Microsoft is a proud sponsor of the 38th Annual Conference on Neural Information Processing Systems. (Opens in new tab) (NeurIPS). This interdisciplinary conference brings together researchers in machine learning, neuroscience, statistics, optimization, computer vision, natural language processing, life sciences, natural sciences, social sciences, and other adjacent fields.
We are pleased to announce that Microsoft has accepted over 100 papers at this year’s conference. Please stop by our booth (#445) at the back of Hall A. Speak with our team, learn more about Microsoft research, and explore our open career positions.
Invited keynote speech
Congratulations to Mr. Lidong Zhou, who was selected as the keynote speaker. Mr. Lidong will speak on co-innovation of AI and systems.
Interested in being contacted about career opportunities at Microsoft? Share your contact details here: Careers at Microsoft – NeurIPS 2024 (Opens in new tab)
oral
CVQA: Culturally Diverse Multilingual Visual Question Answering Benchmark: Pranjal Chitale Not All Tokens Required for Pre-Training: Yeyun Gong, Xiao Liu, Yelong Shen, Ruochen Xu, Jian Jiao, Nan Duan, Weizhu Chen Reinforcement learning under latent dynamics: Towards statistical and algorithmic modularity: Dylan J Foster, Akshay Krishnamurthy VASA-1: Realistic audio-driven speaking faces generated in real time: Sicheng Xu, Guojun Chen, Yu-Xiao Guo, Jiaolong Yang, Chong Li, Zhenyu Zang, Yizhong Zhang, Xin Tong, Baining Gu Cache only once: Language model Decoder-Decoder Architecture: Li Dong, Yi Zhu, Shaohan Fan, Wang Wenhui, Zhang Kuanlu, Full Wei
spotlight session
Studying plasticity loss in on-policy deep reinforcement learning: Jordan Ash Advances in spiking neural networks for sequential modeling with central pattern generators: Dongqi Han, Yansen Wang Beyond Assouad, Fano, Le Cam: Unifying statistical inference and interactive Decision-making towards the lower bound: Dylan J Foster BPQP: Differentiable Convex Optimization Framework Efficient end-to-end learning: Xiao Yang, Xu Yang, Weiqing Liu, Lewen Wang, Jiang Bian Generalizing configurations across distribution shifts with sparse tree operations: Paul Smolensky, Jianfeng Gao, Roland Fernandez Lessons learned from the dataset and 2024 SaTML LLM capture – The Flag Competition: Reshmi Ghosh, Ahmed – Salem, Giovanni Cherubin, Santiago Zanella-Beguelin, Sahar Abdelnabi Diffusion of World Modeling: Atari The importance of visual details in: Anssi Kanervisto, Tim Pearce, Cuiling Lan, Yan Lu DiscoveryWorld: A virtual environment for the development and evaluation of automated scientific discovery agents: Marc-Alexandre CôtéEfficient LLM with continuous attacks Adversarial Training: Alessandro Sordoni ERBench: An Entity-Relation-Based Automatically Verifiable Hallucination Benchmark for Large-Scale Language Models: Ruochen Xu, Xing Xie Generalized Linear Bandits with Limited Adaptability: Nirjhar Das, Gaurav Sinha Human-Aware Vision and Language Navigation: Bridging to Reality with Dynamic Simulations Human Interaction: Identifying Training Dynamics Equivalent to Qi Dai: Juan Bello-Rivas Procgen’s Implicit Curriculum Made Explicit: Kaixin Wang Is Replication of Behavior All You Need? Understanding the Horizon in Imitation Learning: Dylan J Foster, Adam Block MInference: Dynamic Sparse Accelerating prefilling of long context LLMs with attention: Huiqiang Jiang, Chengruidong Zhang, Qianhui Wu, Xufang Luo, Surin Ahn, Zhenhua Han, Amir Abdi, Chin -Yew Lin, Yuqing Yang, Lili Qiu “The Power of Reset” Online Reinforcement Learning : Dylan J Foster VideoGUI: Benchmarking GUI automation from educational videos: Linjie Li, Lijuan Wang Voila-A: Visual Language Model and User Gaze Alignment Note: Lei Ji, Nan Duan
General Chair: Lester McKee
Program Chair Assistant: Babak Rahmani
Competition Chairman: Tao Ching
Workshop Chair: Adil Salim
Communication Chair: Alex X Lu
microsoft research forum
Join us for an ongoing conversation about science and technology research in the general AI era. This series explores recent research advances, bold new ideas, and important discussions with the global research community. Sign up to tune in to future episodes or watch previous episodes available on demand.
