha Jaques, Tim Baarslag, Jose Hernandez-Orallo, Joel Z. Leibo, Akash Kundu, Aliaksei Korshuk, Ananya Ananya, Arrasy Rahman, Avinaash Anand Kulandaivel, Bain McHale, Beining Zhang, Buyantuev Alexander, Carlos Saith Rodriguez Rojas, Caroline Wang, Chetan Talele, Chenao Liu, Chichen Lin, Diana Riazi, Di Yang Shi, Emanuel Tewolde, Elizaveta Tennant, Fangwei Zhong, Fuyang Cui, Gang Zhao, Gema Parreño Piqueras, Hyeonggeun Yun, Ilya Makarov, Jiaxun Cui, Jebish Purbey, Jim Dilkes, Jord Nguyen, Lingyun Xiao, Luis Felipe Giraldo, Manuela Chacon-Chamorro, Manuel Sebastian Rios Beltran, Marta Emili García Segura, Mengmeng Wang, Mogtaba Alim, Nicanor Quijano, Nico Schiavone, Olivia Macmillan-Scott, Oswaldo Peña, Peter Stone (The University of Texas at Austin/Sony AI), Ram Mohan Rao Kadiyala, Rolando Fernandez, Ruben Manrique, Sunjia Lu, Sheila A. McIlraith, Shamika Dhuri, Shuqing Shi, Siddhant Gupta, Sneheel Sarangi, Sriram Ganapathi Subramanian, Taehun Cha, Toryn Q. Klassen, Wenming Tu, Weijian Fan, Wu Ruiyang, Xue Feng, Yali Du, Yang Liu, Yiding Wang, Yipeng Kang, Yoonchang Sung, Yuxuan Chen, Zhaowei Zhang, Zhihan Wang, Zhiqiang Wu, Ziang Chen, Zilong Zheng, Zixia Jia, Ziyan Wang
- Date/Time: [Poster Session 1] December 3rd (Wed) 11:00 - 14:00 (PST)
- Place: Exhibit Hall C,D,E #3603

< Link >
- [Poster] https://neurips.cc/virtual/2025/loc/san-diego/poster/121382
- [Paper] https://openreview.net/forum?id=yG4Fj0voJZ

FlowerTune: A Cross-Domain Benchmark for Federated Fine-Tuning of Large Language Models

- Authors: Yan Gao, Massimo R. Scamarcia, Javier Fernandez-Marques, Mohammad Naseri, Chong Ng, Dimitris Stripelis, Zexi Li, Tao Shen, Jiamu Bai, Daoyuan Chen, Zikai Zhang, Rui Hu, InSeo Song, KangYoon Lee, Hong Jia, Ting Dang, Junyan Wang, Zheyuan Liu, Daniel J. Beutel, Lingjuan Lyu (Sony AI), Nicholas Lane
- Date/Time: [Poster Session 4] December 4th (Thu) 16:30 — 19:30 (PST)
- Place: Exhibit Hall C,D,E #800

< Link >
- [Poster] https://neurips.cc/virtual/2025/poster/121489
- [Paper] https://arxiv.org/abs/2506.02961

LIFEBENCH: Evaluating Length Instruction Following in Large Language Models

- Authors: Wei Zhang, Zhenhong Zhou, Kun Wang, Junfeng Fang, Rongwu Xu, Yuanhe Zhang, Rui Wang, Ge Zhang, Xinfeng Li, Li Sun, Lingjuan Lyu (Sony AI), Yang Liu, Sen Su
- Date/Time: [Poster Session 3] December 4th (Thu) 11:00 — 14:00 (PST)
- Place: Exhibit Hall C,D,E #3502

< Link >
- [Poster] https://neurips.cc/virtual/2025/poster/121535
- [Paper] https://arxiv.org/abs/2505.16234

PolypSense3D: A Multi-Source Benchmark Dataset for Depth-Aware Polyp Size Measurement in Endoscopy

