Ax Chicago Y. Park, Edward P. Chandler, Yuyang Hu, Michael T. McCann, Cristina Garcia-Cardona, Brendt Wohlberg, Ulugbek S. Kamilov 4/7/2026

Stochastic Generative Plug-and-Play Priors

Framework combining score-based diffusion models as priors in plug-and-play optimization for imaging inverse problems.

Ax Yuqi Zhu, Jintian Zhang, Zhenjie Wan, Yujie Luo, Shuofei Qiao, Zhengke Gui, Da Zheng, Lei Liang, Huajun Chen, Ningyu Zhang 4/7/2026

LightThinker++: From Reasoning Compression to Memory Management

Method for LLMs to dynamically compress intermediate reasoning thoughts into compact representations while maintaining reasoning quality.

Ax Anjun Gao, Feng Wang, Zhenglin Wan, Yueyang Quan, Zhuqing Liu, Minghong Fang 4/7/2026

SecureAFL: Secure Asynchronous Federated Learning

SecureAFL: Asynchronous federated learning framework addressing straggler problem while maintaining security.

Ax Hanchen Li, Runyuan He, Qizheng Zhang, Changxiu Ji, Qiuyang Mang, Xiaokun Chen, Lakshya A Agrawal, Wei-Liang Liao, Eric Yang, Alvin Cheung, James Zou, Kunle Olukotun, Ion Stoica, Joseph E. Gonzalez 4/7/2026

Combee: Scaling Prompt Learning for Self-Improving Language Model Agents

Combee framework for scaling prompt learning in LLM agents enabling efficient self-improvement through system prompt optimization across parallel runs.

Ax Anushree Sinha, Srivaths Ranganathan, Debanshu Das, Abhishek Dharmaratnakar 4/7/2026

Beyond Fluency: Toward Reliable Trajectories in Agentic IR

Position paper analyzing failure modes in agentic IR systems where early errors cascade despite linguistic fluency, causing misalignment between reasoning and execution.

Ax Edward Hirst, Henrique N. S\'a Earp, Tom\'as S. R. Silva 4/7/2026

Minimising Willmore Energy via Neural Flow

Neural Willmore flow approach using neural architectures and PINN-style loss functions to minimize Willmore energy on 2D surfaces.