- Authors: Ruyu Liu, Lin Wang, Zhou Mingming, Jianhua Zhang, ZHANG HAOYU, Xiufeng Liu, Xu Cheng, Sixian Chan, Shen yanbin, Dai Sheng, Yuping Yan, Yaochu Jin, Lingjuan Lyu (Sony AI)
- Date/Time: [Mexico City Poster] December 3rd (Wed) 11:00 — 14:00 (PST)
- Place: Foyer

< Link >
- [Poster] https://neurips.cc/virtual/2025/poster/121870
- [Paper] https://openreview.net/forum?id=138y2wo6ok

TalkCuts: A Large-Scale Dataset for Multi-Shot Human Speech Video Generation

- Authors: Jiaben Chen, Zixin Wang, Ailing Zeng, Yang Fu, Xueyang Yu, Siyuan Cen, Julian Tanke (Sony AI), Yihang Chen, Koichi Saito (Sony AI), Yuki Mitsufuji (Sony AI/Sony Group Corporation), Chuang Gan
- Date/Time: [Poster Session 5] December 5th (Fri) 11:00 — 14:00 (PST)
- Place: Exhibit Hall C,D,E #5103

< Link >
- [Poster] https://neurips.cc/virtual/2025/poster/121841
- [Paper] https://arxiv.org/abs/2510.07249
- [Project Page] https://talkcuts.github.io/

VideoGameQA-Bench: Evaluating Vision-Language Models for Video Game Quality Assurance

- Authors: Mohammad Reza Taesiri, Abhijay Ghildyal (Sony Interactive Entertainment), Saman Zadtootaghaj (Sony Interactive Entertainment), Nabajeet Barman (Sony Interactive Entertainment), Cor-Paul Bezemer
- Date/Time: [Poster Session 4] December 4th (Thu) 16:30 — 19:30 (PST)
- Place: Exhibit Hall C,D,E #1405

< Link >
- [Poster] https://neurips.cc/virtual/2025/poster/121740
- [Paper] https://arxiv.org/pdf/2505.15952

Posters - Creative AI Track

'Studies for': A Human-AI Co-Creative Sound Artwork Using a Real-time Multi-channel Sound Generation Model

- Authors: Chihiro Nagashima (Sony Group Corporation), Akira Takahashi (Sony Group Corporation), Zhi Zhong (Sony Group Corporation), Shusuke Takahashi (Sony Group Corporation), Yuki Mitsufuji (Sony AI/Sony Group Corporation)
- Date/Time: [Creative AI Session 2] December 3rd (Wed) 16:30 - 19:30 (PST)
- Place: Upper Level Room 29A-D

< Link >
- [Paper] https://arxiv.org/abs/2510.25228
- [Project Page] https://www.ntticc.or.jp/en/archive/works/studies-for/

Large-Scale Training Data Attribution for Music Generative Models via Unlearning

- Authors: Woosung Choi (Sony AI), Junghyun Koo (Sony AI), Kin Wai Cheuk (Sony AI), Joan Serrà (Sony AI), Marco A. Martínez-Ramírez (Sony AI), Yukara Ikemiya (Sony AI), Naoki Murata (Sony AI), Yuhta Takida (Sony AI), Wei-Hsiang Liao (Sony AI), Yuki Mitsufuji (Sony AI/Sony Group Corporation)
- Date/Time: [Creative AI Session 1] December 3rd (Wed) 11:00 - 14:00 (PST)
- Place: Upper Level Room 29A-D

< Link >
- [Paper] https://arxiv.org/abs/2506.18312

Music Arena: Live Evaluation for Text-to-Music

- Authors: Yonghyun Kim, Wayne Chi, Anastasios N. Angelopoulos, Wei-Lin Chiang, Koichi Saito (Sony AI), Shinji Watanabe, Yuki Mitsufuji (Sony AI/Sony Group Corporation), Chris Donahue
- Date/Time: [Creative AI Session 2] December 3rd (Wed) 16:30 - 19:30 (PST)
- Place: Upper Level Room 29A-D

< Link >
- [Paper]: https://arxiv.org/abs/2507.20900
- [Project Page]: https://huggingface.co/spaces/music-arena/music-arena
- [Hugging Face]: https://huggingface.co/music-arena

Workshops

Organizers
GenProCC: 1st Workshop on Generative and Protective AI for Content Creation

- Date/Time: December 6th (Sat) 8:00 - 17:00 (PST)
- Place: Upper Level Room 23ABC
- Organizers: Wei-Yao Wang (Sony Group Corporation), Takashi Shibuya (Sony AI), Vali Lalioti, Qiyu Wu (Sony Group Corporation), Wei Wang, Shusuke Takahashi (Sony Group Corporation), Yuki Mitsufuji (Sony AI/Sony Group Corporation)

< Link >
- [Workshop] https://neurips.cc/virtual/2025/loc/san-diego/workshop/109545
- [Workshop Page] https://genprocc.github.io/

Invited Talk
Embodied World Models for Decision Making

- Date/Time: December 6th (Sat) 8:00 - 17:00 (PST) / [Keynote] 11:00 - 11:30 (PST)
- Place: Upper Level Room 30A-E
- Speaker: Peter Stone (The University of Texas at Austin & Sony AI)

< Link >
- [Workshop] https://neurips.cc/virtual/2025/loc/san-diego/workshop/109532
- [Workshop Page] https://embodied-world-models.github.io/

Invited Talk
Learning to Sence (L2S)

- Date/Time: December 7th (Sat) 8:00 - 17:00 (PST) / [Keynote] 10:00 - 10:40 (PST)
- Place: Upper Level Room 32AB
- Speaker: Daisuke Iso (Sony AI)

< Link >
- [Workshop] https://neurips.cc/virtual/2025/loc/san-diego/workshop/109563
- [Workshop Page] https://sites.google.com/view/l2s-workshop/home

Poster
LAW 2025: Bridging Language, Agent, and World Models for Reasoning and Planning
Automated Reward Design for Gran Turismo

- Date/Time: December 7th (Sun) 8:00 - 17:00 (PST)
- Place: Upper Level Ballroom 20D
- Authors: Michel Ma, Takuma Seno, Kaushik Subramanian (Sony AI), Peter R. Wurman (Sony AI), Peter Stone (The University of Texas at Austin/Sony AI), Craig Sherstan (Sony AI)

< Link >
- [Workshop] https://neurips.cc/virtual/2025/loc/san-diego/workshop/109552
- [Workshop Page] https://sites.google.com/view/law-2025
- [Paper] https://arxiv.org/abs/2511.02094

Poster
Structured Probabilistic Inference and Generative Modeling
Blind Inverse Problem Solving Made Easy by Text-to-Image Latent Diffusion

- Date/Time: December 6th (Sat) 8:00 - 17:00 (PST)
- Place: Upper Level Ballroom 20C
- Authors: Michail Dontas, Yutong He, Naoki Murata (Sony AI), Yuki Mitsufuji (Sony AI/Sony Group Corporation), J. Zico Kolter, Ruslan Salakhutdinov

< Link >
- [Workshop] https://neurips.cc/virtual/2025/loc/san-diego/workshop/109570
- [Workshop Page] https://spigmworkshopv3.github.io/
- [Paper] https://arxiv.org/abs/2412.00557

Poster
GenProCC: 1st Workshop on Generative and Protective AI for Content Creation
EnTruth: Tracing the Unauthorized Dataset Usage in Diffusion Models

- Date/Time: December 6th (Sat) 8:00 - 17:00 (PST)
- Place: Upper Level Room 23ABC
- Authors: Jie Ren, Yingqian Cui, Chen Chen (Sony AI), Yue Xing, Hui Liu, Lingjuan Lyu (Sony AI)

< Link >
- [Workshop] https://neurips.cc/virtual/2025/loc/san-diego/workshop/109545
- [Workshop Page] https://genprocc.github.io/
- [Paper] https://arxiv.org/abs/2406.13933

Poster
GenProCC: 1st Workshop on Generative and Protective AI for Content Creation
SHIELD: A Benchmark Study on Zero-Shot Detection of AI-Edited Images with Vision Language Models

- Date/Time: December 6th (Sat) 8:00 - 17:00 (PST)
- Place: Upper Level Room 23ABC
- Authors: Siyuan Cheng, Hanxi Guo, Zhenting Wang, Xiangyu Zhang, Lingjuan Lyu (Sony AI)

< Link >
- [Workshop] https://neurips.cc/virtual/2025/loc/san-diego/workshop/109545
- [Workshop Page] https://genprocc.github.io/
- [Project Page] https://github.com/Megum1/SHIELD

Poster
GenProCC: 1st Workshop on Generative and Protective AI for Content Creation
FlashFoley: Fast Interactive Sketch2Audio Generation

- Date/Time: December 6th (Sat) 8:00 - 17:00 (PST)
- Place: Upper Level Room 23ABC
- Authors: Zachary Novack, Koichi Saito (Sony AI), Zhi Zhong (Sony Group Corporation), Takashi Shibuya (Sony AI), Shuyang Cui (Sony Group Corporation), Julian McAuley, Taylor Berg-Kirkpatrick, Christian Simon (Sony Group Corporation), Shusuke Takahashi (Sony Group Corporation), Yuki Mitsufuji (Sony AI/Sony Group Corporation)

< Link >
- [Workshop] https://neurips.cc/virtual/2025/loc/san-diego/workshop/109545
- [Workshop Page] https://genprocc.github.io/
- [Paper] https://openreview.net/forum?id=Fsqxyyjysv
- [Project page] https://anonaudiogen.github.io/web/

Poster
Artificial Intelligence for Music: Where Creativity Meets Computation
FlashFoley: Fast Interactive Sketch2Audio Generation

- Date/Time: December 7th (Sun) 8:00 - 17:00 (PST)
- Place: Upper Level Room 27AB
- Authors: Zachary Novack, Koichi Saito (Sony AI), Zhi Zhong (Sony Group Corporation), Takashi Shibuya (Sony AI), Shuyang Cui (Sony Group Corporation), Julian McAuley, Taylor Berg-Kirkpatrick, Christian Simon (Sony Group Corporation), Shusuke Takahashi (Sony Group Corporation), Yuki Mitsufuji (Sony AI/Sony Group Corporation)

< Link >
- [Workshop] https://neurips.cc/virtual/2025/loc/san-diego/workshop/109534
- [Workshop Page] https://aiformusicworkshop.github.io/
- [Paper] https://openreview.net/forum?id=Fsqxyyjysv
- [Project page] https://anonaudiogen.github.io/web/

EXPO Workshop

Creative and Protective AI for Music and Entertainment

- Organizers: Chieh-Hsin Lai (Sony AI), Kazumi Fukuda (Sony AI), Yuki Mitsufuji (Sony AI/Sony Group Corporation)
- Date/Time: December 2nd (Tue) 12:00 - 13:30 (PST)
- Place: Exhibit Hall F

< Link >
- [EXPO Workshop] https://neurips.cc/virtual/2025/loc/san-diego/128679

Exhibition Booth
Open Hours

Visit our booth at the exhibition to explore our latest technology firsthand and engage with our team.

Location: #1519 (Hall A & B)
Sony Booth Open Hours:
- December 2nd (Tue) 12:00 - 20:00 (PST)
- December 3rd (Wed) 09:00 - 17:00 (PST)
- December 4th (Thu) 09:00 - 17:00 (PST)
- December 5th (Fri) 09:00 - 12:00 (PST)

Exhibition Booth
Technology Presentation

The Principles of Diffusion Models

- Presenter : Chieh-Hsin Lai
- Date/Time :
(1) December 3rd (Wed) 09:35 - 09:50
(2) December 4th (Thu) 14:00 - 14:15

< Link >
- [Paper] https://arxiv.org/pdf/2510.21890

D2USt3R: Enhancing 3D Reconstruction with 4D Pointmaps for Dynamic Scenes

- Presenters : Jisang Han, Honggyu An, Kazumi Fukuda
- Date/Time :
(1) December 2nd (Tue) 16:30 - 16:45 (PST)
(2) December 3rd (Wed) 11:30 - 11:45 (PST)

< Link >
- [Project Page] https://cvlab-kaist.github.io/DDUSt3R/

Large-Scale Training Data Attribution for Music Generative Models via Unlearning

- Presenters : Woosung Choi
- Date/Time :
(1) December 2nd (Tue) 16:15 - 16:30 (PST)
(2) December 4th (Thu) 09:35 - 09:50 (PST)

< Link >
- [Paper] https://arxiv.org/abs/2506.18312

'Studies for': A Human-AI Co-Creative Sound Artwork Using a Real-time Multi-channel Sound Generation Model

- Presenter : Chihiro Nagashima
- Date/Time :
(1) December 3rd (Wed) 11:15 - 11:30 (PST)
(2) December 4th (Thu) 16:35 - 16:50 (PST)

< Link >
- [Paper] https://arxiv.org/abs/2510.25228
- [Project Page] https://www.ntticc.or.jp/en/archive/works/studies-for/

Multimodal NLP for Content Creation

- Presenter : Qiyu Wu
- Date/Time : December 4th (Thu) 14:15 - 14:30 (PST)

< Link >
- [ACL Anthology] https://aclanthology.org/2025.emnlp-main.653/
- [Paper] https://arxiv.org/abs/2504.05154
- [Paper] https://arxiv.org/abs/2503.20871
- [CDP Challenege] https://www.aicrowd.com/challenges/commonsense-persona-grounded-dialogue-challenge-2025

Exhibition Booth
Technology Demonstrations & Introductions

Demonstration
Gran Turismo Sophy

A superhuman racing AI agent capable of driving over 500 cars on multiple tracks, available to all Gran Turismo 7 (PS5) players worldwide.

< Link >
- https://www.gran-turismo.com/us/gran-turismo-sophy/

Video
FHIBE | Fair Human-Centric Image Benchmark

The Fair Human-Centric Image Benchmark (pronounced Fee-Bee) is the first publicly available, globally diverse, consent-driven dataset built specifically to evaluate fairness in human-centric computer vision tasks.

< Link >
- https://fairnessbenchmark.ai.sony/

Video
Sony Women in Technology Award with Nature

The Sony Women in Technology Award with Nature celebrates remarkable women spearheading advancements in technology, driving positive change for society and the planet. Each year, the award recognizes three outstanding early to mid-career researchers with a prize of $250,000 USD each to accelerate breakthroughs and a chance to showcase work on Nature.com.

< Link >
- https://womenintechnology.sony.com/

Event Report

Sony had a strong presence at NeurIPS 2025 in San Diego, US, where we introduced our latest research and technologies.
We were delighted to welcome many visitors to our booth and engage in meaningful conversations with researchers and professionals from around the world.
Our Technology Blog captures these moments along with details of our accepted papers.

Visit to learn more about our contributions:
https://www.sony.com/en/SonyInfo/technology/stories/entries/NeurIPS2025_report/

Follow us on LinkedIn!

Sony Technology - https://www.linkedin.com/company/sony_technology/

Sony Women in Technology Award with Nature

This annual award honors outstanding early to mid-career women researchers pioneering breakthroughs in science, technology, engineering, and mathematics.
Each year, Sony and Nature recognize three researchers with a prize of $250,000 USD each and a chance to showcase work on nature.com.

The application period for the 2026 award is now closed. Eligible NeurIPS attendees are encouraged to apply next year. Join our newsletter to be the first to know when the next cycle opens.

Career Information

We look forward to working with highly motivated individuals to fill the world with emotion and to pioneer future innovation through dreams and curiosity. If interested, please access our career site and/or consider visiting the Sony booth (Booth#: 1519) at the NeurIPS exhibition hall (Hall A & B) to know more about Sony Group.

Career Site Link: https://www.sony.com/en/SonyInfo/Careers/

Sony Group Technology Portal

You can explore our technology by clicking HERE.

Back to Academic Conferences

Technology